WO2023125698A1 - 清洁设备及其控制方法和控制装置 - Google Patents
清洁设备及其控制方法和控制装置 Download PDFInfo
- Publication number
- WO2023125698A1 WO2023125698A1 PCT/CN2022/142944 CN2022142944W WO2023125698A1 WO 2023125698 A1 WO2023125698 A1 WO 2023125698A1 CN 2022142944 W CN2022142944 W CN 2022142944W WO 2023125698 A1 WO2023125698 A1 WO 2023125698A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cleaning
- obstacle
- room
- robot
- laser sensor
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
- A47L11/24—Floor-sweeping machines, motor-driven
Definitions
- the present disclosure relates to the technical field of equipment control, and in particular to a cleaning equipment control method, a cleaning equipment control device, a cleaning equipment and a readable storage medium.
- the intelligence of cleaning equipment is mainly reflected in the improvement of navigation motion accuracy, the identification and collision avoidance of isolated objects, and the cleaning of divided areas without omission.
- the cleaning strategy there is no fine control method for the cleaning strategy, resulting in a single cleaning strategy for the cleaning equipment and not intelligent enough.
- the present disclosure aims to solve one of the technical problems in the related art at least to a certain extent. Therefore, the first purpose of the present disclosure is to propose a cleaning device control method, which can control the cleaning device based on at least one of the room characteristic parameters and obstacle parameters, and realize different cleaning control methods adopted in different scenarios , fully meet the needs of users.
- the second object of the present disclosure is to propose a control device for cleaning equipment.
- a third object of the present disclosure is to propose a cleaning device.
- the fourth object of the present disclosure is to provide a readable storage medium.
- an embodiment of the present disclosure proposes a cleaning device control method, the method includes: detecting the operating environment of the cleaning device, and acquiring environmental characteristic parameters, wherein the environmental characteristic parameters include At least one of the room characteristic parameter and the obstacle parameter; according to at least one of the room characteristic parameter and the obstacle parameter, the cleaning device is controlled to perform cleaning.
- the room characteristic parameters include ground characteristic information of the room
- the controlling the cleaning equipment to perform cleaning according to the room characteristic parameters includes: determining control information according to the ground characteristic information, and The control information controls the cleaning equipment to work.
- the cleaning equipment can be a sweeping robot, a mopping robot, an integrated sweeping and mopping machine, etc., and can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with equipment such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, the corresponding control information is determined according to the ground feature information in the room, so that the cleaning equipment performs cleaning work according to the control information.
- the cleaning equipment can realize more intelligent and customized cleaning based on the ground conditions of the room, and improve the efficiency and accuracy of room cleaning.
- the ground feature information includes the ground paving material
- the control information is determined according to the ground feature information, including: determining the first control information corresponding to the ground paving material; wherein, the first control information includes at least one of the following: water output , cleaning times, fan suction, moving speed.
- the ground feature information may include the material of the ground, for example, the material includes wood (such as floor), quality, stone (such as floor tiles) and the like.
- the control information of the cleaning device includes first control information, and the first control information may be at least one of water output, cleaning times, fan suction, and moving speed.
- the cleaning equipment based on the material of the floor of the room, correspondingly determine the water output, fan suction, and moving speed of the cleaning equipment, and determine the number of times the cleaning equipment cleans the room.
- the cleaning device can realize more personalized and intelligent cleaning of the room based on the material laid on the floor in the room.
- the water yield when the ground paving material is wood is smaller than the water yield when the ground paving material is porcelain or stone.
- the water output of the cleaning equipment can be relatively increased, thereby improving the cleaning degree of the floor tiles and ensuring the cleanliness of the floor tiles. Effect.
- the number of times of cleaning when the ground paving material is wood is greater than that of the case where the ground paving material is porcelain or stone.
- the water output of the cleaning equipment can be relatively increased, thereby improving the cleaning degree of the floor tiles and ensuring the cleanliness of the floor tiles.
- the number of cleanings is relatively reduced to reduce the waste of electric energy for cleaning equipment.
- the ground feature information includes the direction of laying the ground
- determining the control information according to the ground feature information includes: determining the second control information corresponding to the laying direction of the ground; wherein, the second control information is the cleaning direction of the cleaning equipment Consistent with the laying direction of the ground.
- the ground feature information may include the direction in which the ground is laid, that is, the texture of the floor or floor tiles laid on the ground.
- the control information of the cleaning device includes second control information, and the second control information may be control information of the cleaning direction of the cleaning device.
- the cleaning direction of the cleaning equipment is correspondingly determined so that the cleaning direction of the cleaning equipment is the same as the laying direction of the floor, that is to say, the cleaning direction of the cleaning equipment is parallel to the laying direction of the floor.
- the cleaning equipment can clean parallel to the direction in which the floor is laid in the room, thereby reducing the residual dust and water stains in the gaps of the floor or floor tiles, and making the cleaning marks of the cleaning equipment on the floor or floor tiles not chaotic, improving Cleaning effect.
- the ground feature information includes ground size
- determining the control information according to the ground feature information includes: determining the room type according to the ground size; and determining third control information corresponding to the room type.
- the ground feature information may include the ground size, that is, the size of the room, and the control information of the cleaning equipment includes the third control information.
- the size of the room is determined based on the floor size of the room, thereby determining the type of the room, and then the third control information of the cleaning device is correspondingly determined according to the type of the room.
- the cleaning of the cleaning equipment can be adaptively controlled according to the type of the room, thereby improving the efficiency and accuracy of room cleaning.
- the room type includes at least one of the following: bedroom, living room, kitchen, bathroom; the third control information includes at least one of the following: room cleaning sequence, cleaning dose, and disinfectant dose.
- the room may include a bedroom, a living room, a kitchen or a bathroom, and the cleaning methods of the cleaning equipment in different types of rooms may be different.
- the third control information of the cleaning equipment may be at least one of room cleaning sequence, cleaning dose, and disinfectant dose. For example, when the room is determined to be a bedroom, the room can be cleaned first; when the room is determined to be the living room, the living room can be cleaned after the bedroom is cleaned; when the room is determined to be the kitchen or bathroom, the cleaning equipment can spray detergent , Disinfectants, etc.
- the ground feature information includes the socket position
- determining the control information according to the ground feature information includes: determining fourth control information corresponding to the socket position.
- the ground feature information may include the position of the socket, that is, the position of the socket installed on the ground, and the control information of the cleaning device includes fourth control information, which is used to control the moving route of the cleaning device.
- the movement route of the cleaning equipment is controlled to avoid the risk of electric leakage at the cleaning socket location of the cleaning equipment and improve the safety during the cleaning process.
- the fourth control information is that the cleaning range of the cleaning device is outside the preset range of the socket position.
- the cleaning device can keep a certain safe distance from the socket during cleaning, that is, clean outside the preset range from the socket, for example, within a distance
- the socket is 10 cm or 20 cm away for cleaning.
- the ground feature information includes the room boundary feature of the room
- determining the control information according to the ground feature information includes: determining the control information corresponding to the room boundary feature based on the height of the room boundary feature being less than or equal to a preset threshold .
- the ground feature information may include the room boundary features of the room, such as door crossing strips, threshold stones, sliding door tracks, and the like.
- the cleaning device can be controlled to clean the position; when it is recognized that the height of the room boundary feature exceeds the preset threshold, it indicates that the room If the height of the boundary feature is high, the cleaning equipment will not clean the position, preventing the cleaning equipment from being stuck at the room boundary feature.
- acquiring the ground feature information of the room includes: acquiring the room boundary feature of the room; and acquiring the room ground feature information based on the cleaning equipment entering the room through the room boundary feature.
- the room boundary feature is an important basis for room division, which may include door bars, threshold stones, sliding door tracks, and the like.
- the ground feature information of the room is collected, and then the cleaning equipment is controlled to clean the room according to the control information corresponding to the ground feature information.
- the boundary characteristics of the room it can be accurately determined whether the cleaning equipment enters the room, so that the ground feature information is collected after entering the room, and the timely and accurate collection of the ground feature information is realized.
- the room characteristic parameters include room characteristic information of the room
- the obstacle parameters include the positions of objects in the room
- Cleaning the device includes: determining cleaning parameters according to the room feature information; controlling the cleaning device to avoid the position of the object and work according to the cleaning parameters.
- the cleaning device can be a sweeping robot, a mopping robot, a sweeping and mopping machine, etc., which can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with cameras, infrared sensors and other equipment, which can collect room characteristic information in the room and the specific position of fixed objects in the room.
- the position characteristic information of the object can indicate the type of room, the floor layout in the room and so on.
- the corresponding cleaning parameters are determined according to the room characteristic information in the room, and the route of the cleaning equipment is determined according to the specific position of the fixed object, so that the cleaning equipment can avoid the specific position of the fixed object and move, and perform cleaning work according to the control information .
- the cleaning equipment can adaptively set a reasonable cleaning method based on the specific conditions of the room, realize more intelligent and customized cleaning, and improve the efficiency and accuracy of room cleaning.
- the room characteristic information includes the room type
- determining the cleaning parameters according to the room characteristic information includes: determining the first cleaning parameter corresponding to the room type; wherein, the first cleaning parameter includes at least one of the following: cleaning priority, Cleanliness.
- the room feature information may include the type of the room, and then the first cleaning parameter of the cleaning device can be correspondingly determined according to the type of the room.
- the cleaning parameters of the cleaning device include the first cleaning parameter
- the room may include a bedroom, a living room, a kitchen or a bathroom
- the first cleaning parameters such as the cleaning priority and cleaning degree of the cleaning device in different types of rooms may be different.
- the cleaning mode of the cleaning equipment can be adaptively controlled according to the type of the room, thereby improving the efficiency and accuracy of room cleaning.
- the cleaning priority when the room type is a bedroom or a living room is higher than that when the room type is a bathroom or a kitchen.
- the cleaning priority is greater than or equal to the first threshold, and based on the room being a bathroom or a kitchen, the cleaning priority is less than the first threshold.
- the cleanliness of the room type is a bathroom or a kitchen, which is greater than that of a bedroom or a living room.
- the degree of dirtiness of the bathroom or the kitchen is greater than that of the bedroom or the living room
- the degree of cleanliness of the bathroom or the kitchen is also greater. That is to say, when the room type is a bathroom or a kitchen, the cleanliness degree is greater than or equal to the second threshold, and when the room type is a bedroom or a living room, the cleanliness degree is less than the second threshold.
- the room characteristic information includes floor paving materials
- determining the cleaning parameters according to the room characteristic information includes: determining a second cleaning parameter corresponding to the floor paving materials; wherein the second cleaning parameters include at least one of the following: Water output, cleaning times, fan suction.
- the room feature information may include the material of the floor, for example, the material includes wood (such as floor), porcelain, stone (such as floor tile), concrete, and the like.
- the cleaning parameters of the cleaning device include a second cleaning parameter, and the second cleaning parameter may be at least one of water output, cleaning times, and fan suction.
- the water output, cleaning times, fan suction, etc. of the cleaning equipment are correspondingly determined.
- the cleaning device can realize more personalized and intelligent cleaning of the room based on the material laid on the floor in the room.
- the water yield when the ground paving material is wood, the water yield when the ground paving material is porcelain or stone, and the water yield when the ground paving material is concrete increases sequentially.
- the water output of the cleaning equipment is less than or equal to the third threshold; when the material of the ground paving is porcelain or stone, the water output of the cleaning equipment is greater than the third threshold
- the threshold is less than or equal to the fourth threshold; in the case that the floor material is concrete, the water output of the cleaning equipment is greater than the fourth threshold, wherein the fourth threshold is greater than the third threshold.
- the amount of water output by the cleaning equipment can be relatively reduced, thereby reducing the damage of water stains to the floor and protecting the floor. .
- the cleaning equipment can be controlled to moderate the water output during cleaning, thereby improving the cleaning degree of the floor tiles and ensuring the cleanliness of the floor tiles. Effect.
- the water output of the cleaning equipment can be relatively increased, thereby improving the degree of cleaning of the cement floor and ensuring the cleaning effect.
- the number of times of cleaning when the floor material is wood, the number of cleaning times when the material of the floor is porcelain or stone, and the number of times of cleaning when the material of the floor is concrete decreases in turn.
- the number of times the cleaning equipment cleans is greater than or equal to the fifth threshold; when the floor material is porcelain or stone, the cleaning frequency of the cleaning equipment is less than the fifth threshold.
- the threshold is greater than or equal to the sixth threshold; when the floor material is concrete, the cleaning frequency of the cleaning equipment is less than the sixth threshold, wherein the sixth threshold is less than the fifth threshold.
- the amount of water output by the cleaning equipment can be relatively reduced, thereby reducing the damage of water stains to the floor and protecting the floor. , and at the same time increase the cleaning frequency of the cleaning equipment to ensure the cleaning effect.
- the water output and cleaning frequency of the cleaning equipment can be controlled to improve the cleaning degree of the floor tiles , to ensure the cleaning effect.
- the water output of the cleaning equipment can be relatively increased, thereby improving the degree of cleaning of the cement floor and ensuring the cleaning effect. Relatively reduce the number of cleanings to reduce the waste of electric energy for cleaning equipment.
- controlling the position of the cleaning device to avoid the object includes: determining relative position information between the object and the floor of the room; and controlling the position of the cleaning device to avoid the object according to the relative position information.
- the relative position information between the object and the ground in the room is determined, and the relative position information can indicate whether there is a gap between the object and the ground, and if there is a gap, the size of the gap. Then, according to whether there is a gap or the size of the gap when there is a gap, it is controlled whether the cleaning device avoids the movement of the object.
- acquiring the environment feature parameters includes: collecting a first image of the room, identifying the room according to the first image; and determining the room feature information corresponding to the room and the position of the object according to the preset corresponding relationship.
- the specific room that the cleaning equipment enters is determined based on the first image, and then according to the preset correspondence between the room and the room characteristic information and the position of the object, determine the The room feature information corresponding to the room and the position of the object.
- the preset corresponding relationship between the room and the room feature information and the position of the object is stored in advance, and after the specific room is specified according to the first image, the room feature information and the position of the object corresponding to the room can be obtained .
- the pre-stored room feature information and the position of the object can be obtained according to the preset corresponding relationship, and there is no need to identify the room feature information and the position of the object through the image, which improves the room feature information. and the accuracy and timeliness of object location acquisition.
- the cleaning equipment before acquiring the environmental characteristic parameters, it also includes: controlling the cleaning equipment to move in the room and collecting a second image of the room; determining the room characteristic information and the position of the object according to the second image, and establishing a preset Set up a corresponding relationship.
- the cleaning equipment is controlled to move in the room, and the second image of the room is acquired during the movement, so as to realize positioning and mapping. Further, the room characteristic information and the position of the object of the room are identified in the second image, and the room name is stored in correspondence with the room characteristic information and the position of the object, so as to establish a preset correspondence.
- the room feature information and the position of the object are determined, so as to realize the classification and formulation of cleaning plans, and improve the intelligence of the cleaning equipment.
- the cleaning device is a cleaning robot, wherein, according to the obstacle parameter, controlling the cleaning device to perform cleaning includes: after obtaining the operation instruction, starting the cleaning function in the target area at a first rate; There is a target obstacle at the first distance in the current forward direction, based on the camera device installed on the cleaning robot, the recognition result for determining the object category corresponding to the target obstacle is obtained; based on the recognition result, select the corresponding A target obstacle avoidance route, the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; based on the target obstacle avoidance route, the cleaning robot is operated.
- the selection of a corresponding target obstacle avoidance route based on the identification result includes:
- a first obstacle avoidance route is selected, and the first obstacle avoidance route is used to instruct the cleaning robot to avoid the the course of the target obstacle;
- a second obstacle avoidance route is selected, and the second obstacle avoidance route is used to instruct the cleaning robot to avoid the target obstacle, by Other routes run in the forward direction.
- selecting a first obstacle avoidance route includes:
- the first obstacle avoidance route is calculated and generated.
- the method further includes:
- selecting a second obstacle avoidance route includes:
- a rotation angle for rotating the forward direction of the cleaning robot is determined, and based on the rotation angle, the second obstacle avoidance route is calculated and generated.
- the method further includes:
- the method further includes:
- the first speed is switched to a second speed, wherein the second speed is lower than the first speed, and the first speed is lower than the first speed. the second distance is greater than the first distance;
- the method before starting the cleaning function in the target area at the first rate, the method further includes:
- sample obstacle information includes parameters of the sample obstacle and object categories corresponding to the sample obstacle
- each sample obstacle is projected onto the initial grid map to generate a semantic map
- start the cleaning function in the target area at the first rate including:
- a cleaning function is started in the target area at the first rate based on the semantic map.
- the obtaining the recognition result for determining the object category corresponding to the target obstacle based on the camera device set on the cleaning robot includes:
- the object features include at least one of size features, color features, and contour features;
- the method before using the camera device to obtain the image of the target obstacle, the method further includes:
- sample images include at least one obstacle feature
- the preset image semantic segmentation model is trained to obtain the image detection and classification model satisfying the preset condition, the image The detection and classification model is used to determine the object category corresponding to the target obstacle.
- the cleaning function is started in the target area at the first rate; if it is detected that there is a target obstacle at the first distance in the current direction of travel, based on the camera device installed on the cleaning robot, the used Determine the recognition result of the object category corresponding to the target obstacle; based on the recognition result, select the corresponding target obstacle avoidance route, and the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; based on the target obstacle avoidance route , to run the cleaning robot.
- the robot detects an obstacle ahead, it can select different obstacle avoidance routes according to whether the object type of the obstacle can be identified.
- the purpose of performing different obstacle avoidance methods according to different types of object contours is achieved. Furthermore, the obstacle avoidance ability of the cleaning robot is improved, and the collision avoidance function is realized, which also avoids the problem that the obstacle cannot be completely avoided due to the limited sensing range of the robot.
- the cleaning device is a robot, and the robot is equipped with a first laser sensor and a second laser sensor, the inclination angle of the first laser sensor on the robot and the inclination angle of the second laser sensor on the robot
- the inclination angle on the robot is different, and the installation height of the first laser sensor on the robot and the installation height of the second laser sensor on the robot are also different, wherein, according to the obstacle parameters, the control of the Cleaning equipment for cleaning, including:
- the first sensing distance being the distance between the spot landing point of the laser light emitted by the first laser sensor and the first laser sensor;
- the second sensing distance is the distance between the spot landing point of the laser light emitted by the second laser sensor and the second laser sensor;
- the inclination angle and the first sensing distance determine the first landing point coordinates, the first landing point coordinates are the laser light emitted by the first laser sensor The coordinates of the falling point of the light spot;
- the inclination angle and the second sensing distance, the second landing point coordinates are determined, and the second landing point coordinates are the laser light emitted by the second laser sensor The coordinates of the falling point of the light spot;
- the coordinates of the first landing point the coordinates of the second landing point and the preset allowable obstacle clearance height, identify the obstacle type corresponding to the target area, and the target area is the coordinates of the first landing point and the second landing point coordinates.
- the movement of the robot is controlled according to the obstacle type.
- the installation height of the first laser sensor is greater than the installation height of the second laser sensor, and the distance that the laser emitted by the first laser sensor can reach is greater than the distance that the laser emitted by the second laser sensor can reach distance, the coordinates of the first landing point are (Xa, Ya), and before identifying the obstacle type corresponding to the target area, the method further includes:
- the coordinates of the second landing point are (Xb, Yb), the allowable obstacle clearance height is h, and according to the coordinates of the first landing point, the coordinates of the second landing point and the preset allowable Obstacle clearance height, identifying the obstacle type corresponding to the target area, including:
- the Ya is less than -h, and the Yb is not greater than the Ya, then it is determined that the obstacle type corresponding to the target area is a large step;
- the Ya is less than the -h, and the Yb is less than 0 but greater than the Ya, then it is determined that the obstacle type corresponding to the target area is a downhill slope;
- the Ya is less than the -h and the Yb is not less than 0, it is determined that the obstacle type corresponding to the target area is a large step.
- the obstacle type is a downhill slope
- the controlling the movement of the robot according to the obstacle type includes:
- the movement of the robot is controlled according to the angle corresponding to the downhill slope and the preset allowable climbing degree.
- the coordinates of the second landing point are (Xb, Yb), the allowable obstacle clearance height is h, and according to the coordinates of the first landing point, the coordinates of the second landing point and the preset allowable Obstacle clearance height, identifying the obstacle type corresponding to the target area, including:
- the Ya is greater than the h, and the Xb is not less than the Xa, it is determined that the obstacle type corresponding to the target area is a high obstacle;
- the obstacle type corresponding to the target area is an uphill slope.
- the obstacle type is an uphill ramp
- the controlling the movement of the robot according to the obstacle type includes:
- the movement of the robot is controlled according to the angle corresponding to the uphill ramp and the preset allowable climbing degree.
- the installation height of the first laser sensor is greater than the installation height of the second laser sensor, and the reachable distance of the laser light emitted by the first laser sensor is greater than the reachable distance of the laser light emitted by the second laser sensor.
- the coordinates of the first landing point are (Xa, Ya)
- the allowable obstacle clearance height is h, and the method also includes:
- the robot is controlled to switch from the normal mode to the low-speed mode, the target height is greater than 0 and less than the h, and the speed of the low-speed mode is lower than the normal mode speed;
- the robot is controlled to switch from the normal mode to the low speed mode.
- the first laser sensor is a line laser sensor
- the second laser sensor is a laser ranging sensor
- the first landing point coordinates and the second landing point coordinates obtained based on the first laser sensor and the second laser sensor are coordinates corresponding to two different positions. Since the coordinates of two different positions can reflect the height difference between the two positions, combined with the preset allowable obstacle clearance height, the obstacle type corresponding to the area where the two different positions are located can be quickly and accurately identified. For example, identify whether the obstacle type is a step that the robot can climb.
- another embodiment of the present disclosure also proposes a control device for cleaning equipment, including: detection equipment, used to detect the operating environment of the cleaning equipment and obtain environmental characteristic parameters, wherein the The environmental characteristic parameters include at least one of room characteristic parameters and obstacle parameters; the control device is configured to control the cleaning device to perform cleaning according to at least one of the room characteristic parameters and the obstacle parameters.
- the cleaning device is a cleaning robot, wherein the control device includes:
- the first obtaining module is configured to start the cleaning function in the target area at a first rate after obtaining the operation instruction
- the first detection module is configured to, if it is detected that there is a target obstacle at a first distance in the current forward direction, based on the camera device arranged on the cleaning robot, obtain the information used to determine the object category corresponding to the target obstacle recognition result;
- the first selection module is configured to select a corresponding target obstacle avoidance route based on the identification result, and the target obstacle avoidance route corresponds to one of changing the current advancing direction and not changing the current advancing direction;
- the first running module is configured to run the cleaning robot based on the target obstacle avoidance route.
- the cleaning robot when the cleaning robot detects an obstacle ahead, it can select different obstacle avoidance routes according to whether the object type of the obstacle can be identified. Therefore, the purpose of performing different obstacle avoidance methods according to different types of object contours is achieved. Furthermore, the obstacle avoidance ability of the cleaning robot is improved, and the collision avoidance function is realized, which also avoids the problem that the obstacle cannot be completely avoided due to the limited sensing range of the robot.
- the cleaning device is a robot, and the robot is equipped with a first laser sensor and a second laser sensor, and the first laser sensor is at the inclination angle of the robot and the second laser sensor is at the inclination angle of the robot.
- the inclination angles are different, and the installation height of the first laser sensor on the robot is also different from the installation height of the second laser sensor on the robot, and the control device includes:
- the first distance acquisition module is configured to acquire a first sensing distance through the first laser sensor, and the first sensing distance is the spot falling point of the laser light emitted by the first laser sensor and the first laser sensor distance;
- the second distance acquisition module is configured to acquire a second sensing distance through the second laser sensor, and the second sensing distance is the spot falling point of the laser light emitted by the second laser sensor and the second laser sensor distance;
- the first landing point coordinate determination module is configured to determine the first landing point coordinates according to the installation height, inclination angle and the first sensing distance of the first laser sensor on the robot, and the first landing point coordinates are The coordinates of the spot falling point of the laser light emitted by the first laser sensor;
- the second landing point coordinate determination module is used to determine the second landing point coordinates according to the installation height, inclination angle and the second sensing distance of the second laser sensor on the robot, and the second landing point coordinates are The coordinates of the spot falling point of the laser light emitted by the second laser sensor;
- the obstacle type identification module is used to identify the obstacle type corresponding to the target area according to the first landing point coordinates, the second landing point coordinates and the preset allowable obstacle clearance height, and the target area is the first The coordinates of the first drop point and the area where the coordinates of the second drop point are located;
- a motion control module configured to control the motion of the robot according to the type of the obstacle.
- the first landing point coordinates and the second landing point coordinates obtained based on the first laser sensor and the second laser sensor are coordinates corresponding to two different positions. Since the coordinates of two different positions can reflect the height difference between the two positions, combined with the preset allowable obstacle clearance height, the obstacle type corresponding to the area where the two different positions are located can be quickly and accurately identified. For example, identify whether the obstacle type is a step that the robot can climb.
- the room feature parameters include ground feature information of the room, wherein the control device is further configured to determine control information according to the ground feature information, and control the cleaning device to work according to the control information.
- the cleaning device can be a sweeping robot, a mopping robot, a sweeping and mopping machine, etc., which can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with equipment such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, the corresponding control information is determined according to the ground feature information in the room, so that the cleaning equipment performs cleaning work according to the control information.
- the cleaning equipment can realize more intelligent and customized cleaning based on the ground conditions of the room, and improve the efficiency and accuracy of room cleaning.
- the room characteristic parameters include room characteristic information of the room
- the obstacle parameters include the positions of objects in the room
- the control device is further configured to:
- the cleaning device is controlled to avoid the position of the object and operate according to the cleaning parameters.
- the cleaning device can be a sweeping robot, a mopping robot, a sweeping and mopping machine, etc., which can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with cameras, infrared sensors and other equipment, which can collect room characteristic information in the room and the specific position of fixed objects in the room.
- the position characteristic information of the object can indicate the type of room, the floor layout in the room and so on.
- the corresponding cleaning parameters are determined according to the room characteristic information in the room, and the route of the cleaning equipment is determined according to the specific position of the fixed object, so that the cleaning equipment can avoid the specific position of the fixed object and move, and perform cleaning work according to the control information .
- the cleaning equipment can adaptively set a reasonable cleaning method based on the specific conditions of the room, realize more intelligent and customized cleaning, and improve the efficiency and accuracy of room cleaning.
- a cleaning device including: a memory for storing programs or instructions; a processor, and when the processor executes the programs or instructions, it implements the cleaning device control method according to any of the above technical solutions step.
- the cleaning equipment provided by the present disclosure when the program or instruction is executed by the processor, implements the steps of the cleaning equipment control method of any of the above technical solutions, so the cleaning equipment includes all the benefits of the cleaning equipment control method of any of the above technical solutions Effect.
- a readable storage medium on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the steps of the cleaning device control method according to any of the above technical solutions are implemented.
- the readable storage medium provided by the present disclosure, when the program or instruction is executed by the processor, implements the steps of the cleaning device control method of any of the above technical solutions, so the readable storage medium includes the control of the cleaning device of any of the above technical solutions All beneficial effects of the method.
- FIG. 1 is one of the schematic flowcharts of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 2 is a second schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 3 is a third schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 4 is a fourth schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 5 is a fifth schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 6 is a sixth schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure
- Fig. 7 is a seventh schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure.
- Fig. 8 is one of schematic diagrams of floor laying in a room according to an embodiment of the present disclosure.
- Fig. 9 is the second schematic diagram of floor laying in a room according to an embodiment of the present disclosure.
- Fig. 10 is the eighth schematic flow diagram of a control method of a cleaning device according to an embodiment of the present disclosure.
- Fig. 11 is a ninth schematic flow diagram of a cleaning device control method according to an embodiment of the present disclosure.
- Fig. 12 is a tenth schematic flow diagram of a cleaning device control method according to an embodiment of the present disclosure.
- Fig. 13 is an eleventh schematic flow diagram of a cleaning device control method according to an embodiment of the present disclosure.
- Fig. 14 is the twelfth schematic flow diagram of a cleaning device control method according to an embodiment of the present disclosure.
- Fig. 15 is the thirteenth schematic flow diagram of a cleaning device control method according to an embodiment of the present disclosure.
- FIG. 16 is one of schematic diagrams of a room layout according to an embodiment of the present disclosure.
- Fig. 17 is the second schematic diagram of room layout according to an embodiment of the present disclosure.
- Fig. 18 is a schematic diagram of an operating system architecture of a cleaning robot according to an embodiment of the present disclosure.
- Fig. 19 is a schematic diagram of an obstacle avoidance method of a cleaning robot according to an embodiment of the present disclosure.
- Fig. 20 is a schematic diagram of generating an obstacle avoidance route of a cleaning robot according to an embodiment of the present disclosure
- Fig. 21 is a scene display diagram of obstacle avoidance of a cleaning robot according to an embodiment of the present disclosure.
- Fig. 22 is a flowchart of generating a semantic map according to an embodiment of the present disclosure.
- Fig. 23 is a schematic flowchart of the operation of a cleaning robot according to an embodiment of the present disclosure.
- Fig. 24 is a flowchart of a first robot control method according to an embodiment of the present disclosure.
- Fig. 25 is a schematic diagram of information such as a laser sensor's inclination angle, emission point, and spot drop point according to an embodiment of the present disclosure
- Fig. 26 is a flowchart of a second robot control method according to an embodiment of the present disclosure.
- Fig. 27 is a schematic diagram of a downhill ramp according to an embodiment of the present disclosure.
- Fig. 28 is a schematic diagram of a large step according to an embodiment of the present disclosure.
- Fig. 29 is a schematic diagram of a tall obstacle according to an embodiment of the present disclosure.
- Fig. 30 is a schematic diagram of an uphill ramp according to an embodiment of the present disclosure.
- Fig. 31 is a schematic block diagram of an obstacle avoidance device of a cleaning robot according to an embodiment of the present disclosure
- Fig. 32 is a logical structural block diagram of an electronic device according to an embodiment of the present disclosure.
- Fig. 33 is a structural example diagram of a robot control device according to an embodiment of the present disclosure.
- Fig. 34 is a schematic structural diagram of a robot according to an embodiment of the present disclosure.
- Fig. 35 is a schematic block diagram of a control device of a cleaning device according to an embodiment of the present disclosure.
- Figure 36 is a schematic block diagram of a cleaning device according to one embodiment of the present disclosure.
- FIG. 37 is a schematic block diagram of a cleaning device according to another embodiment of the present disclosure.
- Fig. 38 is a schematic block diagram of a control device of a mobile device according to an embodiment of the present disclosure.
- Figure 39 is a schematic block diagram of a mobile device according to one embodiment of the present disclosure.
- FIG. 40 is a schematic block diagram of a mobile device according to another embodiment of the present disclosure.
- a cleaning device control method includes: detecting the operating environment of the cleaning device, and obtaining environmental characteristic parameters, wherein the environmental characteristic parameters include room characteristic parameters and /or obstacle parameters.
- the cleaning device can be controlled to perform cleaning.
- the cleaning device is a cleaning robot.
- the cleaning robot determines its cleaning route, cleaning parameters, etc. according to the room characteristic parameters and/or obstacle parameters, and automatically cleans the room based on the determined cleaning route, cleaning parameters, etc.
- the cleaning robot may include, for example, a sweeper, a floor washing machine, a window cleaning robot, a desktop robot, a gardening robot, and the like. It should be noted that the method disclosed in this specification is not limited to cleaning equipment, and can also be used in other industrial, commercial, and household robots, such as restaurant service robots.
- the cleaning device control method can control the cleaning device based on at least one of the room characteristic parameters and obstacle parameters, realize different cleaning control methods adopted in different scenarios, realize more intelligent and customized cleaning, and improve room The efficiency and accuracy of cleaning fully meet the needs of users.
- the room feature parameters may include floor feature information of the room; optionally, controlling the cleaning equipment to clean according to the room feature parameters includes: determining control information according to the ground feature information, and controlling the cleaning equipment to work according to the control information.
- FIG. 1 shows one of the schematic flowcharts of a cleaning device control method.
- the cleaning device can be a mobile device, as shown in Figure 1, the method includes:
- Step 102 obtaining ground feature information of the room
- Step 104 based on the ground feature information, determine control information for the movable device
- Step 106 controlling the mobile device to work according to the control information.
- the movable device may be a cleaning device such as a sweeping robot, a mopping robot, or an all-in-one sweeping and mopping machine, which can move in multiple rooms, thereby achieving the purpose of cleaning in different rooms.
- a cleaning device such as a sweeping robot, a mopping robot, or an all-in-one sweeping and mopping machine, which can move in multiple rooms, thereby achieving the purpose of cleaning in different rooms.
- the mobile device is equipped with devices such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, corresponding control information is determined according to the ground feature information in the room, so that the mobile device performs cleaning work according to the control information.
- devices such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, corresponding control information is determined according to the ground feature information in the room, so that the mobile device performs cleaning work according to the control information.
- the floor feature information includes at least one of floor laying material, floor laying direction, floor size, socket position, and room boundary feature.
- the mobile device can realize more intelligent and customized cleaning based on the ground conditions of the room, and improve the efficiency and accuracy of room cleaning.
- the default cleaning strategy can be executed to ensure the smooth progress of cleaning.
- FIG. 2 shows a second schematic flowchart of a method for controlling a mobile device.
- the method includes:
- Step 202 obtaining the floor paving material of the room
- Step 204 based on the ground laying material, determine first control information for the movable device
- Step 206 control the mobile device to work according to the first control information.
- the ground feature information may include the material of the ground, for example, the material includes wood (such as floor), quality, stone (such as floor tiles) and the like.
- the control information of the movable device includes first control information, and the first control information may be at least one of water output, cleaning times, fan suction, and moving speed.
- the movable device determines the cleaning times of the room by the movable device.
- the movement parameters (such as the motor speed feedback of the movable device, etc.) Smoother and smoother.
- different materials can correspond to different fan suction, and the fan suction of specific materials can be determined according to the user's setting parameters.
- the user can set the corresponding fan suction force to be large when the ground paving material is porcelain or stone, so that the water stains on the porcelain or stone floor can be sucked up to the greatest extent, and the problem of users being slipped can be avoided.
- Users can also set the corresponding fan suction when the floor is made of wood, because the bedroom is usually the floor, so that the water stains on the bedroom floor can be absorbed to the greatest extent, and avoid excessive water stains that cause bedding to become damp The problem.
- the mobile device can realize more personalized and intelligent cleaning of the room based on the material laid on the floor in the room.
- the water yield when the ground laying material is wood is smaller than the water yield when the ground laying material is porcelain or stone.
- the water output of the movable equipment can be relatively increased, thereby improving the cleaning degree of the floor tiles and ensuring Cleaning effect.
- the number of cleanings when the floor paving material is wood is greater than the cleaning times when the floor paving material is porcelain or stone.
- the material of the floor in the room is wood, that is to say, the floor is laid in the room, the water output when the movable equipment is cleaned can be reduced, thereby reducing the damage of water stains to the floor , Protect the floor, and increase the number of cleanings at the same time to ensure the cleaning effect.
- the water output of the movable equipment can be relatively increased, thereby improving the cleaning degree of the floor tiles and ensuring Cleaning effect, while relatively reducing the number of cleanings to reduce the waste of electric energy of mobile equipment.
- FIG. 3 shows a third schematic flowchart of a method for controlling a mobile device.
- the method includes:
- Step 302 obtaining the floor laying direction of the room
- Step 304 Determine second control information for the movable device based on the ground laying direction
- Step 306 controlling the mobile device to work according to the second control information.
- the second control information is that the cleaning direction of the movable device is consistent with the floor laying direction.
- the ground feature information may include the direction in which the ground is laid, that is, the texture of the floor or floor tiles laid on the ground.
- the control information of the movable device includes second control information, and the second control information may be control information of a cleaning direction of the movable device.
- the cleaning direction of the movable device is correspondingly determined so that the cleaning direction of the movable device is the same as the direction in which the floor is laid, that is to say, the cleaning direction of the movable device is parallel to the direction in which the floor is laid.
- the cleaning direction of the movable equipment is controlled to be parallel to the laying direction of the floor.
- the movable device can be cleaned parallel to the direction in which the floor is laid in the room, thereby reducing the residual dust, water stains, etc. in the gaps of the floor or floor tiles, and making the cleaning marks of the movable device on the floor or floor tiles not messy , making the cleaning marks more beautiful and improving the cleaning effect.
- FIG. 4 shows a fourth schematic flowchart of a method for controlling a mobile device.
- the method includes:
- Step 402 obtaining the ground size of the room
- Step 404 based on the ground size, determine the type of the room
- Step 406 according to the type of the room, determine third control information for the mobile device
- Step 408 control the mobile device to work according to the third control information.
- the ground feature information may include the ground size, that is, the size of the room, and the control information of the mobile device includes the third control information.
- the size of the room is determined based on the ground size of the room, thereby determining the type of the room, and then the third control information of the movable device is correspondingly determined according to the type of the room.
- the cleaning of the mobile device can be adaptively controlled according to the type of the room, thereby improving the efficiency and accuracy of room cleaning.
- the type of room includes at least one of bedroom, living room, kitchen and bathroom.
- the room may include a bedroom, a living room, a kitchen or a bathroom, and the cleaning methods of the mobile device in different types of rooms may be different.
- the third control information includes at least one of room cleaning sequence, cleaning dose and disinfectant dose.
- the third control information of the movable device may be at least one of room cleaning sequence, cleaning dose, and disinfectant dose.
- the room can be cleaned first; when the room is determined to be the living room, the living room can be cleaned after the bedroom; when the room is determined to be the kitchen or bathroom, the mobile device can be sprayed for cleaning Agents, disinfectants, etc.
- controlling the movable device in combination with the size of the ground may be performed after the step of controlling the movable device according to the material and/or direction of the ground laying.
- the movable device may be controlled in combination with the size of the ground, the material of the ground laying and/or the direction of the laying of the ground.
- the room will be cleaned first, and then the kitchen, bathroom and other rooms will be cleaned to meet user needs . If it is recognized that the floor tiles are laid in the room, and the size of the room is relatively small, it can be determined that it is a kitchen or bathroom, and the room is finally cleaned, and detergents, disinfectants, etc. can be sprayed during cleaning.
- FIG. 5 shows a fifth schematic flowchart of a method for controlling a mobile device.
- the method includes:
- Step 502 obtaining the socket position of the room
- Step 504 based on the socket position, determine fourth control information for the mobile device
- Step 506 control the mobile device to work according to the fourth control information.
- the ground feature information may include the location of the socket, that is, the location of the socket installed on the ground, and the control information of the movable device includes fourth control information, which is used to control the movement of the movable device route.
- the movement route of the movable device is controlled to avoid the risk of electric leakage at the location of the socket when the movable device cleans, and to improve the safety during the cleaning process.
- the fourth control information is to control the cleaning range of the movable device to be outside the preset range of the socket position.
- the mobile device can keep a certain safe distance from the socket 902 during cleaning, that is, within a distance from the socket 902 Cleaning is performed outside a preset range, for example, cleaning is performed within a range 10 cm or 20 cm away from the socket 902 .
- controlling the movable device in combination with the position of the socket may be before or after the step of controlling the movable device according to the material and/or direction of the ground laying.
- the movable device may be controlled in conjunction with the socket position, the ground laying material and/or the laying direction of the ground at the same time.
- the step of determining the control information for the mobile device based on the ground feature information specifically includes: judging the room boundary feature Whether the height of the room boundary feature does not exceed the preset threshold, and when the height of the room boundary feature does not exceed the preset threshold, determine the control information corresponding to the room boundary feature.
- the room boundary feature refers to a feature line (such as a boundary line) that separates different rooms, such as a door pass, a threshold stone, a sliding door track, and the like.
- the ground feature information may include the room boundary features of the room, such as door crossing strips, threshold stones, sliding door tracks, and the like.
- the mobile device can be controlled to clean the location; when it is recognized that the height of the room boundary feature exceeds the preset threshold, it indicates that If the height of the room boundary feature is high, the movable device will not be cleaned at this position, preventing the movable device from being stuck at the room boundary feature.
- the mopping robot taking the mobile device as an example of a mopping robot, the mopping robot usually uses a single-line laser radar or a camera as a main sensor to perceive the environment and build a map.
- the degree of intelligence is mainly reflected in The improvement of navigation motion accuracy, the identification and collision avoidance of isolated objects, the cleaning of segmented areas without omission, etc.
- cleaning is mostly reflected in the characteristics of carpet pressurization, cleaning times, bow distance, disinfection and sterilization.
- Fig. 6 shows a sixth schematic flow diagram of a method for controlling a mobile device according to an embodiment of the present disclosure. Wherein, as shown in Figure 6, the method includes:
- Step 602 obtaining at least one of the room's floor laying material, floor laying direction, floor size, socket position, and room boundary features;
- Step 604 based on at least one of the ground laying material, ground laying direction, ground size, socket position and room boundary features, determine the corresponding control information of the mopping robot;
- Step 606 controlling the mopping robot to work according to the control information.
- This method uses cameras, infrared sensors, etc. to collect ground feature information, and through feature extraction, image recognition, big data training and learning, etc., to obtain the classification results of the ground material (usually binary classification, such as floor or floor tiles), and the laying method of the ground material (Usually a binary classification, such as horizontal laying or vertical laying), added to the map semantics to assist the mopping robot to implement a more efficient, accurate, and friendly cleaning strategy to achieve intelligent deep cleaning.
- binary classification such as floor or floor tiles
- laying method of the ground material usually a binary classification, such as horizontal laying or vertical laying
- the mopping robot can realize more intelligent and customized cleaning based on the ground conditions of the room, and improve the efficiency and accuracy of room cleaning.
- FIG. 7 shows a seventh schematic flowchart of a method for controlling a mobile device.
- the method includes:
- Step 720 identifying room boundary features of the room.
- Step 740 when the mobile device enters the room through the room boundary feature, acquire the ground feature information of the room;
- Step 760 based on the ground feature information, determine control information for the movable device
- Step 780 control the mobile device to work according to the control information.
- the room boundary feature is an important basis for room division, which may include door bars, threshold stones, sliding door tracks, and the like.
- the ground feature information of the room is collected, and then the mobile device is controlled to clean the room according to the control information corresponding to the ground feature information.
- the room boundary feature it can be accurately determined whether the mobile device enters the room, so as to collect ground feature information after entering the room, and realize timely and accurate collection of ground feature information.
- a deep learning model is trained on the server side for features such as the type of ground material, the direction of paving lines, the doorway strip, the threshold stone, and the sliding door track, and the mobile device can complete the identification and save the result. If the room boundary features such as door bars, threshold stones, and sliding door tracks are identified, mark them on the map as an important basis for map room division, which can make the APP map more real and accurate, and the cleaning route of mobile devices is clearer and easier to understand. Avoid getting stuck at the sliding door track and improve cleaning efficiency.
- the step of acquiring the ground feature information of the room before the step of acquiring the ground feature information of the room, it further includes: determining a correspondence between the ground feature information and the control information.
- the room characteristic parameters include room characteristic information of the room
- the obstacle parameters include the positions of objects in the room
- the cleaning step includes: determining cleaning parameters according to room feature information; controlling the cleaning equipment to avoid the position of objects, and working according to the cleaning parameters.
- FIG. 10 shows the eighth schematic flowchart of the cleaning device control method according to the embodiment of the present disclosure.
- the method includes:
- Step 820 determine the room feature information of the room to be cleaned by the cleaning equipment and the positions of objects in the room to be cleaned
- Step 840 based on the room characteristic information of the room to be cleaned, determine the cleaning parameters
- Step 860 according to the cleaning parameters, control the cleaning equipment to work, and avoid the position of objects in the room to be cleaned during the work.
- the cleaning device can be a sweeping robot, a mopping robot, a sweeping and mopping machine, etc., which can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with cameras, infrared sensors and other equipment, which can collect room characteristic information in the room and the specific position of fixed objects in the room.
- the position characteristic information of the object can indicate the type of room, the floor layout in the room and so on.
- the object may be furniture, electrical appliances, etc., for example, tables and chairs, sofas, carpets, air conditioners, and the like.
- the corresponding cleaning parameters are determined according to the room characteristic information in the room, and the route of the cleaning equipment is determined according to the specific position of the fixed object, so that the cleaning equipment can avoid the specific position of the fixed object and move, and perform cleaning work according to the control information .
- the room feature information includes at least one of room type and floor paving material.
- the cleaning equipment can adaptively set a reasonable cleaning method based on the specific conditions of the room, realize more intelligent and customized cleaning, and improve the efficiency and accuracy of room cleaning.
- FIG. 11 shows a ninth schematic flowchart of a cleaning device control method.
- the method includes:
- Step 902 determining the room type of the room to be cleaned by the cleaning equipment and the positions of objects in the room to be cleaned;
- Step 904 based on the room type of the room to be cleaned, determine the first cleaning parameters
- Step 906 Control the cleaning device to work according to the first cleaning parameter, and avoid the position of objects in the room to be cleaned during the work.
- the first cleaning parameter includes at least one of cleaning priority and cleaning degree.
- the room feature information may include the type of the room, and then the first cleaning parameter of the cleaning device can be correspondingly determined according to the type of the room.
- the cleaning parameters of the cleaning device include the first cleaning parameter
- the room may include a bedroom, a living room, a kitchen or a bathroom
- the first cleaning parameters such as the cleaning priority and cleaning degree of the cleaning device in different types of rooms may be different.
- the cleaning mode of the cleaning equipment can be adaptively controlled according to the type of the room, thereby improving the efficiency and accuracy of room cleaning.
- the cleaning priority when the room is a bedroom or a living room, the cleaning priority is greater than or equal to the first threshold, and based on the room being a bathroom or a kitchen, the cleaning priority is less than the first threshold, that is, the cleaning priority of the bedroom or the living room Prioritize cleaning over bathroom or kitchen.
- the room may include a bedroom 702, a living room 704, a kitchen 706, and a bathroom 708.
- the room may be cleaned with priority; or the kitchen 706, the bathroom 708 or the kitchen 706 can be cleaned after cleaning the bedroom 702 or the living room 704.
- the degree of dirtiness of the bathroom or the kitchen is greater than that of the bedroom or the living room
- the degree of cleanliness of the bathroom or the kitchen is also greater
- the degree of cleanliness of the bathroom or the kitchen is greater than that of the bedroom or the living room degree of cleanliness. That is to say, when the room type is a bathroom or a kitchen, the cleanliness degree is greater than or equal to the second threshold, and when the room type is a bedroom or a living room, the cleanliness degree is less than the second threshold.
- the degree of cleanliness can be expressed as the number of times of cleaning, the strength of wiping the floor, whether to spray cleaners, disinfectants, etc.
- the cleaning device can spray detergent, disinfectant, etc. to improve the cleanliness.
- FIG. 12 shows a tenth schematic flowchart of a cleaning device control method.
- the method includes:
- Step 1002 determining the floor material of the room to be cleaned by the cleaning equipment and the positions of objects in the room to be cleaned;
- Step 1004 based on the floor material of the room to be cleaned, determine the second cleaning parameters
- Step 1006 according to the second cleaning parameter, control the cleaning device to work, and avoid the position of the object in the room to be cleaned during the work.
- the second cleaning parameter includes at least one of water output, cleaning times, and fan suction.
- the room feature information may include the material of the floor, for example, the material includes wood (such as floor), porcelain, stone (such as floor tile), concrete, and the like.
- the cleaning parameters of the cleaning device include a second cleaning parameter, and the second cleaning parameter may be at least one of water output, cleaning times, and fan suction.
- the water output, cleaning times, fan suction, etc. of the cleaning equipment are correspondingly determined.
- the cleaning device can realize more personalized and intelligent cleaning of the room based on the material laid on the floor in the room.
- the water output of the cleaning equipment is less than when the ground paving material is porcelain or stone, and when the ground paving material is porcelain or stone, the water output of the cleaning equipment is less than The water output of the cleaning equipment when the ground paving material is concrete.
- the water output of the cleaning equipment is less than or equal to the third threshold; when the material of the ground paving is porcelain or stone, the water output of the cleaning equipment is greater than the third threshold
- the threshold is less than or equal to the fourth threshold; in the case that the floor material is concrete, the water output of the cleaning equipment is greater than the fourth threshold, wherein the fourth threshold is greater than the third threshold.
- the room can include a bedroom 702, a living room 704, a kitchen 706, a bathroom 708, and a balcony 710, wherein the material laid on the ground in the bedroom 702 and the living room 704 is wood, and the floor laid on the ground in the kitchen 706 and the bathroom 708 is wood.
- the material is porcelain or stone, and the material of the floor in the balcony 710 is concrete.
- the amount of water produced by the cleaning equipment during cleaning can be relatively reduced, thereby reducing the damage of water stains to the floor and protecting the floor.
- the cleaning equipment can be controlled to moderate the water output during cleaning, thereby improving the cleaning degree of the floor tiles and ensuring the cleanliness of the floor tiles. Effect.
- the water output of the cleaning equipment can be relatively increased, thereby improving the degree of cleaning of the cement floor and ensuring the cleaning effect.
- the cleaning times of the cleaning equipment when the ground paving material is wood is greater than that of the cleaning equipment when the ground paving material is porcelain or stone, and the cleaning times of the cleaning equipment when the ground paving material is porcelain or stone are greater than The number of cleanings of the cleaning equipment when the floor covering is concrete.
- the number of times the cleaning equipment cleans is greater than or equal to the fifth threshold; when the floor material is porcelain or stone, the cleaning frequency of the cleaning equipment is less than the fifth threshold.
- the threshold is greater than or equal to the sixth threshold; when the floor material is concrete, the cleaning frequency of the cleaning equipment is less than the sixth threshold, wherein the sixth threshold is less than the fifth threshold.
- the amount of water output by the cleaning equipment can be relatively reduced, thereby reducing the damage of water stains to the floor and protecting the floor. , and at the same time increase the cleaning frequency of the cleaning equipment to ensure the cleaning effect.
- the water output and cleaning frequency of the cleaning equipment can be controlled to improve the cleaning degree of the floor tiles , to ensure the cleaning effect.
- the water output of the cleaning equipment can be relatively increased, thereby improving the degree of cleaning of the cement floor and ensuring the cleaning effect. Relatively reduce the number of cleanings to reduce the waste of electric energy for cleaning equipment.
- FIG. 13 shows an eleventh schematic flowchart of a cleaning device control method.
- the method includes:
- Step 1102 determine the room characteristic information of the room to be cleaned by the cleaning equipment and the positions of objects in the room to be cleaned;
- Step 1104 based on the room characteristic information of the room to be cleaned, determine the cleaning parameters
- Step 1106 determine the relative position information between the object and the ground of the room
- Step 1108 according to the cleaning parameter, control the cleaning equipment to work, and avoid the position of the object in the room to be cleaned according to the relative position information during the work.
- the relative position information between the object and the ground in the room is determined, and the relative position information can indicate whether there is a gap between the object and the ground, and if there is a gap, the size of the gap. Then, according to whether there is a gap or the size of the gap when there is a gap, it is controlled whether the cleaning device avoids the movement of the object.
- a carpet 802 is laid on a partial area of the floor of the room, and there is no gap between the carpet 802 and the floor, so the cleaning equipment is controlled to avoid the carpet for cleaning. Selectively avoid cleaning objects such as tables and chairs in the room.
- the table legs pass under the table top of the dining table 804, that is, it does not completely avoid the dining table 804.
- FIG. 14 shows a schematic flowchart No. 12 of a cleaning device control method.
- the method includes:
- Step 1202 collect a first image of the room to be cleaned, and identify the room to be cleaned according to the first image;
- Step 1204 according to the preset corresponding relationship between the room to be cleaned and the room feature information and the position of the object, determine the room feature information of the room to be cleaned and the position of the object in the room to be cleaned;
- Step 1206 based on the room characteristic information of the room to be cleaned, determine the cleaning parameters
- Step 1208 according to the cleaning parameters, control the cleaning equipment to work, and avoid the position of objects in the room to be cleaned during the work.
- the specific room that the cleaning equipment enters is determined based on the first image, and then according to the preset correspondence between the room and the room characteristic information and the position of the object, determine the The room feature information corresponding to the room and the position of the object.
- the preset corresponding relationship between the room and the room feature information and the position of the object is stored in advance, and after the specific room is specified according to the first image, the room feature information and the position of the object corresponding to the room can be obtained .
- the pre-stored room feature information and the position of the object can be obtained according to the preset corresponding relationship, and there is no need to identify the room feature information and the position of the object through the image, which improves the room feature information. and the accuracy and timeliness of object location acquisition.
- the step of determining the room characteristic information of the room to be cleaned and the positions of objects in the room to be cleaned it may further include: controlling the cleaning equipment to move in the room, and during the moving process Collecting the second image of the room; identifying the second image, acquiring the room characteristic information and the position of the object, and establishing a preset correspondence between the room and the room characteristic information and the position of the object.
- the cleaning equipment is controlled to move in the room, and the second image of the room is acquired during the movement, so as to realize positioning and mapping. Further, the room characteristic information and the position of the object of the room are identified in the second image, and the room name is stored in correspondence with the room characteristic information and the position of the object, so as to establish a preset correspondence.
- the room feature information and the position of the object are determined, so as to realize the classification and formulation of cleaning plans, and improve the intelligence of the cleaning equipment.
- FIG. 15 shows a thirteenth schematic flowchart of a cleaning device control method.
- the method includes:
- Step 1302 the floor mopping robot uses cameras, radars and other equipment to locate and map the room for the first time;
- Step 1304 during the positioning and mapping process, mark some environmental attributes of the room, such as ground material, room type, furniture position, etc., through cameras, ultrasound and other equipment;
- Step 1306 when the mopping robot cleans next time, formulate a mopping plan according to the marked environmental attributes
- Step 1308 controlling the mopping robot to complete the cleaning according to the mopping scheme formulated by classification.
- the water output of a wooden floor mopping robot is low, the water output of a ceramic tile floor mopping robot is moderate, and the water output of a cement floor mopping robot is large.
- the bedroom and living room mop and clean first, and the normal frequency is enough; for the kitchen and bathroom, the last mop and sweep, the frequency is increased, etc. Carpets need to be avoided, and tables and chairs are selectively avoided.
- the cleaning of the mopping robot is made more targeted, making the decision-making and planning method of the mopping machine category different from that of the sweeper; on the other hand, the cleaning of the mopping robot is made more intelligent and can According to the classification of environmental attributes, the mopping plan is formulated adaptively, with a high degree of intelligence.
- the cleaning device may be a cleaning robot, wherein the step of controlling the cleaning device to perform cleaning according to the obstacle parameters includes: The area starts the cleaning function; if it is detected that there is a target obstacle at the first distance in the current direction of travel, based on the camera device installed on the cleaning robot, the recognition result for determining the object category corresponding to the target obstacle is obtained; Based on the identification result, select a corresponding target obstacle avoidance route, the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; based on the target obstacle avoidance route, run The cleaning robot.
- controlling the cleaning device according to obstacle parameters may be performing obstacle avoidance control on the cleaning robot.
- FIG. 18 shows a schematic diagram of an exemplary system architecture 100 for an obstacle avoidance method for a cleaning robot or an obstacle avoidance system for a cleaning robot according to an embodiment of the present disclosure.
- the system architecture 100 may include one or more of cleaning robots 110 , 120 , 130 , a network 140 and a server 150 .
- the network 140 is used as a medium for providing communication links between the cleaning robots 110 , 120 , 130 and the server 150 .
- Network 140 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.
- the numbers of cleaning robots, networks and servers in Figure 18 are merely illustrative. There can be any number of cleaning robots, networks and servers depending on implementation needs.
- the server 150 may be a server cluster composed of multiple servers.
- the cleaning robots 110, 120, 130 may include various electronic devices with display screens and camera collection devices.
- the cleaning robots 110, 120, 130 in the present disclosure may be cleaning robots that provide various services.
- the user realizes through the cleaning robot 130 (it can also be the cleaning robot 110 or 120): after obtaining the operation instruction, start the cleaning function in the target area at the first rate; Based on the camera device arranged on the cleaning robot, a recognition result for determining the object category corresponding to the target obstacle is obtained; based on the recognition result, a corresponding target obstacle avoidance route is selected, and the target obstacle avoidance route corresponds to Based on one of changing the current heading and not changing the current heading; based on the target obstacle avoidance route, run the cleaning robot.
- the obstacle avoidance method of the cleaning robot provided by the embodiment of the present disclosure may be executed by one or more of the cleaning robots 110, 120, 130, and/or the server 150, and accordingly, the implementation of the present disclosure
- the obstacle avoidance device of the cleaning robot provided by the example is generally provided in the corresponding cleaning robot, and/or in the server 150, but the present disclosure is not limited thereto.
- Fig. 19 schematically shows a schematic flowchart of an obstacle avoidance method for a cleaning robot according to an embodiment of the present disclosure. As shown in Figure 19, the method is applied to cleaning robots, including:
- the cleaning robot is a kind of smart household appliances, which can automatically complete the floor cleaning work in the area by virtue of certain artificial intelligence.
- brushing and vacuuming are used to absorb the debris on the ground into its own garbage storage box, so as to complete the function of ground cleaning.
- the operating instructions in the present disclosure may be generated by the user, or may be generated according to preset rules.
- the robot can be instructed to perform an operation command for cleaning the room at regular intervals.
- the present disclosure does not limit the target area.
- it may correspond to a bedroom, may also correspond to a kitchen, may also correspond to an office area, and so on.
- the present disclosure does not limit the first speed, for example, it may be a normal running speed or a fast running speed.
- the cleaning robot when a traditional cleaning robot performs indoor cleaning, it usually needs to avoid obstacles to prevent the robot from running into a wall continuously.
- the cleaning robot usually recognizes obstacles based on sensor perception such as laser radar and ultrasonic waves.
- the obstacle detection scheme of the sweeper for sensors such as lidar and ultrasonic often cannot avoid obstacles accurately.
- the present disclosure proposes a method in which when an obstacle is detected ahead, an identification event for determining its object type may be performed on the obstacle first.
- an identification event for determining its object type may be performed on the obstacle first.
- the cleaning robot can be selected and instructed to implement different obstacle avoidance routes based on the recognition result of the object category.
- the present disclosure may use the camera device installed on the cleaning robot to take images of the obstacles in front, so as to Thus obtain the target obstacle image; and subsequently use the preset image detection and classification model to extract at least one object feature corresponding to the size feature, color feature and contour feature of the target obstacle image, so that the subsequent feature to determine the object category corresponding to the target obstacle.
- the present disclosure does not specifically limit the image detection and classification model.
- it may be a convolutional neural network (Convolutional Neural Networks, CNN).
- Convolutional neural network is a kind of feedforward neural network (Feedforward Neural Networks) with convolution calculation and deep structure, and it is one of the representative algorithms of deep learning.
- the convolutional neural network has the ability of representation learning, which can perform translation invariant classification on the input information according to its hierarchical structure. Thanks to the powerful feature representation ability of CNN (Convolutional Neural Network) for images, it has achieved remarkable results in image classification, target detection, semantic segmentation and other fields.
- the present disclosure can use the image detection and classification model to detect the feature information in multiple target obstacle images collected by the camera device carried by the cleaning robot, and then perform feature recognition on the feature information to determine the corresponding object category.
- the image to be recognized needs to be input into the preset convolutional neural network model, and the output of the last fully connected layer (FC, fully connected layer) of the convolutional neural network model is used as the corresponding image to the image to be recognized.
- FC fully connected layer
- the present disclosure does not specifically limit the object category corresponding to the target obstacle, for example, it may be animal feces, socks, shoes, wires, stools, beds, trash cans, tables, toilets and so on.
- the cleaning robot determines that it can identify the object category corresponding to the target obstacle, it can select the first obstacle avoidance route for instructing the cleaning robot to avoid the target obstacle without changing the current direction, that is, the robot is in the original If there is a way forward, choose a route that avoids obstacles.
- the embodiment of the present disclosure may first calculate the circumscribed image of the target obstacle based on the category of the obstacle object and its corresponding contour shape and size parameters and based on the pre-stored obstacle data set, and based on the circumscribed image and
- the purePuresuit algorithm can be divided into the following categories:
- Circumscribed circle As shown in Figure 20, if the polygon is close to a circle and the obstacles are stool legs, trash cans, table legs, and toilet obstacles, then find the circumscribed circle, and then determine the trajectory point with a straight line distance of 5CM.
- Circumscribed Rectangle If the polygon is close to a rectangle and the obstacles are socks, shoes, wires, tables. Then find the circumscribed rectangle, and then determine the track point with a straight-line distance of 5CM.
- Enveloping body If the polygon is not a circle and the obstacle is animal feces, calculate the enveloping body, and then determine the trajectory point with a straight line distance of 5CM.
- the first obstacle avoidance route can be calculated and generated according to the track point.
- the second obstacle avoidance route for instructing the cleaning robot to run in other directions in the case of avoiding the target obstacle can be selected, that is, the robot chooses a A route that can completely avoid obstacles (for example, the original heading is due north, and the heading of the second obstacle avoidance route is due west).
- the present disclosure can adopt a real-time avoidance method. Specifically, when the robot is moving, the deceleration needs to be triggered first to realize the deceleration of the robot, and when it detects a certain distance from the obstacle, the robot obtains the angle information from the virtual collision interface, and the machine refers to the returned angle, according to the following algorithm Calculate the angle at which the machine is parallel to the obstacle, turn the machine to be parallel to the obstacle, and then make an arc and walk along the obstacle. When the virtual collision occurs again, the machine rotates according to the calculated angle, and then turns an arc, and so on until the machine rotates 360 degrees or returns to the original point, and the machine exits the real-time obstacle avoidance function.
- the second obstacle avoidance route may be as follows:
- the robot may be driven to run along the target obstacle avoidance route until the cleaning robot finishes cleaning the target area.
- the cleaning function is started in the target area at the first rate; if it is detected that there is a target obstacle at the first distance in the current direction of travel, based on the camera device installed on the cleaning robot, Obtain the recognition result used to determine the object category corresponding to the target obstacle; based on the recognition result, select the corresponding target obstacle avoidance route, and the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; based on the target Obstacle avoidance route, run cleaning robot.
- the robot detects an obstacle ahead, it can select different obstacle avoidance routes according to whether the object type of the obstacle can be identified.
- the purpose of performing different obstacle avoidance methods according to different types of object contours is achieved. Furthermore, the obstacle avoidance ability of the cleaning robot is improved, and the collision avoidance function is realized, which also avoids the problem that the obstacle cannot be completely avoided due to the limited sensing range of the robot.
- step S1903 selecting a corresponding target obstacle avoidance route based on the recognition result
- a first obstacle avoidance route is selected, and the first obstacle avoidance route is a route for instructing the cleaning robot to avoid the target obstacle without changing the current forward direction;
- a second obstacle avoidance route is selected, and the second obstacle avoidance route is a route for instructing the cleaning robot to avoid the target obstacle and run in another direction.
- the present disclosure selects the first obstacle avoidance route after determining the object category corresponding to the target obstacle that can be identified, including:
- the circumscribed image of the target obstacle is calculated
- the present disclosure further includes:
- the cleaning robot can determine the object category corresponding to the obstacle, then it can determine the outline shape and size of the obstacle according to the pre-stored obstacle data set. And according to the contour shape and size, generate a route to avoid the obstacle.
- the present disclosure selects a second obstacle avoidance route after determining that the object category corresponding to the target obstacle cannot be recognized, including:
- a rotation angle for the forward direction of the rotating cleaning robot is determined, and based on the rotation angle, a second obstacle avoidance route is calculated and generated.
- the present disclosure further includes:
- the cleaning robot when there are too many or too large combinations of obstacles in front or no relevant parameters are injected in advance, the cleaning robot will not be able to recognize the object category corresponding to the obstacle.
- the rotation angle can ensure that the cleaning robot changes its forward direction (for example, the rotation angle can be 190 degrees, which can make the requester make a U-turn), so as to ensure that the robot can completely avoid the target obstacle and follow the route of other forward direction keep running.
- the rotation angle can be determined by the difference in parallel angle between the target obstacle and the cleaning robot, that is, the larger the difference in parallel angle between the two, the smaller the rotation angle in the forward direction of the rotating cleaning robot can be generated.
- the difference between the two parallel angles is smaller, an instruction with a larger rotation angle in the forward direction of the rotary cleaning robot can be generated.
- the method further includes:
- the cleaning robot when the cleaning robot runs at a speed of 30cm/s, when it approaches an obstacle, the cleaning robot will slow down to 15cm/s (ie the second speed).
- the above deceleration method can prevent the robot from colliding with obstacles with force. And it is more conducive to the robot to stop and move more smoothly. It can also be beneficial to use the camera device to collect more accurate image data (subsequently used to determine the object category of the obstacle).
- the deceleration interface is designed as follows. When an obstacle falls within the area formed by the slowdown distance threshold (Slowdown Distance) and the width of the fuselage (Robot withd) (ie, the second distance), the deceleration can be triggered.
- the slowdown distance threshold Smalldown Distance
- the width of the fuselage Robot withd
- the method before S1901 (starting the cleaning function in the target area at the first rate), the method further includes:
- sample obstacle information includes sample obstacle parameters and object categories corresponding to the sample obstacle
- each sample obstacle is projected onto the initial grid map to generate a semantic map
- the cleaning function is started in the target area based on the semantic map.
- FIG. 22 shows a flow chart of generating a semantic map.
- the cleaning robot of the obstacle avoidance method of the cleaning robot proposed in this disclosure includes five nodes: LDS_SLAM, Recognition, Perception3D, Semantic_Map, and Planer, wherein:
- the LDS_SLAM node is responsible for constructing localization and mapping.
- the LDS_SLAM node obtains data from IMU, Odometry, and Lidar sensors, creates a map, and outputs the pose of the machine. Solve the "Where am I?” question.
- the Recognition node realizes object recognition through AI technology.
- the Recognition node mainly realizes the recognition of nine types of objects such as animal feces, socks, shoes, wires, stools, beds, trash cans, tables, and toilets. Solve the "what is it?" question.
- the Perception3D node is responsible for outputting the depth information of obstacles. Solve the "Where is it?" question.
- the Semntic_map node obtains the spatial pose of the obstacle and the type of the obstacle from Recognition and Perception3D, combines the Pose of LDS_SLAM, and projects the obstacle onto the occupied grid map through the Bresenham algorithm, and marks the object on the corresponding grid type of information to generate a semantic map.
- the Planner node mainly realizes intelligent obstacle avoidance based on the information of the semantic map.
- the semantic map generation in the present disclosure is one of the functions of the planner. Specifically, a thread needs to be started first to accept the global grid map, machine pose, obstacle bounding box, obstacle category, and obstacle 3D point cloud information. Then calculate the point cloud that meets the conditions (such as height h, points within the range of groud ⁇ h ⁇ robot_hight) and the bounding box of the obstacle returned by Recognition to obtain the category of each point, and then calculate each point through the Bresennham algorithm The position and probability of falling into the grid, and mark the type of obstacle on the corresponding grid. At this point, the occupancy grid map with semantic information (ie, semantic map) is obtained, and it is deployed on the cleaning robot to provide obstacle avoidance algorithms.
- semantic information ie, semantic map
- the object features include at least one of size features, color features, and contour features;
- the present disclosure further includes:
- sample images include at least one obstacle feature
- the preset image semantic segmentation model is trained to obtain an image detection and classification model that meets the preset conditions, and the image detection and classification model is used to determine the target obstacle The object category corresponding to the object.
- the image detection and classification model needs to be trained first. Specifically, a certain number of sample images including features of multiple obstacle objects need to be acquired first. And use the plurality of sample images to train the basic blank image semantic segmentation model, and then obtain the first image detection and classification model that meets the preset conditions.
- each sample image is marked with a corresponding category identifier. For example, when there is an obstacle with a trash can in the sample image, it is necessary to mark the sample image with the category identification that the obstacle is a trash can. Or when an obstacle of a bed frame appears in the sample image, it is necessary to mark the sample image with a category identification that the obstacle is a bed frame.
- the present disclosure can identify at least one obstacle object feature (such as a size feature, an outline feature, a color feature, etc.) included in a sample image through a preset image semantic segmentation model. Furthermore, the image semantic segmentation model can also classify the features of each obstacle object in the sample image, and classify the sample features belonging to the same category into the same type of object.
- a sample feature can be a sample feature composed of multiple different types.
- the neural network image classification model performs semantic segmentation processing on the sample image, the more accurate the classification of the pixel points in the sample image is, the higher the accuracy rate of identifying the marked object in the sample image will be.
- the preset condition may be set by a user.
- the preset condition can be set as follows: the classification accuracy rate of pixels reaches more than 70%.
- the image detection and classification model can be applied in the embodiments of the present disclosure to perform image feature recognition on multiple obstacle images captured by the camera device in the cleaning robot.
- FIG. 23 it is an overall flow chart of the operation method of the cleaning robot proposed in the present disclosure, which includes:
- the cleaning function is started in the target area at the first rate, and when it is detected that there is a target obstacle at the first distance in the current forward direction, based on the camera device installed on the cleaning robot, it is obtained The recognition result used to determine the object category corresponding to the target obstacle.
- the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; finally, based on the target obstacle avoidance route, run Cleaning robot.
- the robot when the robot detects an obstacle ahead, it can select different obstacle avoidance routes according to whether the object type of the obstacle can be identified. Therefore, the purpose of performing different obstacle avoidance methods according to different types of object contours is achieved. Furthermore, the obstacle avoidance ability of the cleaning robot is improved, and the collision avoidance function is realized, which also avoids the problem that the obstacle cannot be completely avoided due to the limited sensing range of the robot.
- the cleaning device may be a robot, and the robot is equipped with a first laser sensor and a second laser sensor, and the inclination angle of the first laser sensor on the robot and the inclination angle of the second laser sensor on the robot are The inclination angles are different, and the installation height of the first laser sensor on the robot and the installation height of the second laser sensor on the robot are also different, wherein the step of controlling the cleaning equipment to clean according to the obstacle parameters may include: The first laser sensor obtains the first sensing distance, and the first sensing distance is the distance between the spot landing point of the laser light emitted by the first laser sensor and the first laser sensor; obtained by the second laser sensor The second sensing distance, the second sensing distance is the distance between the spot landing point of the laser light emitted by the second laser sensor and the second laser sensor; according to the installation of the first laser sensor on the robot Height, inclination and the first sensing distance, determine the first landing point coordinates, the first landing point coordinates are the coordinates of the spot
- the step of controlling the cleaning device according to the obstacle parameters may be to control the movement of the robot by identifying the obstacle type corresponding to the target area.
- an embodiment of the present disclosure provides a robot Control Method.
- two laser sensors are installed on the side in the forward direction of the robot, so that the two laser sensors can emit laser light to the front of the robot.
- the robot can calculate the coordinates of the spot landing points corresponding to different laser sensors, and then it can The allowable obstacle clearance height, and identify the obstacle type corresponding to the area where the two light spots fall.
- Fig. 24 shows a flow chart of a first robot control method provided by an embodiment of the present disclosure, and the robot control method is applied to a robot equipped with a first laser sensor and a second laser sensor.
- the inclination angle of the first laser sensor on the robot body is not equal to the inclination angle of the second laser sensor on the robot body
- the installation height of the first laser sensor on the robot body is the same as that of the second laser sensor on the robot body.
- the installation heights on the robot body are also not equal, as detailed below:
- step S11 the first sensing distance is obtained by the first laser sensor, and the first sensing distance is the distance between the spot of the laser light emitted by the first laser sensor and the first laser sensor.
- the first laser sensor emits laser light, and when the laser light is blocked, a spot of light will be formed on the blocking object. Since the propagation velocity of light is fixed, the distance between the first laser sensor and the corresponding spot landing point can be calculated according to the propagation velocity of light and its propagation time.
- the first sensing distance in the embodiment of the present disclosure may be calculated by the first laser sensor and sent to the robot by the first laser sensor, or may be calculated by the robot.
- the robot in the embodiment of the present disclosure may be a cleaning device such as a cleaning robot for cleaning.
- Step S12 acquiring a second sensing distance through the second laser sensor, where the second sensing distance is the distance between the spot of the laser light emitted by the second laser sensor and the second laser sensor.
- the calculation method of the second sensing distance is the same as that of the first sensing distance, and will not be repeated here.
- Step S13 according to the installation height of the first laser sensor on the robot, the inclination angle and the first sensing distance, determine the coordinates of the first landing point, where the first landing point coordinates are where the light spot of the laser light emitted by the first laser sensor falls. The coordinates of the point.
- the installation height of the first laser sensor on the robot refers to the distance from the installation position of the first laser sensor installed on the robot to the ground.
- the inclination angle of the first laser sensor on the robot refers to an angle less than 90° among the angles between the laser emitting port of the first laser sensor and the robot.
- the laser emitting point of the first laser sensor is A1, the spot of A1 is A2, the inclination angle of the first laser sensor is ⁇ , the installation height of the first laser sensor on the robot is H1, and the A sensing distance is the length of the side corresponding to A1A2.
- the laser emitting point of the second laser sensor is B1, the spot of B1 is B2, the inclination angle of the second laser sensor is ⁇ , the installation height of the first laser sensor on the robot is H2, and the first sensing distance is B1B2 .
- the length of the hypotenuse (such as A1A2) and the inclination angle (such as ⁇ ) of the right triangle in FIG. 25
- the length of the right-angled side in the horizontal direction in the right triangle can be determined, and then the abscissa in A2 can be determined.
- the length of the right-angled side in the vertical direction of the right-angled triangle can be determined according to the length and inclination of the hypotenuse of the right-angled triangle, and the vertical coordinate of A2 can be calculated by combining the length of the right-angled side with the installation height H1.
- Step S14 according to the installation height of the second laser sensor on the robot, the inclination angle and the second sensing distance, determine the second landing point coordinates, the second landing point coordinates are the spot where the laser beam emitted by the second laser sensor falls The coordinates of the point.
- the calculation method of the coordinates of the second landing point is the same as that of the coordinates of the first landing point, and will not be repeated here.
- Step S15 according to the coordinates of the first landing point, the coordinates of the second landing point and the preset allowable obstacle clearance height, identify the obstacle type corresponding to the target area, the target area is the coordinates of the first landing point and the second landing point The region where the point coordinates lie.
- the preset allowable obstacle clearance height refers to the highest obstacle height that the robot can overcome.
- the aforementioned obstacle types include: large steps.
- the information in the vertical direction and the information in the horizontal direction of the two close positions can reflect the obstacle type in the area where the two close positions are located, for example, the obstacle type in the area where the two close positions are located is For the type of large steps, the absolute values of the values in the vertical direction of these two similar positions are usually much greater than the allowable obstacle clearance height. Therefore, through the above method, the obstacle type in the corresponding area can be accurately identified.
- Step S16 controlling the movement of the robot according to the obstacle type.
- the robot controls itself to perform corresponding movements according to different types of obstacles, so as to improve control accuracy.
- the installation height of the first laser sensor on the robot is also the same as that of the second laser sensor
- the coordinates of the first landing point obtained based on the first laser sensor and the coordinates of the second landing point obtained based on the second laser sensor are coordinates corresponding to two different positions. Since the coordinates of two different positions can reflect the height difference between the two positions, combined with the preset allowable obstacle clearance height, the obstacle type corresponding to the area where the two different positions are located can be quickly and accurately identified. For example, identify whether the obstacle type is a step that the robot can climb. For example, the robot can recognize whether there is a step ahead before reaching the step, instead of recognizing whether there is a step ahead when it reaches the step.
- Fig. 26 shows the flow chart of the second robot control method provided by the embodiment of the present disclosure.
- step S31, step S32, step S33, and step S34 are respectively the same as step S11, step S12, step S13 and step S14 are the same, and step S37 and step S38 are respectively the same as step S15 and step S16 of the above-mentioned embodiment, and will not be repeated here.
- the installation height of the first laser sensor on the robot is greater than the installation height of the second laser sensor on the robot, and the distance that the laser emitted from the first laser sensor can reach is greater than that from the second laser sensor.
- the distance that the laser emitted from the laser sensor can reach is detailed as follows:
- step S31 the first sensing distance is obtained by the first laser sensor, and the first sensing distance is the distance between the spot of the laser light emitted by the first laser sensor and the first laser sensor.
- Step S32 acquiring a second sensing distance through the second laser sensor, where the second sensing distance is the distance between the spot of the laser light emitted by the second laser sensor and the second laser sensor.
- Step S33 according to the installation height of the first laser sensor on the robot, the inclination angle and the first sensing distance, determine the coordinates of the first landing point, where the first landing point coordinates are where the light spot of the laser light emitted by the first laser sensor falls. The coordinates of the point.
- Step S34 according to the installation height of the second laser sensor on the robot, the inclination angle and the second sensing distance, determine the second landing point coordinates, the second landing point coordinates are where the light spot of the laser light emitted by the second laser sensor falls The coordinates of the point.
- Step S35 comparing the absolute value of Ya with the allowable obstacle clearance height.
- Ya is the ordinate of the coordinates of the first falling point, and its value may be greater than 0 or less than 0.
- the allowable obstacle clearance height is a value greater than 0.
- Step S36 if the absolute value of Ya is greater than the allowable obstacle clearance height, the robot is controlled to suspend its movement.
- Step S37 according to the coordinates of the first landing point, the coordinates of the second landing point and the preset allowable obstacle clearance height, identify the obstacle type corresponding to the target area.
- the target area is the coordinates of the first landing point and the second landing point. The region where the point coordinates lie.
- Step S38 controlling the movement of the robot according to the obstacle type.
- the installation position of the first laser sensor on the robot is higher than the installation height of the second laser sensor on the robot, And the distance that the laser light emitted from the first laser sensor can reach is greater than the distance that the laser light emitted from the second laser sensor can reach. Therefore, compared with the coordinates of the second falling point, the first falling point The coordinate Ya can reflect the obstacle information at a farther position in front of the robot, which is beneficial for the robot to respond earlier.
- the robot when the absolute value of Ya is greater than the allowable obstacle clearance height, it indicates that there may be an upward step or obstacle in front of the robot, or there may be a downward step, so the robot is first controlled to stop moving, and when the obstacle is judged Then continue to control the movement of the robot after detecting the type of object, so that the robot can have enough time to change its movement when it cannot pass the obstacle, thereby effectively reducing the probability of the robot having an accident.
- the first laser sensor may be a line laser sensor
- the second laser sensor may be a laser ranging sensor
- the first laser sensor is set as line laser sensor, setting the second laser sensor as a laser ranging sensor can not only increase the probability of scanning obstacles, but also reduce costs.
- the step S37 includes:
- the Ya is less than -h and the Yb is not greater than the Ya, it is determined that the obstacle type corresponding to the target area is a large step.
- the Ya is less than the -h, and the Yb is less than 0 but greater than the Ya, it is determined that the obstacle type corresponding to the target area is a downhill slope.
- the obstacle type is a downhill slope
- the step S38 specifically includes:
- the angle corresponding to the downhill slope can be calculated according to the coordinates of the first landing point and the second landing point.
- the robot when the angle corresponding to the downhill slope is not greater than the preset allowable climbing degree, the robot continues to move forward and downhill. When the angle corresponding to the downhill slope is greater than the preset allowable climbing degree, the robot backs up and then turns to change the path.
- the robot after the robot is designed, it usually cannot climb over a slope with a large angle (for example, it cannot exceed the preset allowable climbing degree).
- the angle corresponding to the slope and the preset allowable climbing degree select the corresponding movement, so as to avoid the tipping caused by the robot still moving forward when the angle corresponding to the downhill is too large.
- the step S37 includes:
- the obstacle type is an uphill ramp
- the step S38 specifically includes:
- the angle corresponding to the uphill slope can be calculated according to the coordinates of the first drop point and the second drop point.
- the robot when the angle corresponding to the uphill slope is not greater than the preset allowable climbing degree, the robot continues to move forward and go uphill. When the angle corresponding to the uphill slope is greater than the preset allowable climbing degree, the robot backs up and then turns to change the path.
- the corresponding movement is selected in combination with the angle corresponding to the uphill and the preset allowable degree of climbing, so it is possible to avoid When it is too large, the robot will still move forward and cause it to overturn.
- the installation height of the first laser sensor is greater than the installation height of the second laser sensor
- the reachable distance of the laser light emitted by the first laser sensor is greater than the reachable distance of the laser light emitted by the second laser sensor
- the coordinates of the first landing point are (Xa, Ya)
- the allowable obstacle clearance height is h
- the method also includes:
- the target height is greater than 0 but less than the h, and the speed of the low-speed mode is lower than the speed of the normal mode.
- the target height may be set to h/2.
- the robot is switched from normal mode to The low-speed mode can reduce the probability of robot accidents by predicting in advance, thereby improving the accuracy of robot control.
- the target height is between 0 and h, when it is judged that Ya is not less than the negative number of the target height and not greater than the target height, it indicates that the area in front of the robot has a higher probability that the robot can climb over. At this time, It is only necessary to control the robot to move in a normal mode to ensure that the robot can perform tasks smoothly.
- a control device for cleaning equipment includes: detection equipment and control equipment, the detection equipment is used to detect the operating environment of the cleaning equipment, and obtain environmental characteristic parameters , wherein the environment characteristic parameters include at least one of room characteristic parameters and obstacle parameters; the control device is configured to control the cleaning device to perform cleaning according to at least one of the room characteristic parameters and the obstacle parameters.
- the cleaning device may be a cleaning robot.
- the first selection module 2003 the first operation module 2004, wherein,
- the first obtaining module 2001 is configured to start the cleaning function in the target area at a first rate after obtaining the operation instruction
- the first detection module 2002 is configured to, if it is detected that there is a target obstacle at the first distance in the current forward direction, based on the camera device set on the cleaning robot, obtain the object category corresponding to the target obstacle The recognition result;
- the first selection module 2003 is configured to select a corresponding target obstacle avoidance route based on the identification result, and the target obstacle avoidance route corresponds to one of changing the current heading and not changing the current heading;
- the first running module 2004 is configured to run the cleaning robot based on the target obstacle avoidance route.
- the cleaning function is started in the target area at the first rate; if it is detected that there is a target obstacle at the first distance in the current direction of travel, based on the camera device installed on the cleaning robot, the used Determine the recognition result of the object category corresponding to the target obstacle; based on the recognition result, select the corresponding target obstacle avoidance route, and the target obstacle avoidance route corresponds to one of changing the current forward direction and not changing the current forward direction; based on the target obstacle avoidance route , to run the cleaning robot.
- the robot detects an obstacle ahead, it can select different obstacle avoidance routes according to whether the object type of the obstacle can be identified.
- the purpose of performing different obstacle avoidance methods according to different types of object contours is achieved. Furthermore, the obstacle avoidance ability of the cleaning robot is improved, and the collision avoidance function is realized, which also avoids the problem that the obstacle cannot be completely avoided due to the limited sensing range of the robot.
- the first selection module 2003 is further configured to:
- a first obstacle avoidance route is selected, and the first obstacle avoidance route is used to instruct the cleaning robot to avoid the the course of the target obstacle;
- a second obstacle avoidance route is selected, and the second obstacle avoidance route is used to instruct the cleaning robot to avoid the target obstacle, by Other routes run in the forward direction.
- the first selection module 2003 is further configured to:
- the first obstacle avoidance route is calculated and generated.
- the first selection module 2003 is configured to:
- the first selection module 2003 is configured to:
- a rotation angle for rotating the forward direction of the cleaning robot is determined, and based on the rotation angle, the second obstacle avoidance route is calculated and generated.
- the calculation after the calculation generates the second obstacle avoidance route, it further includes:
- the first detection module 2002 is configured to:
- the first speed is switched to a second speed, wherein the second speed is lower than the first speed, and the first speed is lower than the first speed. the second distance is greater than the first distance;
- the first acquisition module 2001 is configured to:
- sample obstacle information includes parameters of the sample obstacle and object categories corresponding to the sample obstacle
- each sample obstacle is projected onto the initial grid map to generate a semantic map
- start the cleaning function in the target area at the first rate including:
- a cleaning function is started in the target area at the first rate based on the semantic map.
- the first detection module 2002 is configured to:
- the object features include at least one of size features, color features, and contour features;
- the method before acquiring the image of the target obstacle by using the imaging device, the method further includes:
- sample images include at least one obstacle feature
- the preset image semantic segmentation model is trained to obtain the image detection and classification model satisfying the preset condition, the image The detection and classification model is used to determine the object category corresponding to the target obstacle.
- Fig. 32 is a logical structural block diagram of an electronic device according to an exemplary embodiment.
- the electronic device 3000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
- an electronic device 3000 may include one or more of the following components: a processor 3001 and a memory 3002 .
- the processor 3001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like.
- Processor 3001 can adopt at least one hardware form in DSP (Digital Signal Processing, digital signal processing), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, programmable logic array) accomplish.
- the processor 3001 can also include a main processor and a coprocessor, and the main processor is a processor for processing data in a wake-up state, also called a CPU (Central Processing Unit, central processing unit); the coprocessor is Low-power processor for processing data in standby state.
- CPU Central Processing Unit, central processing unit
- the coprocessor is Low-power processor for processing data in standby state.
- the processor 3001 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used for rendering and drawing the content that needs to be displayed on the display screen.
- the processor 3001 may also include an AI (Artificial Intelligence, artificial intelligence) processor, where the AI processor is used to process computing operations related to machine learning.
- AI Artificial Intelligence, artificial intelligence
- Memory 3002 may include one or more computer-readable storage media, which may be non-transitory.
- the memory 3002 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices.
- the non-transitory computer-readable storage medium in the memory 3002 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 3001 to realize the obstacle avoidance provided by the method embodiments of the present disclosure. method.
- the electronic device 3000 may optionally further include: a peripheral device interface 3003 and at least one peripheral device.
- the processor 3001, the memory 3002, and the peripheral device interface 3003 may be connected through buses or signal lines.
- Each peripheral device can be connected to the peripheral device interface 3003 through a bus, a signal line or a circuit board.
- the peripheral device includes: at least one of a radio frequency circuit 3004 , a touch screen 3005 , a camera 3006 , an audio circuit 3007 , a positioning component 3008 and a power supply 3009 .
- the peripheral device interface 3003 may be used to connect at least one peripheral device related to I/O (Input/Output, input/output) to the processor 3001 and the memory 3002 .
- the processor 3001, memory 3002 and peripheral device interface 3003 are integrated on the same chip or circuit board; in some other embodiments, any one of the processor 3001, memory 3002 and peripheral device interface 3003 or The two can be implemented on a separate chip or circuit board, which is not limited in this embodiment.
- the radio frequency circuit 3004 is used to receive and transmit RF (Radio Frequency, radio frequency) signals, also called electromagnetic signals.
- the radio frequency circuit 3004 communicates with the communication network and other communication devices through electromagnetic signals.
- the radio frequency circuit 3004 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals.
- the radio frequency circuit 3004 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and the like.
- the radio frequency circuit 3004 can communicate with other terminals through at least one wireless communication protocol.
- the wireless communication protocol includes but is not limited to: metropolitan area network, mobile communication networks of various generations (2G, 3G, 4G and 5G), wireless local area network and/or WiFi (Wireless Fidelity, wireless fidelity) network.
- the radio frequency circuit 3004 may also include circuits related to NFC (Near Field Communication, short-range wireless communication), which is not limited in the present disclosure.
- the display screen 3005 is used to display a UI (User Interface, user interface).
- the UI can include graphics, text, icons, video, and any combination thereof.
- the display screen 3005 also has the ability to collect touch signals on or above the surface of the display screen 3005 .
- the touch signal can be input to the processor 3001 as a control signal for processing.
- the display screen 3005 can also be used to provide virtual buttons and/or virtual keyboards, also called soft buttons and/or soft keyboards.
- the display screen 3005 may be a flexible display screen, which is set on the curved surface or the folding surface of the electronic device 3000 . Even, the display screen 3005 can also be set as a non-rectangular irregular figure, that is, a special-shaped screen.
- the display screen 3005 can be made of LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, organic light-emitting diode) and other materials.
- the camera assembly 3006 is used to capture images or videos.
- the camera component 3006 includes a front camera and a rear camera.
- the front camera is set on the front panel of the terminal, and the rear camera is set on the back of the terminal.
- there are at least two rear cameras which are any one of the main camera, depth-of-field camera, wide-angle camera, and telephoto camera, so as to realize the fusion of the main camera and the depth-of-field camera to realize the background blur function.
- camera assembly 3006 may also include a flash.
- the flash can be a single-color temperature flash or a dual-color temperature flash. Dual color temperature flash refers to the combination of warm light flash and cold light flash, which can be used for light compensation under different color temperatures.
- Audio circuitry 3007 may include a microphone and speakers.
- the microphone is used to collect sound waves of the user and the environment, and convert the sound waves into electrical signals and input them to the processor 3001 for processing, or input them to the radio frequency circuit 3004 to realize voice communication.
- the microphone can also be an array microphone or an omnidirectional collection microphone.
- the speaker is used to convert the electrical signal from the processor 3001 or the radio frequency circuit 3004 into sound waves.
- the loudspeaker can be a conventional membrane loudspeaker or a piezoelectric ceramic loudspeaker.
- the audio circuit 3007 may also include a headphone jack.
- the positioning component 3008 is used to locate the current geographic location of the electronic device 3000, so as to realize navigation or LBS (Location Based Service, location-based service).
- the positioning component 3008 may be a positioning component based on the GPS (Global Positioning System, Global Positioning System) of the United States, the Beidou system of China, the Greinus system of Russia or the Galileo system of the European Union.
- the power supply 3009 is used to supply power to various components in the electronic device 3000 .
- the power source 3009 can be alternating current, direct current, disposable batteries or rechargeable batteries.
- the rechargeable battery can support wired charging or wireless charging.
- the rechargeable battery can also be used to support fast charging technology.
- the electronic device 3000 further includes one or more sensors 4100 .
- the one or more sensors 4100 include, but are not limited to: an acceleration sensor 4101 , a gyroscope sensor 4102 , a pressure sensor 4103 , a fingerprint sensor 4104 , an optical sensor 4105 and a proximity sensor 4106 .
- the acceleration sensor 4101 can detect the acceleration on the three coordinate axes of the coordinate system established by the electronic device 3000 .
- the acceleration sensor 4101 can be used to detect the components of the acceleration of gravity on the three coordinate axes.
- the processor 3001 can control the touch display screen 3005 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 4101 .
- the acceleration sensor 4101 can also be used for collecting game or user's motion data.
- the gyro sensor 4102 can detect the body direction and rotation angle of the electronic device 3000 , and the gyro sensor 4102 can cooperate with the acceleration sensor 4101 to collect 3D actions of the user on the electronic device 3000 .
- the processor 3001 can realize the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control and inertial navigation.
- the pressure sensor 4103 may be disposed on the side frame of the electronic device 3000 and/or the lower layer of the touch display screen 3005 .
- the pressure sensor 4103 When the pressure sensor 4103 is installed on the side frame of the electronic device 3000 , it can detect the user's grip signal on the electronic device 3000 , and the processor 3001 performs left and right hand recognition or shortcut operation according to the grip signal collected by the pressure sensor 4103 .
- the processor 3001 controls the operable controls on the UI interface according to the user's pressure operation on the touch screen 3005.
- the operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.
- the fingerprint sensor 4104 is used to collect the user's fingerprint, and the processor 3001 identifies the user's identity according to the fingerprint collected by the fingerprint sensor 4104, or the fingerprint sensor 4104 identifies the user's identity according to the collected fingerprint.
- the processor 3001 authorizes the user to perform related sensitive operations, such sensitive operations include unlocking the screen, viewing encrypted information, downloading software, making payment, and changing settings.
- the fingerprint sensor 4104 may be provided on the front, back or side of the electronic device 3000 . When the electronic device 3000 is provided with a physical button or a manufacturer's logo, the fingerprint sensor 4104 may be integrated with the physical button or the manufacturer's Logo.
- the optical sensor 4105 is used to collect ambient light intensity.
- the processor 3001 can control the display brightness of the touch screen 3005 according to the ambient light intensity collected by the optical sensor 4105. Specifically, when the ambient light intensity is high, the display brightness of the touch screen 3005 is increased; when the ambient light intensity is low, the display brightness of the touch screen 3005 is decreased.
- the processor 3001 may also dynamically adjust shooting parameters of the camera assembly 3006 according to the ambient light intensity collected by the optical sensor 4105 .
- the proximity sensor 4106 also known as a distance sensor, is usually arranged on the front panel of the electronic device 3000 .
- the proximity sensor 4106 is used to collect the distance between the user and the front of the electronic device 3000 .
- the processor 3001 controls the touch display screen 3005 to switch from the bright screen state to the off-screen state; when the proximity sensor 4106 When it is detected that the distance between the user and the front of the electronic device 3000 gradually increases, the processor 3001 controls the touch display screen 3005 to switch from the off-screen state to the on-screen state.
- FIG. 32 does not constitute a limitation to the electronic device 3000, and may include more or less components than shown in the figure, or combine certain components, or adopt a different component arrangement.
- a non-transitory computer-readable storage medium including instructions, such as a memory 3002 including instructions, the above instructions can be executed by the processor 3001 of the electronic device 3000 to complete the obstacle avoidance of the above-mentioned cleaning robot
- the method includes: after obtaining the operation command, starting the cleaning function in the target area at a first rate; if it is detected that there is a target obstacle at the first distance in the current direction of travel, based on the camera device set on the cleaning robot, Obtaining a recognition result for determining the object category corresponding to the target obstacle; based on the recognition result, selecting a corresponding target obstacle avoidance route, the target obstacle avoidance route corresponding to changing the current forward direction and not changing the One of the current forward directions; based on the target obstacle avoidance route, run the cleaning robot.
- the above instructions may also be executed by the processor 3001 of the electronic device 3000 to complete other steps involved in the above exemplary embodiments.
- the non-transitory computer readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
- an application program/computer program product comprising one or more instructions executable by the processor 3001 of the electronic device 3000 to complete the obstacle cleaning robot described above
- the avoidance method includes: after obtaining the operation instruction, start the cleaning function in the target area at a first rate; if it is detected that there is a target obstacle at the first distance in the current forward direction, based on the camera device set on the cleaning robot , to obtain a recognition result for determining the object category corresponding to the target obstacle; based on the recognition result, a corresponding target obstacle avoidance route is selected, and the target obstacle avoidance route corresponds to changing the current forward direction and not changing the One of the above-mentioned current forward directions; based on the target obstacle avoidance route, run the cleaning robot.
- the above instructions may also be executed by the processor 3001 of the electronic device 3000 to complete other steps involved in the above exemplary embodiments.
- the cleaning device may be a robot
- the control device may be a robot control device.
- the robot control device 8 is applied to a robot, and the robot is equipped with a first laser sensor With the second laser sensor, the inclination angle of the first laser sensor on the robot body is different from the inclination angle of the second laser sensor on the robot body, and the installation height of the first laser sensor on the robot body is the same as that of the first laser sensor.
- the installation heights of the two laser sensors on the robot body are also different.
- the robot control device 8 includes: a first distance acquisition module 81, a second distance acquisition module 82, a first drop point coordinate determination module 83, and a second drop point coordinate determination module.
- the first distance acquisition module 81 is configured to acquire a first sensing distance through the first laser sensor, where the first sensing distance is the distance between the spot of the laser light emitted by the first laser sensor and the first laser sensor.
- the first laser sensor emits laser light, and when the laser light is blocked, a spot of light will be formed on the blocking object. Since the propagation velocity of light is fixed, the distance between the first laser sensor and the corresponding spot landing point can be calculated according to the propagation velocity of light and its propagation time.
- the first sensing distance in the embodiment of the present disclosure may be calculated by the first laser sensor and sent to the robot by the first laser sensor, or may be calculated by the robot.
- the robot in the embodiment of the present disclosure may be a cleaning device such as a cleaning robot for cleaning.
- the second distance acquisition module 82 is configured to acquire a second sensing distance through the second laser sensor, and the second sensing distance is the distance between the spot of the laser light emitted by the second laser sensor and the second laser sensor.
- the calculation method of the second sensing distance is the same as that of the first sensing distance, and will not be repeated here.
- the first landing point coordinate determination module 83 is used to determine the first landing point coordinates according to the installation height, inclination angle and the first sensing distance of the first laser sensor on the robot, and the first landing point coordinates are the first landing point coordinates.
- the installation height of the first laser sensor on the robot refers to the distance from the installation position of the first laser sensor on the robot to the ground.
- the inclination angle of the first laser sensor on the robot refers to an angle less than 90° among the angles between the laser emitting port of the first laser sensor and the robot.
- the laser emitting point of the first laser sensor is A1, the spot of A1 is A2, the inclination angle of the first laser sensor is, the installation height of the first laser sensor on the robot is H1, and the first The sensing distance is A1A2.
- the laser emitting point of the second laser sensor is B1, the light spot of B1 is B2, the inclination angle of the first laser sensor is, the installation height of the first laser sensor on the robot is H2, and the first sensing distance is B1B2.
- the length of the hypotenuse (such as A1A2) of the right triangle in Fig. 25 and the inclination (such as) can determine the length of the right angle side in the horizontal direction in the right triangle, and then determine the abscissa in A2.
- the length of the right-angled side in the vertical direction of the right-angled triangle can be determined according to the length and inclination of the hypotenuse of the right-angled triangle, and the vertical coordinate of A2 can be calculated by combining the length of the right-angled side with the installation height H1.
- the second landing point coordinate determination module 84 is used to determine the second landing point coordinates according to the installation height, inclination angle and the second sensing distance of the second laser sensor on the robot, and the second landing point coordinates are the second landing point coordinates.
- the calculation method of the coordinates of the second landing point is the same as that of the coordinates of the first landing point, and will not be repeated here.
- the obstacle type identification module 85 is used to identify the obstacle type corresponding to the target area according to the first landing point coordinates, the second landing point coordinates and the preset allowable obstacle clearance height, and the target area is the first landing point coordinates and the area where the coordinates of the second drop point are located.
- the preset allowable obstacle clearance height refers to the highest obstacle height that the robot can overcome.
- the information in the vertical direction and the information in the horizontal direction of the two close positions can reflect the obstacle type in the area where the two close positions are located, for example, the obstacle type in the area where the two close positions are located is
- the values of these two similar positions in the vertical direction are usually much smaller than the allowable obstacle clearance height. Therefore, through the above method, the obstacle type in the corresponding area can be accurately identified.
- the motion control module 86 is used to control the motion of the robot according to the obstacle type.
- the robot controls itself to perform corresponding movements according to different types of obstacles, so as to improve control accuracy.
- the first landing point coordinates and the second landing point coordinates obtained based on the first laser sensor and the second laser sensor are coordinates corresponding to two different positions. Since the coordinates of two different positions can reflect the height difference between the two positions, combined with the preset allowable obstacle clearance height, the obstacle type corresponding to the area where the two different positions are located can be quickly and accurately identified. For example, identify whether the obstacle type is a step that the robot can climb. For example, it is possible to recognize whether there is a step ahead before the robot reaches the step, instead of identifying whether there is a step ahead when it reaches the step.
- the installation height of the first laser sensor is greater than the installation height of the second laser sensor, and the distance that the laser light emitted by the first laser sensor can reach is greater than the distance that the laser light emitted by the second laser sensor can reach , the coordinates of the first falling point are (Xa, Ya), the robot control device 8 also includes:
- the absolute value comparison module is used to compare the absolute value of Ya with the allowable obstacle clearance height.
- Ya is the ordinate of the coordinates of the first falling point, and its value may be greater than 0 or less than 0.
- the allowable obstacle clearance height is a value greater than 0.
- a pause control module configured to control the robot to pause if the absolute value of Ya is greater than the allowable obstacle clearance height.
- the installation position of the first laser sensor on the robot is higher than the installation height of the second laser sensor on the robot, Moreover, the distance that the laser light emitted from the first laser sensor can reach is greater than the distance that the laser light emitted from the second laser sensor can reach. Therefore, compared with the coordinates of the second falling point, the first The Ya of the landing point coordinates can reflect the obstacle information at a farther position in front of the robot, which is beneficial for the robot to respond earlier.
- the robot when the absolute value of Ya is greater than the preset allowable obstacle clearance height, it indicates that there may be an upward step or obstacle in front of the robot, or there may be a downward step, so the robot is first controlled to stop moving, and After judging the type of obstacle and then continuing to control the movement of the robot, the robot can have enough time to change its movement when it cannot pass the obstacle, thereby effectively reducing the probability of the robot having an accident.
- the first laser sensor may be a line laser sensor
- the second laser sensor may be a laser ranging sensor
- the first laser sensor and the second The two laser sensors are respectively set as a line laser sensor and a laser ranging sensor, which can not only increase the probability of scanning obstacles, but also reduce costs.
- the obstacle type identification module 85 is specifically used for:
- the Ya is less than -h, and the Yb is not greater than the Ya, it is determined that the obstacle type corresponding to the target area is a large step;
- the Ya is less than the -h, and the Yb is less than 0 but greater than the Ya, then it is determined that the obstacle type corresponding to the target area is a downhill slope;
- the Ya is less than the -h and the Yb is not less than 0, it is determined that the obstacle type corresponding to the target area is a large step.
- controlling the movement of the robot according to the obstacle type includes:
- the angle corresponding to the downhill slope can be calculated according to the relationship between the coordinates of the first landing point and the coordinates of the second landing point.
- the robot continues to move forward and downhill.
- the robot backs up and then turns to change the path.
- the robot after the robot is designed, it usually cannot climb over a slope with a large angle (for example, it cannot exceed the preset allowable climbing degree).
- the angle corresponding to the slope and the preset allowable climbing degree select the corresponding movement, so as to avoid the tipping caused by the robot still moving forward when the angle corresponding to the downhill is too large.
- the obstacle type identification module 85 is also specifically used for:
- the Ya is greater than the h, and the Xb is not less than the Xa, it is determined that the obstacle type corresponding to the target area is a high obstacle;
- the obstacle type corresponding to the target area is an uphill slope.
- controlling the movement of the robot according to the obstacle type includes:
- the angle corresponding to the uphill slope can be calculated according to the coordinates of the first drop point and the second drop point.
- the robot continues to move forward and go uphill.
- the robot backs up and then turns to change the path.
- the corresponding movement is selected in combination with the angle corresponding to the uphill and the preset allowable degree of climbing, so it is possible to avoid When it is too large, the robot will still move forward and cause it to overturn.
- the installation height of the first laser sensor on the robot is greater than the installation height of the second laser sensor on the robot, and the distance that the laser emitted from the first laser sensor can reach is greater than that from the second laser sensor.
- the distance that the laser light emitted in the laser sensor can reach, the coordinates of the first landing point are (Xa, Ya), and the allowable obstacle-crossing height is h.
- the robot control device 8 also includes a mode switching module, and the mode switching module Used for:
- the robot is controlled to switch from the normal mode to the low-speed mode, the target height is greater than 0 and less than the h, and the speed of the low-speed mode is lower than the speed of the normal mode;
- the target height may be set to h/2.
- the robot is switched from normal mode to The low-speed mode can reduce the probability of robot accidents by predicting in advance, thereby improving the accuracy of robot control.
- the target height is between 0 and h
- Ya is between the negative number of the target height and the target height
- the robot is controlled to switch from the normal mode to the low speed mode.
- Fig. 34 is a schematic structural diagram of a robot provided by an embodiment of the present disclosure.
- the robot 9000 of this embodiment includes: at least one processor 9100 (only one processor is shown in FIG. 34 ), a memory 9101 and stored in the memory 9101 and available on the at least one processor 9100.
- a running computer program 9102 when the processor 9100 executes the computer program 9102, implements the steps in any of the foregoing method embodiments.
- the robot may include, but not limited to, a processor 9100 and a memory 9101.
- FIG. 34 is only an example of the robot 9000, and does not constitute a limitation to the robot 9000. It may include more or less components than shown in the illustration, or combine certain components, or different components, such as It may also include input and output devices, network access devices, etc.
- the so-called processor 9100 may be a central processing unit (Central Processing Unit, CPU), and the processor 9100 may also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit) , ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
- the memory 9101 may be an internal storage unit of the robot 9000 in some embodiments, such as a hard disk or memory of the robot 9000.
- the memory 9101 can also be an external storage device of the robot 9000 in other embodiments, such as a plug-in hard disk equipped on the robot 9000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD ) card, flash memory card (Flash Card), etc.
- the storage 9101 may also include both an internal storage unit of the robot 9000 and an external storage device.
- the memory 9101 is used to store operating systems, application programs, boot loaders (BootLoader), data, and other programs, such as program codes of the computer programs.
- the memory 91 can also be used to temporarily store data that has been output or will be output.
- An embodiment of the present disclosure also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and operable on the at least one processor, and the processor executes the computer program implement the steps in any of the above method embodiments.
- the embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be realized.
- An embodiment of the present disclosure provides a computer program product, which, when the computer program product is run on a mobile terminal, enables the mobile terminal to realize the steps in the foregoing method embodiments when executed.
- the room characteristic parameter includes room characteristic information of the room
- the obstacle parameter includes the position of an object in the room
- the control device is further configured to,
- the cleaning device is controlled to avoid the position of the object and operate according to the cleaning parameters.
- FIG. 35 shows a schematic block diagram of a control device 9200 for cleaning equipment.
- the control device 9200 of the cleaning equipment includes a second acquisition module 9202 , a second determination module 9204 and a second control module 9206 .
- the second obtaining module 9202 can obtain the room characteristic information of the room to be cleaned by the cleaning equipment and the position of objects in the room to be cleaned; the second determination module 9204 can determine the cleaning parameters based on the room characteristic information of the room to be cleaned; the second control Module 9206 can control the cleaning equipment to work according to the cleaning parameters, and avoid the position of objects in the room to be cleaned during the work.
- the cleaning device can be a sweeping robot, a mopping robot, a sweeping and mopping machine, etc., which can move in multiple rooms, so as to achieve the purpose of cleaning in different rooms.
- the cleaning equipment is equipped with cameras, infrared sensors and other equipment, which can collect room characteristic information in the room and the specific position of fixed objects in the room.
- the position characteristic information of the object can indicate the type of room, the floor layout in the room and so on.
- the corresponding cleaning parameters are determined according to the room characteristic information in the room, and the route of the cleaning equipment is determined according to the specific position of the fixed object, so that the cleaning equipment can avoid the specific position of the fixed object and move, and perform cleaning work according to the control information .
- the cleaning equipment can adaptively set a reasonable cleaning method based on the specific conditions of the room, realize more intelligent and customized cleaning, and improve the efficiency and accuracy of room cleaning.
- the room characteristic information may include the type of the room, so that the second determining module 9204 can determine the first cleaning parameter of the cleaning device according to the type of the room.
- the cleaning parameters of the cleaning device include the first cleaning parameter
- the room may include a bedroom, a living room, a kitchen or a bathroom, and the first cleaning parameters such as the cleaning priority and cleaning degree of the cleaning device in different types of rooms may be different.
- the cleaning priority is greater than or equal to the first threshold, and based on the room being a bathroom or a kitchen, the cleaning priority is less than the first threshold.
- the degree of dirtiness of the bathroom or the kitchen is larger than that of the bedroom or the living room, the degree of cleanliness of the bathroom or the kitchen is also large. That is to say, when the room type is a bathroom or a kitchen, the cleanliness degree is greater than or equal to the second threshold, and when the room type is a bedroom or a living room, the cleanliness degree is less than the second threshold.
- the room feature information may include the material of the floor, for example, the material includes wood (such as floor), porcelain, stone (such as floor tile), concrete, and the like.
- the cleaning parameters of the cleaning device include a second cleaning parameter, and the second cleaning parameter may be at least one of water output, cleaning times, and fan suction.
- the second determination module 9204 can correspondingly determine the water output, cleaning times, fan suction, etc. of the cleaning equipment based on the material of the floor of the room.
- the water output of the cleaning equipment is less than or equal to the third threshold; when the material of the ground paving is porcelain or stone, the water output of the cleaning equipment is greater than the third threshold
- the threshold is less than or equal to the fourth threshold; in the case that the floor material is concrete, the water output of the cleaning equipment is greater than the fourth threshold, wherein the fourth threshold is greater than the third threshold.
- the number of times the cleaning equipment cleans is greater than or equal to the fifth threshold; when the floor material is porcelain or stone, the cleaning frequency of the cleaning equipment is less than the fifth threshold.
- the threshold is greater than or equal to the sixth threshold; when the floor material is concrete, the cleaning frequency of the cleaning equipment is less than the sixth threshold, wherein the sixth threshold is less than the fifth threshold.
- the second determination module 9204 can also determine the relative position information between the object and the ground in the room, the relative position information can indicate whether there is a gap between the object and the ground, and if there is a gap, the gap size of.
- the second determination module 9204 determines whether there is a gap or the size of the gap when there is a gap, so that the second control module 9206 can control whether the cleaning device moves away from the object based on the relative position information.
- control device 9200 of the cleaning equipment also includes a collection module capable of collecting the first image of the room, and the second determination module 9204 specifies the specific room that the cleaning equipment enters based on the first image, and then according to the room and the characteristics of the room
- the preset corresponding relationship between the information and the position of the object determines the room characteristic information corresponding to the room and the position of the object.
- the second control module 9206 is also used to control the movement of the cleaning equipment in the room, and the acquisition module is also used to acquire the second image of the room during the movement of the cleaning equipment to realize positioning and mapping. Further, the second control module 9206 is also used to identify the room feature information and the location of the object in the second image, and store the room name in correspondence with the room feature information and the location of the object, so as to establish a preset correspondence .
- FIG. 36 shows a schematic block diagram of a cleaning device 1001 in the embodiment of the present disclosure.
- the cleaning device 1001 includes a memory 1002 and a processor 1004 .
- the memory 1002 stores programs or instructions
- the processor 1004 implements the steps of the cleaning device control method according to any of the above technical solutions when executing the programs or instructions.
- the memory 1002 and the processor 1004 may be connected via a bus or other means.
- the processor 1004 can include one or more processing units, and the processor 1004 can be a central processing unit (Central Processing Unit, CPU), a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC ), Field Programmable Gate Array (Field Programmable Gate Array, FPGA) and other chips.
- CPU Central Processing Unit
- DSP digital signal processor
- ASIC Application Specific Integrated Circuit
- FPGA Field Programmable Gate Array
- the cleaning device 1001 provided in the present disclosure, when the program or instruction is executed by the processor 1004, implements the steps of the cleaning device control method of any of the above technical solutions, so the cleaning device 1001 includes the cleaning device control method of any of the above technical solutions all beneficial effects.
- the cleaning device 1001 may be a mopping machine or an all-in-one sweeping and mopping machine.
- FIG. 37 shows a schematic block diagram of a cleaning device 1100 in this embodiment of the disclosure.
- the cleaning equipment 1100 includes a cleaning equipment control device 9200 according to the above technical solution.
- the cleaning device 1100 provided in the present disclosure includes the cleaning device control device 9200 of the above technical solution, so the cleaning device 1100 includes all the beneficial effects of the cleaning device control device 9200 of any of the above technical solutions.
- Embodiments of the present disclosure provide a readable storage medium on which programs or instructions are stored. When the programs or instructions are executed by a processor, the steps of the cleaning device control method according to any of the above technical solutions are implemented.
- the readable storage medium includes a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
- ROM Read-Only Memory
- RAM Random Access Memory
- magnetic disk or an optical disk and the like.
- the readable storage medium provided by the present disclosure, when the program or instruction is executed by the processor, implements the steps of the cleaning device control method of any of the above technical solutions, so the readable storage medium includes the control of the cleaning device of any of the above technical solutions All beneficial effects of the method.
- the room feature parameters include ground feature information of the room, wherein the control device is further configured to determine control information according to the ground feature information, and determine the control information according to the control Information controls the operation of the cleaning device.
- FIG. 38 shows a schematic block diagram of a mobile device control device 4000 according to an embodiment of the present disclosure.
- the control apparatus 4000 of the mobile device includes a third acquisition module 4002 and a third control module 4004 .
- the third obtaining module 4002 can obtain the ground feature information of the room, and the third control module 4004 can determine the control information for the mobile device based on the ground feature information, and control the mobile device to work according to the control information.
- the movable device may be a cleaning device such as a sweeping robot, a mopping robot, or an all-in-one sweeping and mopping machine, which can move in multiple rooms, thereby achieving the purpose of cleaning in different rooms.
- a cleaning device such as a sweeping robot, a mopping robot, or an all-in-one sweeping and mopping machine, which can move in multiple rooms, thereby achieving the purpose of cleaning in different rooms.
- the mobile device is equipped with devices such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, corresponding control information is determined according to the ground feature information in the room, so that the mobile device performs cleaning work according to the control information.
- devices such as a camera and an infrared sensor, which can collect ground feature information in the room, and the ground feature information can indicate the floor layout in the room. Further, corresponding control information is determined according to the ground feature information in the room, so that the mobile device performs cleaning work according to the control information.
- the mobile device can realize more intelligent and customized cleaning based on the ground conditions of the room, and improve the efficiency and accuracy of room cleaning.
- FIG. 39 shows a schematic block diagram of a mobile device 1400 according to an embodiment of the present disclosure.
- the mobile device 1400 includes a memory 1402 and a processor 1404 .
- the memory 1402 is used to store programs or instructions; the processor 1404 is used to implement the steps of the mobile device control method according to any of the above technical solutions when executing the programs or instructions.
- the memory 1402 and the processor 1404 may be connected through a bus or in other ways.
- the processor 1404 may include one or more processing units, and the processor 1404 may be a central processing unit (Central Processing Unit, CPU), a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (Field Programmable Gate Array, FPGA) and other chips.
- CPU Central Processing Unit
- DSP Digital Signal Processor
- ASIC Application Specific Integrated Circuit
- FPGA Field Programmable Gate Array
- the mobile device 1400 provided in this disclosure when the program or instructions are executed by the processor 1404, implements the steps of the control method for the mobile device according to any of the above technical solutions, so the mobile device 1400 includes the mobile devices of any of the above technical solutions The full benefit of the control method of the device.
- FIG. 40 shows a schematic block diagram of a mobile device 1500 according to an embodiment of the present disclosure.
- the mobile device 1500 includes the control device 4000 for the mobile device according to the above technical solution.
- the mobile device 1500 provided in the present disclosure includes the mobile device control device 4000 of the above technical solution, so the mobile device 1500 includes all the beneficial effects of the mobile device control device 4000 of any of the above technical solutions.
- Embodiments of the present disclosure also provide a readable storage medium on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the steps of the method for controlling a mobile device according to any of the above technical solutions are implemented.
- the readable storage medium includes a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
- ROM Read-Only Memory
- RAM Random Access Memory
- magnetic disk or an optical disk and the like.
- the readable storage medium provided by the present disclosure, when the program or instruction is executed by the processor, implements the steps of the control method for the mobile device of any of the above technical solutions, so the readable storage medium includes the mobile device of any of the above technical solutions The full beneficial effect of the control method.
- first and second are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Thus, a feature defined as “first” and “second” may explicitly or implicitly include one or more of these features. Further, in the description of the present disclosure, unless otherwise specified, "plurality" means two or more.
- references to the terms “one embodiment,” “some embodiments,” “exemplary embodiments,” “example,” “specific examples,” or “some examples” are intended to mean that the implementation A specific feature, structure, material, or characteristic described by an embodiment or example is included in at least one embodiment or example of the present disclosure.
- schematic representations of the above terms do not necessarily refer to the same embodiment or example.
- the specific features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Electric Vacuum Cleaner (AREA)
Abstract
一种清洁设备的控制方法、清洁设备的控制装置、清洁设备和可读存储介质,清洁设备的控制方法包括:对清洁设备的运行环境进行检测,获取环境特征参数,环境特征参数包括房间特征参数和障碍物参数中的至少一个;根据房间特征参数和障碍物参数中的至少一个,控制清洁设备进行清洁。本申请能够基于房间特征参数和障碍物参数中的至少一个对清洁设备进行控制,实现不同场景下采用不同的清扫控制方式,充分满足用户的需求。
Description
相关申请的交叉引用
本公开要求分别于,2021年12月28日提交的申请号为202111633171.4、名称为“机器人控制方法、装置及机器人”,2022年01月07日提交的申请号为202210018305.X、名称为“清洁机器人的障碍躲避方法、装置、电子设备以及介质”,2022年02月17日提交的申请号为202210145455.7、名称为“清洁设备的控制方法、装置、清洁设备和可读存储介质”,2022年02月17日提交的申请号为202210145556.4、名称为“可移动设备的控制方法、装置、可移动设备和存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本公开中。
本公开涉及设备控制技术领域,特别涉及一种清洁设备的控制方法、清洁设备的控制装置、清洁设备和可读存储介质。
相关技术中,清扫设备的智能化程度主要体现在导航运动精度的提高、孤立物体的识别与免碰撞、分割区域的不遗漏清扫等。但对于清扫策略,并没有精细的控制方法,导致清扫设备的清扫策略单一、不够智能化。
公开内容
本公开旨在至少在一定程度上解决相关技术中的技术问题之一。为此,本公开的第一个目的在于提出一种清洁设备的控制方法,能够基于房间特征参数和障碍物参数中的至少一个对清洁设备进行控制,实现不同场景下采用的不同的清扫控制方式,充分满足用户的需求。
本公开的第二个目的在于提出一种清洁设备的控制装置。
本公开的第三个目的在于提出一种清洁设备。
本公开的第四个目的在于提出一种可读存储介质。
为达到上述目的,本公开一方面实施例提出了一种清洁设备的控制方法,所述方法包括:对所述清洁设备的运行环境进行检测,获取环境特征参数,其中,所述环境特征参数包括房间特征参数和障碍物参数中的至少一个;根据所述房间特征参数和所述障碍物参数中的至少一个,控制所述清洁设备进行清洁。
可选地,所述房间特征参数包括房间的地面特征信息,其中,所述根据所述房间特征参数,控制所述清洁设备进行清洁,包括:根据所述地面特征信息确定控制信息,并根据所述控制信息控制所述清洁设备工作。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的地面特征信息,该地面特征信息能够表示出房间内的地面铺设情况。进一步地,根据该房间内的地面特征信息确定对应的控制信息,从而使得清洁设备按照该控制信息进行清洁工作。
通过上述方式,清洁设备能够基于房间的地面情况,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
在上述技术方案中,地面特征信息包括地面铺设材质,根据地面特征信息确定控制信息,包括:确定与地面铺设材质对应的第一控制信息;其中,第一控制信息包括以下至少一项:出水量、清洁次数、风机吸力、移动速度。
在该技术方案中,地面特征信息可以包括地面铺设的材质,例如材质包括木质(例如地板)、资质、石质(例如地砖)等。
清洁设备的控制信息包括第一控制信息,第一控制信息可以为出水量、清洁次数、风机吸力、移动速度中的至少一项。
具体地,基于房间的地面铺设的材质,对应确定清洁设备工作的出水量、风机吸力、移动速度,以及确定清洁设备对该房间的清洁次数。
通过上述方式,清洁设备能够基于房间内地面铺设的材质,对该房间实现更加个性化、智能化的清洁。
在上述任一技术方案中,地面铺设材质为木质情况下的出水量小于地面铺设材质为瓷质或石质情况下的出水量。
在该技术方案中,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以相对增加清洁设备进行清洁时的出水量,从而提高对地砖的清洁程度,保证清洁效果。
在上述任一技术方案中,地面铺设材质为木质情况下的清洁次数大于地面铺设材质为瓷质或石质情况下的清洁次数。
在该技术方案中,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板,同时增加清洁次数,以保证清洁效果。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以相对增加清洁设备进行清洁时的出水量,从而提高对地砖的清洁程度,保证清洁效果,同时相对减少清洁次数,以减少清洁设备的电能的浪费。
在上述任一技术方案中,地面特征信息包括地面铺设方向,根据地面特征信息确定控制信息,包括:确定与地面铺设方向对应的第二控制信息;其中,第二控制信息为清洁设备的清洁方向与地面铺设方向一致。
在该技术方案中,地面特征信息可以包括地面铺设的方向,也即,地面铺设的地板或地砖的纹理。
清洁设备的控制信息包括第二控制信息,第二控制信息可以为清洁设备的清洁方向的控制信息。
具体地,基于房间的地面铺设的方向,对应确定清洁设备的清洁方向,使得清洁设备的清洁方向与地面铺设的方向相同,也就是说清洁设备的清洁方向平行于地面铺设的方向。
通过上述方式,清洁设备能够平行于房间内地面铺设的方向进行清洁,从而减少地板或地砖的缝隙内残留的灰尘、水渍等,以及使得清洁设备在地板或地砖上的清洁痕迹不混乱,提高清洁效果。
在上述任一技术方案中,地面特征信息包括地面尺寸,根据地面特征信息确定控制信息,包括:根据地面尺寸确定房间的类型;确定与房间的类型对应的第三控制信息。
在该技术方案中,地面特征信息可以包括地面尺寸,也即,房间的尺寸,清洁设备的控制信息包括第三控制信息。
具体地,基于房间的地面尺寸,判定房间的大小,从而判定房间的类型,进而根据房间的类型对应确定清洁设备的第三控制信息。
通过上述方式,能够按照房间的类型,自适应地控制清洁设备的清洁,从而提高房间清洁的高效性、准确性。
在上述任一技术方案中,房间的类型包括以下至少一项:卧室、客厅、厨房、卫生间;第三控制信息包括以下至少一项:房间清洁顺序、清洁剂量、消毒剂量。
在该技术方案中,房间可以包括卧室、客厅、厨房或卫生间,清洁设备在不同类型的房间的清洁方式可以不同。
清洁设备的第三控制信息可以为房间清洁顺序、清洁剂量、消毒剂量中的至少一项。例如,在确定房间为卧室时,可以对该房间进行优先清洁,在确定房间为客厅时,可以在清洁完卧室后对客厅进行清洁;在确定房间为厨房或卫生间时,清洁设备可以喷洒清洁剂、消毒剂等。
通过上述方式,实现更加智能化、定制化的清洁。
在上述任一技术方案中,地面特征信息包括插座位置,根据地面特征信息确定控制信息,包括:确定与插座位置对应的第四控制信息。
在该技术方案中,地面特征信息可以包括插座位置,也即,地面上安装的插座的位置,清洁设备的控制信息包括第四控制信息,该第四控制信息用于控制清洁设备的移动路线。
具体地,基于房间地面上的插座位置,控制清洁设备的移动路线,以避免清洁设备清洁插座位置出现漏电风险,提高清洁过程中的安全性。
在上述任一技术方案中,第四控制信息为清洁设备的清洁范围为插座位置的预设范围外。
在该技术方案中,如果识别到房间内安装在地面的插座,清洁设备可以在清洁时与该插座保持一定的安全距离,也即,在距离该插座的预设范围外进行清洁,例如在距离该插座10厘米或20厘米外进行清洁。
通过上述方式,避免清洁设备清洁插座位置出现漏电风险,提高清洁过程中的安全性。
在上述任一技术方案中,地面特征信息包括房间的房间分界特征,根据地面特征信息确定控制信息,包括:基于房间分界特征的高度小于或等于预设阈值,确定与房间分界特征对应的控制信息。
在该技术方案中,地面特征信息可以包括房间的房间分界特征,例如过门条、门槛石、移门轨道等。
当识别到房间分界特征的高度没有超过预设阈值时,表明房间分界特征高度较低,则可以控制清洁设备对该位置进行清洁;当识别到房间分界特征的高度超过预设阈值时,表明房间分界特征高度较高,则可以使清洁设备不对该位置进行清洁,避免清洁设备在房间分界特征处被卡住。
在上述任一技术方案中,获取房间的地面特征信息,包括:获取房间的房间分界特征;基于清洁设备经过房间分界特征进入房间,获取房间的地面特征信息。
在该技术方案中,房间分界特征为房间分割的重要依据,可以包括过门条、门槛石、移门轨道等。
在识别到清洁设备经过房间分界特征进入房间时,采集该房间的地面特征信息,进而按照与地面特征信息对应的控制信息,控制清洁设备进行房间清洁。
通过上述方式,根据房间分界特征,可精准地确定清洁设备是否进入房间,从而在进入房间后采集地面特征信息,实现地面特征信息的及时、准确地采集。
可选地,所述房间特征参数包括房间的房间特征信息,所述障碍物参数包括所述房间内的物体的位置,其中,根据所述房间特征参数和所述障碍物参数,控制所述清洁设备进行清洁,包括:根据所述房间特征信息确定清洁参数;控制所述清洁设备避开所述物体的位置,并按照所述清洁参数工作。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的房间特征信息以及房间内的固定物体的具***置,该物体的位置特征信息能够表示出房间类型、房间内的地面铺设等情况。
进一步地,根据该房间内的房间特征信息确定对应的清洁参数,根据固定物体的具***置确定清洁设备的路线,使得清洁设备能够避开固定物体的具***置移动,且按照该控制信息进行清洁工作。
通过上述方式,清洁设备能够基于房间的具体情况,自适应设置合理的清洁方式,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
在上述技术方案中,房间特征信息包括房间类型,根据房间特征信息确定清洁参数,包括:确定与房间类型对应的第一清洁参数;其中,第一清洁参数包括以下至少一项:清洁优先级、清洁程度。
在该技术方案中,房间特征信息可以包括房间的类型,进而能够根据房间的类型对应确定清洁设备的第一清洁参数。
其中,清洁设备的清洁参数包括第一清洁参数,房间可以包括卧室、客厅、厨房或卫生间,清洁设备在不同类型的房间的清洁优先级、清洁程度等第一清洁参数可以不同。
通过上述方式,能够按照房间的类型,自适应地控制清洁设备的清洁方式,从而提高房间清洁的高效性、准确性。
在上述任一技术方案中,房间类型为卧室或客厅情况下的清洁优先级,大于房间类型为卫生间或厨房情况下的清洁优先级。
在该技术方案中,在房间为卧室或客厅的情况下,清洁优先级大于或等于第一阈值,基于房间为卫生间或厨房,清洁优先级小于第一阈值。
通过上述方式,实现更加智能化、定制化的清洁。
在上述任一技术方案中,房间类型为卫生间或厨房情况下的清洁程度,大于房间类型为卧室或客厅情况下的清洁程度。
在该技术方案中,由于卫生间或厨房的脏污程度相比于卧室或客厅的脏污程度要大,所以对卫生间或厨房的清洁程度也要大。也就是说,在房间类型为卫生间或厨房的情况下,清洁程度大于或等于第二阈值,在房间类型为卧室或客厅的情况下,清洁程度小于第二阈值。
通过上述方式,实现更加智能化、定制化的清洁。
在上述任一技术方案中,房间特征信息包括地面铺设材质,根据房间特征信息确定清洁参数,包括:确定与地面铺设材质对应的第二清洁参数;其中,第二清洁参数包括以下至少一项:出水量、清洁次数、风机吸力。
在该技术方案中,房间特征信息可以包括地面铺设的材质,例如材质包括木质(例如地板)、瓷质、石质(例如地砖)、混凝土等。
清洁设备的清洁参数包括第二清洁参数,第二清洁参数可以为出水量、清洁次数、风机吸力中的至少一项。
具体地,基于房间的地面铺设的材质,对应确定清洁设备工作的出水量、清洁次数、风机吸力等。
通过上述方式,清洁设备能够基于房间内地面铺设的材质,对该房间实现更加个性化、智能化的清洁。
在上述任一技术方案中,地面铺设材质为木质情况下的出水量、地面铺设材质为瓷质或石质情况下的出水量、地面铺设材质为混凝土情况下的出水量依次增大。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的出水量小于或等于第三阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的出水量大于第三阈值且 小于或等于第四阈值;在地面铺设材质为混凝土的情况下,清洁设备的出水量大于第四阈值,其中第四阈值大于第三阈值。
具体地,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以相对减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以控制清洁设备进行清洁时的出水量适中,从而提高对地砖的清洁程度,保证清洁效果。
如果识别到房间内地面铺设的材质为混凝土,也就是说,房间内铺设的是水泥,则可以相对增加清洁设备进行清洁时的出水量,从而提高对水泥地面的清洁程度,保证清洁效果。
在上述任一技术方案中,地面铺设材质为木质情况下的清洁次数、地面铺设材质为瓷质或石质情况下的清洁次数、地面铺设材质为混凝土情况下的清洁次数依次减小。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的清洁次数大于或等于第五阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的清洁次数小于第五阈值且大于或等于第六阈值;在地面铺设材质为混凝土的情况下,清洁设备的清洁次数小于第六阈值,其中第六阈值小于第五阈值。
具体地,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以相对减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板,同时增加清洁设备的清洁次数,以保证清洁效果。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以控制清洁设备进行清洁时的出水量、清洁次数适中,从而提高对地砖的清洁程度,保证清洁效果。
如果识别到房间内地面铺设的材质为混凝土,也就是说,房间内铺设的是水泥,则可以相对增加清洁设备进行清洁时的出水量,从而提高对水泥地面的清洁程度,保证清洁效果,同时相对减少清洁次数,以减少清洁设备的电能的浪费。
在上述任一技术方案中,控制清洁设备避开物***置,包括:确定物体与房间的地面的相对位置信息;根据相对位置信息,控制清洁设备避开物体的位置。
在该技术方案中,确定房间内物体与地面之间的相对位置信息,该相对位置信息能够表示出物体与地面之间是否有空隙,以及在有空隙的情况下空隙的尺寸。进而根据是否有空隙或者有空隙时空隙的尺寸,控制清洁设备是否避开物体运动。
通过上述方式,实现对清洁设备避开物体的方式进行控制,提高对房间的清洁效果。
在上述任一技术方案中,获取环境特征参数,包括:采集房间的第一图像,根据第一图像识别房间;根据预设对应关系,确定与房间对应的房间特征信息以及物体的位置。
在该技术方案中,通过采集房间的第一图像,基于该第一图像明确清洁设备所进入的具体房间,进而根据房间与房间特征信息以及物体的位置之间的预设对应关系,确定 与该房间所对应的房间特征信息、物体的位置。
也就是说,预先存储有房间与房间特征信息、物体的位置之间的预设对应关系,在根据第一图像明确了具体房间后,即可得到该房间所对应的房间特征信息和物体的位置。
通过上述方式,在明确了所进入的房间后即可根据预设对应关系,获得预先存储的房间特征信息和物体的位置,无需通过图像来识别房间特征信息和物体的位置,提高了房间特征信息和物体的位置获取的准确性和及时性。
在上述任一技术方案中,在获取环境特征参数之前,还包括:控制清洁设备在房间内移动并采集房间的第二图像;根据第二图像,确定房间特征信息和物体的位置,并建立预设对应关系。
在该技术方案中,控制清洁设备在房间内移动,并在移动过程中获取该房间的第二图像,实现定位建图。进一步地,在第二图像中识别出该房间的房间特征信息以及物体的位置,并将房间名称与房间特征信息以及物体的位置对应存储,实现建立预设对应关系。
在清洁设备进行下次清扫时,根据预设对应关系,确定房间特征信息以及物体的位置,从而实现分类制定清洁方案,提高清洁设备的智能性。
可选地,所述清洁设备为清洁机器人,其中,根据所述障碍物参数,控制所述清洁设备进行清洁,包括:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。
可选地,在基于本公开上述方法的另一个实施例中,所述基于所述识别结果,选取对应的目标障碍躲避路线,包括:
若确定能够识别所述目标障碍物对应的物体类别,选取第一障碍躲避路线,所述第一障碍躲避路线为用于指示所述清洁机器人在不更改当前前进方向的情况下,绕开所述目标障碍物的路线;或,
若确定不能够识别所述目标障碍物对应的物体类别,选取第二障碍躲避路线,所述第二障碍躲避路线为用于指示所述清洁机器人以绕开所述目标障碍物的情况下,以其他前进方向运行的路线。
可选地,在基于本公开上述方法的另一个实施例中,所述若确定能够识别所述目标障碍物对应的物体类别,选取第一障碍躲避路线,包括:
确定所述目标障碍物对应的物体类别,并基于预存的障碍物数据集合,得到所述物体类别对应的轮廓参数以及尺寸参数;
基于所述轮廓参数以及尺寸参数,计算得到所述目标障碍物的外切图像;
基于所述外切图像以及purePuresuit算法,计算生成所述第一障碍躲避路线。
可选地,在基于本公开上述方法的另一个实施例中,在所述计算生成所述第一障碍躲避路线之后,所述方法还包括:
选取所述第一障碍躲避路线并运行所述清洁机器人;
当检测到所述清洁机器人绕开所述目标障碍物且朝向至所述当前前进方向前进时,确定所述清洁机器人的障碍躲避完成。
可选地,在基于本公开上述方法的另一个实施例中,所述若确定不能够识别所述目标障碍物对应的物体类别,选取第二障碍躲避路线,包括:
若确定不能够识别所述目标障碍物对应的物体类别,获取所述目标障碍物与所述清洁机器人的平行角度差值;
基于所述平行角度差值,确定用于旋转所述清洁机器人前进方向的旋转角度,并基于所述旋转角度,计算生成所述第二障碍躲避路线。
可选地,在基于本公开上述方法的另一个实施例中,在所述计算生成所述第二障碍躲避路线之后,所述方法还包括:
选取所述第二障碍躲避路线并运行所述清洁机器人;
当检测到所述清洁机器人朝向所述其他前进方向前进并且距离所述目标障碍物超过第二距离时,确定所述清洁机器人的障碍躲避完成。
可选地,在基于本公开上述方法的另一个实施例中,在所述以第一速率在目标区域启动清洁功能之后,所述方法还包括:
若检测到当前前进方向的第二距离处存在有所述目标障碍物时,将所述第一速率切换为第二速率,其中,所述第二速率低于所述第一速率,所述第二距离大于所述第一距离;
检测所述目标障碍物是否位于所述当前前进方向的第一距离处。
可选地,在基于本公开上述方法的另一个实施例中,在所述以第一速率在目标区域启动清洁功能之前,所述方法还包括:
获取所述目标区域的初始栅格地图,机器姿态信息,样本障碍物信息,其中所述样本障碍物信息包括样本障碍物的参数以及所述样本障碍物对应的物体类别;
通过Bresenham算法,将各个样本障碍物投影到所述初始栅格地图上,生成语义地图;
所述获取运行指令后,以第一速率在目标区域启动清洁功能,包括:
当获取到所述运行指令后,基于所述语义地图以所述第一速率在所述目标区域启动清洁功能。
可选地,在基于本公开上述方法的另一个实施例中,所述基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果,包括:
利用所述摄像装置,获取所述目标障碍物图像;
利用图像检测分类模型,提取所述目标障碍物图像的物体特征,所述物体特征包括大小特征、色彩特征以及轮廓特征的至少一种;
确定存在所述物体特征,确定所述目标障碍物对应的物体类别的识别结果。
可选地,在基于本公开上述方法的另一个实施例中,在所述利用所述摄像装置,获取所述目标障碍物图像之前,所述方法还包括:
获取至少两个的样本图像,其中,所述样本图像中包括至少一个障碍物体特征;
基于所述障碍物的物体类别,对各个所述样本图像标注对应的类别标识;
利用所述标注有类别标识的样本图像,以及所述样本图像中包括的障碍物体特征,对预设的图像语义分割模型进行训练,得到满足预设条件的所述图像检测分类模型,所述图像检测分类模型用于确定所述目标障碍物对应的物体类别。
本公开中,在获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果;基于识别结果,选取对应的目标障碍躲避路线,目标障碍躲避路线对应于更改当前前进方向以及不更改当前前进方向的其中一种;基于目标障碍躲避路线,运行清洁机器人。通过应用本公开的技术方案,可以在机器人检测到前方存在障碍物时,根据是否能对该障碍物的物体类别进行识别来对应选取不同的障碍躲避路线。从而实现依据不同类型的物体轮廓进行不同绕障方法的目的。进而提高清洁机器人的避障能力,实现免碰撞的功能,也就避免了由于机器人感知范围有限所导致的无法完全避开障碍物的问题。
可选地,所述清洁设备为机器人,所述机器人安装有第一激光传感器和第二激光传感器,所述第一激光传感器在所述机器人上的倾角和所述第二激光传感器在所述机器人上的倾角不同,且所述第一激光传感器在所述机器人上的安装高度和所述第二激光传感器在所述机器人上的安装高度也不同,其中,根据所述障碍物参数,控制所述清洁设备进行清洁,包括:
通过所述第一激光传感器获取第一传感距离,所述第一传感距离为所述第一激光传感器发射的激光的光斑落点与所述第一激光传感器的距离;
通过所述第二激光传感器获取第二传感距离,所述第二传感距离为所述第二激光传感器发射的激光的光斑落点与所述第二激光传感器的距离;
根据所述第一激光传感器在所述机器人的安装高度、倾角以及所述第一传感距离,确定第一落点坐标,所述第一落点坐标为所述第一激光传感器发射的激光的光斑落点的坐标;
根据所述第二激光传感器在所述机器人的安装高度、倾角以及所述第二传感距离,确定第二落点坐标,所述第二落点坐标为所述第二激光传感器发射的激光的光斑落点的坐标;
根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,所述目标区域为所述第一落点坐标和所述第二落点坐标所在的区域;
根据所述障碍物类型控制所述机器人的运动。
可选地,所述第一激光传感器的安装高度大于所述第二激光传感器的安装高度,且所述第一激光传感器发射的激光能够到达的距离大于所述第二激光传感器发射的激光能够到达的距离,所述第一落点坐标为(Xa,Ya),在所述识别目标区域对应的障碍物类型之前,所述方法还包括:
将所述Ya的绝对值与所述允许越障高度比较;
若所述Ya的绝对值大于所述允许越障高度,则控制所述机器人暂停运动。
可选地,所述第二落点坐标为(Xb,Yb),所述允许越障高度为h,所述根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,包括:
若所述Ya小于-h,且所述Yb不大于所述Ya,则判定所述目标区域对应的障碍物类型为大台阶;
若所述Ya小于所述-h,且所述Yb小于0但大于所述Ya,则判定所述目标区域对应的障碍物类型为下坡道;
若所述Ya小于所述-h,且所述Yb不小于0,则判定所述目标区域对应的障碍物类型为大台阶。
可选地,所述障碍物类型为下坡道,所述根据所述障碍物类型控制所述机器人的运动,包括:
确定所述下坡道对应的角度;
根据所述下坡道对应的角度和预设的允许爬坡度数,控制所述机器人的运动。
可选地,所述第二落点坐标为(Xb,Yb),所述允许越障高度为h,所述根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,包括:
若所述Ya大于所述h,且所述Xb不小于所述Xa,则判定所述目标区域对应的障碍物类型为高障碍物;
若所述Ya大于所述h,且所述Xb小于所述Xa,则判定所述目标区域对应的障碍物类型为上坡道。
可选地,所述障碍物类型为上坡道,所述根据所述障碍物类型控制所述机器人的运动,包括:
确定所述上坡道对应的角度;
根据所述上坡道对应的角度和预设的允许爬坡度数,控制所述机器人的运动。
可选地,所述第一激光传感器的安装高度大于所述第二激光传感器的安装高度、所述 第一激光传感器发射的激光能够到达的距离大于所述第二激光传感器发射的激光能够到达的距离、所述第一落点坐标为(Xa,Ya),且所述允许越障高度为h,所述方法还包括:
若所述Ya大于目标高度且不大于所述h,则控制所述机器人从正常模式切换至低速模式,所述目标高度大于0且小于所述h,所述低速模式的速度小于所述正常模式的速度;
若所述Ya不小于所述目标高度的负数且不大于所述目标高度,则控制所述机器人以所述正常模式运动;
若所述Ya不小于所述h的负数且小于所述目标高度的负数,则控制所述机器人从正常模式切换至低速模式。
具体地,所述第一激光传感器为线激光传感器,所述第二激光传感器为激光测距传感器。
本公开的实施例中,由于机器人安装的第一激光传感器和第二激光传感器的倾角不同,且该第一激光传感器在该机器人的安装高度和该第二激光传感器在该机器人的安装高度也不同,因此,基于第一激光传感器和第二激光传感器所得到的第一落点坐标和第二落点坐标为两个不同位置对应的坐标。而由于两个不同位置的坐标能够反映这两个位置的高度差,因此,再结合预设的允许越障高度能够快速、准确地识别出这两个不同位置所在的区域对应的障碍物类型,比如识别该障碍物类型是否为机器人能够翻越的台阶。
为达到上述目的,本公开另一方面实施例还提出了一种清洁设备的控制装置,包括:检测设备,用于对所述清洁设备的运行环境进行检测,获取环境特征参数,其中,所述环境特征参数包括房间特征参数和障碍物参数中的至少一个;控制设备,用于根据所述房间特征参数和所述障碍物参数中的至少一个,控制所述清洁设备进行清洁。
可选地,所述清洁设备为清洁机器人,其中,所述控制设备包括:
第一获取模块,被设置为获取运行指令后,以第一速率在目标区域启动清洁功能;
第一检测模块,被设置为若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;
第一选取模块,被设置为基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;
第一运行模块,被设置为基于所述目标障碍躲避路线,运行所述清洁机器人。
通过应用本公开的技术方案,可以在清洁机器人检测到前方存在障碍物时,根据是否能对该障碍物的物体类别进行识别来对应选取不同的障碍躲避路线。从而实现依据不同类型的物体轮廓进行不同绕障方法的目的。进而提高清洁机器人的避障能力,实现免碰撞的功能,也就避免了由于机器人感知范围有限所导致的无法完全避开障碍物的问题。
可选地,所述清洁设备为机器人,所述机器人安装有第一激光传感器和第二激光传感 器,所述第一激光传感器在所述机器人的倾角和所述第二激光传感器在所述机器人的倾角不同,且所述第一激光传感器在所述机器人的安装高度和所述第二激光传感器在所述机器人的安装高度也不同,所述控制设备包括:
第一距离获取模块,用于通过所述第一激光传感器获取第一传感距离,所述第一传感距离为所述第一激光传感器发射的激光的光斑落点与所述第一激光传感器的距离;
第二距离获取模块,用于通过所述第二激光传感器获取第二传感距离,所述第二传感距离为所述第二激光传感器发射的激光的光斑落点与所述第二激光传感器的距离;
第一落点坐标确定模块,用于根据所述第一激光传感器在所述机器人的安装高度、倾角以及所述第一传感距离,确定第一落点坐标,所述第一落点坐标为所述第一激光传感器发射的激光的光斑落点的坐标;
第二落点坐标确定模块,用于根据所述第二激光传感器在所述机器人的安装高度、倾角以及所述第二传感距离,确定第二落点坐标,所述第二落点坐标为所述第二激光传感器发射的激光的光斑落点的坐标;
障碍物类型识别模块,用于根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,所述目标区域为所述第一落点坐标和所述第二落点坐标所在的区域;
运动控制模块,用于根据所述障碍物类型控制所述机器人的运动。
本公开的实施例中,由于机器人安装的第一激光传感器和第二激光传感器的倾角不同,且该第一激光传感器在该机器人的安装高度和该第二激光传感器在该机器人的安装高度也不同,因此,基于第一激光传感器和第二激光传感器所得到的第一落点坐标和第二落点坐标为两个不同位置对应的坐标。而由于两个不同位置的坐标能够反映这两个位置的高度差,因此,再结合预设的允许越障高度能够快速、准确地识别出这两个不同位置所在的区域对应的障碍物类型,比如识别该障碍物类型是否为机器人能够翻越的台阶。
可选地,所述房间特征参数包括房间的地面特征信息,其中,所述控制设备还用于,根据所述地面特征信息确定控制信息,并根据所述控制信息控制所述清洁设备工作。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的地面特征信息,该地面特征信息能够表示出房间内的地面铺设情况。进一步地,根据该房间内的地面特征信息确定对应的控制信息,从而使得清洁设备按照该控制信息进行清洁工作。
通过上述方式,清洁设备能够基于房间的地面情况,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
可选地,所述房间特征参数包括房间的房间特征信息,所述障碍物参数包括所述房间 内的物体的位置,其中,所述控制设备还用于,
根据所述房间特征信息确定清洁参数;
控制所述清洁设备避开所述物体的位置,并按照所述清洁参数工作。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的房间特征信息以及房间内的固定物体的具***置,该物体的位置特征信息能够表示出房间类型、房间内的地面铺设等情况。
进一步地,根据该房间内的房间特征信息确定对应的清洁参数,根据固定物体的具***置确定清洁设备的路线,使得清洁设备能够避开固定物体的具***置移动,且按照该控制信息进行清洁工作。
通过上述方式,清洁设备能够基于房间的具体情况,自适应设置合理的清洁方式,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
根据本公开的再一个方面,提出了一种清洁设备,包括:存储器,用于存储程序或指令;处理器,处理器执行程序或指令时实现如上述任一技术方案的清洁设备的控制方法的步骤。
本公开提供的清洁设备,程序或指令被处理器执行时实现如上述任一技术方案的清洁设备的控制方法的步骤,因此该清洁设备包括上述任一技术方案的清洁设备的控制方法的全部有益效果。
根据本公开的又一个方面,提出了一种可读存储介质,其上存储有程序或指令,程序或指令被处理器执行时实现如上述任一技术方案的清洁设备的控制方法的步骤。
本公开提供的可读存储介质,程序或指令被处理器执行时实现如上述任一技术方案的清洁设备的控制方法的步骤,因此该可读存储介质包括上述任一技术方案的清洁设备的控制方法的全部有益效果。
本公开的附加方面和优点将在下面的描述中部分给出,部分将从下面的描述中变得明显,或通过本公开的实践了解到。
本公开的上述和/或附加的方面和优点从结合下面附图对实施例的描述中将变得明显和容易理解,其中:
图1是根据本公开一个实施例的可移动设备的控制方法的流程示意图之一;
图2是根据本公开一个实施例的可移动设备的控制方法的流程示意图之二;
图3是根据本公开一个实施例的可移动设备的控制方法的流程示意图之三;
图4是根据本公开一个实施例的可移动设备的控制方法的流程示意图之四;
图5是根据本公开一个实施例的可移动设备的控制方法的流程示意图之五;
图6是根据本公开一个实施例的可移动设备的控制方法的流程示意图之六;
图7是根据本公开一个实施例的可移动设备的控制方法的流程示意图之七;
图8是根据本公开一个实施例的房间内地面铺设的示意图之一;
图9是根据本公开一个实施例的房间内地面铺设的示意图之二;
图10是根据本公开一个实施例的清洁设备的控制方法的流程示意图之八;
图11是根据本公开一个实施例的清洁设备的控制方法的流程示意图之九;
图12是根据本公开一个实施例的清洁设备的控制方法的流程示意图之十;
图13是根据本公开一个实施例的清洁设备的控制方法的流程示意图之十一;
图14是根据本公开一个实施例的清洁设备的控制方法的流程示意图之十二;
图15是根据本公开一个实施例的清洁设备的控制方法的流程示意图之十三;
图16是根据本公开一个实施例的房间布局的示意图之一;
图17是根据本公开一个实施例的房间布局的示意图之二;
图18是根据本公开一个实施例的清洁机器人的运行***架构示意图;
图19是根据本公开一个实施例的清洁机器人的障碍躲避方法的示意图;
图20是根据本公开一个实施例的清洁机器人的生成障碍躲避路线的示意图;
图21是根据本公开一个实施例的清洁机器人的障碍躲避的场景显示图;
图22是根据本公开一个实施例的生成语义地图的流程架构图;
图23是根据本公开一个实施例的清洁机器人运行的流程示意图;
图24是根据本公开一个实施例的第一种机器人控制方法的流程图;
图25是根据本公开一个实施例的一种激光传感器的倾角、发射点、光斑落点等信息的示意图;
图26是根据本公开一个实施例的第二种机器人控制方法的流程图;
图27是根据本公开一个实施例的一种下坡道的示意图;
图28是根据本公开一个实施例的一种大台阶的示意图;
图29是根据本公开一个实施例的一种高障碍物的示意图;
图30是根据本公开一个实施例的一种上坡道的示意图;
图31是根据本公开一个实施例的清洁机器人的障碍躲避装置的方框示意图;
图32是根据本公开一个实施例的一种电子设备的逻辑结构框图;
图33是根据本公开一个实施例的机器人控制装置的结构示例图;
图34是根据本公开一个实施例的机器人的结构示意图;
图35是根据本公开一个实施例的清洁设备的控制装置的示意框图;
图36是根据本公开一个实施例的清洁设备的示意框图;
图37是根据本公开另一个实施例的清洁设备的示意框图;
图38是根据本公开一个实施例的可移动设备的控制装置的示意框图;
图39是根据本公开一个实施例的可移动设备的示意框图;
图40是根据本公开另一个实施例的可移动设备的示意框图。
下面详细描述本公开的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,仅用于解释本公开,而不能理解为对本公开的限制。
下面参考附图来描述本公开实施例提出的清洁设备的控制方法、清洁设备的控制装置、清洁设备和可读存储介质。
概括地,在本公开的一些实施例中,提出了一种清洁设备的控制方法,该方法包括:对清洁设备的运行环境进行检测,获取环境特征参数,其中,环境特征参数包括房间特征参数和/或障碍物参数。根据房间特征参数和/或障碍物参数,可以控制所述清洁设备进行清洁。示例性地,所述清洁设备为清洁机器人。所述清洁机器人根据所述房间特征参数和/或障碍物参数,确定其清洁路线、清洁参数等,并基于确定的清洁路线、清洁参数等,进行房间自动清洁。所述清洁机器人可以包括,例如,扫地机、洗地机、擦窗机器人、桌面机器人、园林机器人等。需要说明的是,本说明书所披露的方法并不限于清洁设备,也可以用于其他工业、商用、家居机器人,例如,餐厅服务机器人。
该清洁设备的控制方法,能够基于房间特征参数和障碍物参数中的至少一个对清洁设备进行控制,实现不同场景下采用的不同的清扫控制方式,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性,充分满足用户的需求。
可选地,通过具体的实施例及其应用场景对本公开实施例提供的清洁设备的控制方法进行详细地说明。
其中,房间特征参数可以包括房间的地面特征信息;可选地,根据房间特征参数,控制所述清洁设备进行清洁,包括:根据地面特征信息确定控制信息,并根据控制信息控制清洁设备工作。
具体地,在本公开的一些实施例中,图1示出了清洁设备的控制方法的流程示意图之一。其中,清洁设备可以是可移动设备,如图1所示,该方法包括:
步骤102,获取房间的地面特征信息;
步骤104,基于该地面特征信息,确定对可移动设备的控制信息;
步骤106,控制可移动设备,按照该控制信息工作。
在该技术方案中,可移动设备可以为扫地机器人、拖地机器人、扫拖一体机等清洁设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,可移动设备上安装有摄像头、红外线传感器等设备,能够采集房间内的地面特征信息,该地面特征信息能够表示出房间内的地面铺设情况。进一步地,根据该房间内的地面特征信息确定对应的控制信息,从而使得可移动设备按照该控制信息进行清洁工作。
需要说明的是,地面特征信息包括地面铺设材质、地面铺设方向、地面尺寸、插座位置以及房间分界特征中的至少一项。
通过上述方式,可移动设备能够基于房间的地面情况,实现更加智能化、定制化的 清洁,提高房间清洁的高效性、准确性。
此外,如果无法识别出房间的地面特征信息,可以执行默认的清扫策略,以保证清洁的顺利进行。
可选地,根据本公开的一些实施例,在地面特征信息包括地面铺设材质的情况下,图2示出了可移动设备的控制方法的流程示意图之二。其中,如图2所示,该方法包括:
步骤202,获取房间的地面铺设材质;
步骤204,基于该地面铺设材质,确定对可移动设备的第一控制信息;
步骤206,控制可移动设备,按照第一控制信息进行工作。
在该技术方案中,地面特征信息可以包括地面铺设的材质,例如材质包括木质(例如地板)、资质、石质(例如地砖)等。
可移动设备的控制信息包括第一控制信息,第一控制信息可以为出水量、清洁次数、风机吸力、移动速度中的至少一项。
具体地,基于房间的地面铺设的材质,对应确定可移动设备工作的出水量、风机吸力、移动速度,以及确定可移动设备对该房间的清洁次数。
示例性地,可以根据地面铺设材质的不同,在直行、转弯、脱困、绕障等动作中,自适应的调整移动参数(例如可移动设备的电机转速反馈等),从而使得可移动设备的运动更加平稳顺畅。
另外,对于风机吸力,不同的材质可以对应于不同的风机吸力,具体材质的风机吸力可根据用户的设置参数进行确定。例如,用户可以根据需求,设置地面铺设材质为瓷质或石质时对应的风机吸力大,从而使得瓷质或石质地面上的水渍最大程度被吸干,避免出现用户被滑倒的问题;用户也可以根据需求,设置地面铺设材质为木质时对应的风机吸力大,因为通常卧室是地板,从而使得卧室地面上的水渍最大程度被吸干,避免出现水渍过多导致被褥发潮的问题。
通过上述方式,可移动设备能够基于房间内地面铺设的材质,对该房间实现更加个性化、智能化的清洁。
可选地,在本公开的一些实施例中,地面铺设材质为木质情况下的出水量小于地面铺设材质为瓷质或石质情况下的出水量。
在该技术方案中,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以减少可移动设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以相对增加可移动设备进行清洁时的出水量,从而提高对地砖的清洁程度,保证清洁效果。
在本公开的另一些实施例中,地面铺设材质为木质情况下的清洁次数大于地面铺设材质为瓷质或石质情况下的清洁次数。
在该技术方案中,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺 设的是地板,则可以减少可移动设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板,同时增加清洁次数,以保证清洁效果。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以相对增加可移动设备进行清洁时的出水量,从而提高对地砖的清洁程度,保证清洁效果,同时相对减少清洁次数,以减少可移动设备的电能的浪费。
可选地,在本公开的一些实施例中,在地面特征信息包括地面铺设方向的情况下,图3示出了可移动设备的控制方法的流程示意图之三。其中,如图3所示,该方法包括:
步骤302,获取房间的地面铺设方向;
步骤304,基于该地面铺设方向,确定对可移动设备的第二控制信息;
步骤306,控制可移动设备,按照第二控制信息进行工作。
其中,第二控制信息为可移动设备的清洁方向与地面铺设方向一致。
在该技术方案中,地面特征信息可以包括地面铺设的方向,也即,地面铺设的地板或地砖的纹理。
可移动设备的控制信息包括第二控制信息,第二控制信息可以为可移动设备的清洁方向的控制信息。
具体地,基于房间的地面铺设的方向,对应确定可移动设备的清洁方向,使得可移动设备的清洁方向与地面铺设的方向相同,也就是说可移动设备的清洁方向平行于地面铺设的方向。如图8所示,房间内地面铺设方向为横向,则控制可移动设备的清洁方向平行于地面铺设的方向。
通过上述方式,可移动设备能够平行于房间内地面铺设的方向进行清洁,从而减少地板或地砖的缝隙内残留的灰尘、水渍等,以及使得可移动设备在地板或地砖上的清洁痕迹不混乱,使得清洁痕迹更加美观,提高清洁效果。
可选地,在本公开的一些实施例中,在地面特征信息包括地面尺寸的情况下,图4示出了可移动设备的控制方法的流程示意图之四。其中,如图4所示,该方法包括:
步骤402,获取房间的地面尺寸;
步骤404,基于该地面尺寸,确定该房间的类型;
步骤406,根据该房间的类型,确定对可移动设备的第三控制信息;
步骤408,控制可移动设备,按照第三控制信息进行工作。
在该技术方案中,地面特征信息可以包括地面尺寸,也即,房间的尺寸,可移动设备的控制信息包括第三控制信息。
具体地,基于房间的地面尺寸,判定房间的大小,从而判定房间的类型,进而根据房间的类型对应确定可移动设备的第三控制信息。
通过上述方式,能够按照房间的类型,自适应地控制可移动设备的清洁,从而提高房间清洁的高效性、准确性。
在上述任一技术方案中,房间的类型包括卧室、客厅、厨房和卫生间中的至少一项。
在该技术方案中,房间可以包括卧室、客厅、厨房或卫生间,可移动设备在不同类 型的房间的清洁方式可以不同。
在上述任一技术方案中,第三控制信息包括房间清洁顺序、清洁剂量和消毒剂量中的至少一项。
在该技术方案中,可移动设备的第三控制信息可以为房间清洁顺序、清洁剂量、消毒剂量中的至少一项。例如,在确定房间为卧室时,可以对该房间进行优先清洁,在确定房间为客厅时,可以在清洁完卧室后对客厅进行清洁;在确定房间为厨房或卫生间时,可移动设备可以喷洒清洁剂、消毒剂等。
通过上述方式,实现更加智能化、定制化的清洁。
需要说明的是,结合地面尺寸对可移动设备进行控制,可以在根据地面铺设材质和/或地面铺设方向对可移动设备进行控制的步骤之后。
示例性地,由于卧室和客厅通常铺设的是地板,厨房和卫生间通常铺设的是地砖。在识别到房间内地面铺设的是地板后,可以初步确定该房间为卧室或客厅,并确定出第一控制信息和/或第二控制信息。进一步地,再结合房间尺寸,具体推测出该房间是卧室还是客厅,以便确定房间清洁顺序,例如,基于当前房间的房间尺寸较小,则确定当前房间是卧室,而预先设置了卧室的清洁优先级大于客厅的清洁优先级,则先清扫当前的卧室。
或者,可以同时结合地面尺寸、地面铺设材质和/或地面铺设方向对可移动设备进行控制。
示例性地,如果识别到房间内铺设的是地板,并且结合房间尺寸特征,推测该房间是卧室或客厅,则对该房间进行优先清洁,然后再去厨房、卫生间等房间进行清洁,符合用户需求。如果识别到房间内铺设的是地砖,并且房间尺寸相对较小,可以判定是厨房或卫生间,则对该房间最后清洁,且在清扫时可以喷洒清洁剂、消毒剂等。
可选地,在本公开的一些实施例中,在地面特征信息包括插座位置的情况下,图5示出了可移动设备的控制方法的流程示意图之五。其中,如图5所示,该方法包括:
步骤502,获取房间的插座位置;
步骤504,基于该插座位置,确定对可移动设备的第四控制信息;
步骤506,控制可移动设备,按照第四控制信息进行工作。
在该技术方案中,地面特征信息可以包括插座位置,也即,地面上安装的插座的位置,可移动设备的控制信息包括第四控制信息,该第四控制信息用于控制可移动设备的移动路线。
具体地,基于房间地面上的插座位置,控制可移动设备的移动路线,以避免可移动设备清洁插座位置出现漏电风险,提高清洁过程中的安全性。
在上述技术方案中,第四控制信息为控制可移动设备的清洁范围在插座位置的预设范围之外。
在该技术方案中,如图9所示,如果识别到房间内安装在地面的插座902,可移动设备可以在清洁时与该插座902保持一定的安全距离,也即,在距离该插座902的预设 范围外进行清洁,例如在与该插座902距离10厘米或20厘米外的范围进行清洁。
通过上述方式,避免可移动设备清洁插座位置出现漏电风险,提高清洁过程中的安全性。
需要说明的是,结合插座位置对可移动设备进行控制,可以在根据地面铺设材质和/或地面铺设方向对可移动设备进行控制的步骤之前或之后。或者,可以同时结合插座位置、地面铺设材质和/或地面铺设方向对可移动设备进行控制。
可选地,在本公开的一些实施例中,在地面特征信息包括房间的房间分界特征的情况下,基于地面特征信息,确定对可移动设备的控制信息的步骤,具体包括:判断房间分界特征的高度是否未超过预设阈值,当房间分界特征的高度未超过预设阈值时,确定与房间分界特征对应的控制信息。其中,所述房间分界特征是指分隔不同房间的特征线(如分界线),例如过门条、门槛石、移门轨道等。
在该技术方案中,地面特征信息可以包括房间的房间分界特征,例如过门条、门槛石、移门轨道等。
当识别到房间分界特征的高度没有超过预设阈值时,表明房间分界特征高度较低,则可以控制可移动设备对该位置进行清洁;当识别到房间分界特征的高度超过预设阈值时,表明房间分界特征高度较高,则可以使可移动设备不对该位置进行清洁,避免可移动设备在房间分界特征处被卡住。
可选地,在本公开的一些实施例中,以可移动设备为拖地机器人为例,拖地机器人通常以单线激光雷达或摄像头作为主传感器来感知环境、建立地图,智能化程度主要体现在导航运动精度的提高、孤立物体的识别与免碰撞、分割区域的不遗漏清扫等。而作为拖地机器人的核心功能——清洁,大多在地毯增压、清洁次数、弓形间距、消毒杀菌等特性中体现。
而在一个地区内,不同家庭的户型格局、房间分布、地面材质等宏观特征,是具有高度相似性的。而具体到个体的家庭内,场景、障碍物等又是千差万别的。因此,深度清洁功能,需要从清洁任务和材质的共性入手。基于大量的房间地面纹路图像数据和装修案例,利用深度学习技术,可以训练出高准确率的地面材质与铺设纹路识别模型,可以指导拖地机器人在清扫任务中更准确的分割房间地图、按照房间顺序清扫、调整清扫方向、调整拖地出水量、调节风机吸力等,实现更智能化、定制化的深度清洁。
图6示出了本公开实施例的可移动设备的控制方法的流程示意图之六。其中,如图6所示,该方法包括:
步骤602,获取房间的地面铺设材质、地面铺设方向、地面尺寸、插座位置以及房间分界特征中的至少一项;
步骤604,基于地面铺设材质、地面铺设方向、地面尺寸、插座位置以及房间分界特征中的至少一项,确定拖地机器人的对应的控制信息;
步骤606,控制拖地机器人,按照该控制信息进行工作。
该方法利用摄像头、红外传感器等采集地面特征信息,经过特征提取、图像识别、 大数据训练学习等,获得地面材质的分类结果(通常是二分类,如地板或地砖),以及地面材质的铺设方式(通常是二分类,如横铺或纵铺),添加到地图语义中,来辅助拖地机器人执行更加高效、准确、友好的清洁策略,实现智能深度清洁。
通过上述方式,拖地机器人能够基于房间的地面情况,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
可选地,在本公开的一些实施例中,图7示出了可移动设备的控制方法的流程示意图之七。其中,如图7所示,该方法包括:
步骤720,识别房间的房间分界特征;
步骤740,在可移动设备经过房间分界特征进入房间的情况下,获取该房间的地面特征信息;
步骤760,基于该地面特征信息,确定对可移动设备的控制信息;
步骤780,控制可移动设备,按照该控制信息工作。
在该技术方案中,房间分界特征为房间分割的重要依据,可以包括过门条、门槛石、移门轨道等。
在识别到可移动设备经过房间分界特征进入房间时,采集该房间的地面特征信息,进而按照与地面特征信息对应的控制信息,控制可移动设备进行房间清洁。
通过上述方式,根据房间分界特征,可精准地确定可移动设备是否进入房间,从而在进入房间后采集地面特征信息,实现地面特征信息的及时、准确地采集。
在一些实施例中,针对地面材质类型、铺设纹路方向、过门条、门槛石、移门轨道等特征,服务器端训练深度学习模型,可移动设备完成识别并保存结果。如果识别到过门条、门槛石、移门轨道等房间分界特征,在地图中标记,作为地图房间分割的重要依据,可使APP地图更加真实、准确,可移动设备清洁路线更加清晰、易于理解,避免在移门轨道处卡住,提高清洁效率。
此外,在本公开的一些实施例中,在获取房间的地面特征信息的步骤之前,还包括:确定地面特征信息与控制信息之间的对应关系。
在该技术方案中,建立地面特征信息和控制信息之间的对应关系。
例如,地面铺设材质与出水量、清洁次数、风机吸力、移动速度中至少一项的对应关系;地面铺设方向与可移动设备的清洁方向的对应关系;房间的类型与房间的类型中至少一项的对应关系;插座位置与可移动设备的清洁范围的对应关系等。
通过上述方式,实现更加智能化、定制化的清洁。
可选地,在本公开的一些实施例中,房间特征参数包括房间的房间特征信息,障碍物参数包括房间内的物体的位置,其中,根据房间特征参数和障碍物参数控制所述清洁设备进行清洁的步骤,包括:根据房间特征信息确定清洁参数;控制清洁设备避开物体的位置,并按照清洁参数工作。
具体地,图10示出了本公开实施例的清洁设备的控制方法的流程示意图之八。其中,如图10所示,该方法包括:
步骤820,确定清洁设备待清洁房间的房间特征信息以及待清洁房间内的物体的位置;
步骤840,基于待清洁房间的房间特征信息,确定清洁参数;
步骤860,根据该清洁参数,控制清洁设备工作,并且在工作的过程中避开待清洁房间内的物体的位置。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的房间特征信息以及房间内的固定物体的具***置,该物体的位置特征信息能够表示出房间类型、房间内的地面铺设等情况。其中,物体可以为家具、电器等,例如,桌椅、沙发、地毯、空调等。
进一步地,根据该房间内的房间特征信息确定对应的清洁参数,根据固定物体的具***置确定清洁设备的路线,使得清洁设备能够避开固定物体的具***置移动,且按照该控制信息进行清洁工作。
需要说明的是,房间特征信息包括房间类型和地面铺设材质中的至少一项。
通过上述方式,清洁设备能够基于房间的具体情况,自适应设置合理的清洁方式,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
可选地,在本公开的一些实施例中,在房间特征信息包括房间类型的情况下,图11示出了清洁设备的控制方法的流程示意图之九。其中,如图11所示,该方法包括:
步骤902,确定清洁设备待清洁房间的房间类型以及待清洁房间内的物体的位置;
步骤904,基于待清洁房间的房间类型,确定第一清洁参数;
步骤906,根据该第一清洁参数,控制清洁设备工作,并且在工作的过程中避开待清洁房间内的物体的位置。
其中,第一清洁参数包括清洁优先级、清洁程度中的至少一项。
在该技术方案中,房间特征信息可以包括房间的类型,进而能够根据房间的类型对应确定清洁设备的第一清洁参数。
其中,清洁设备的清洁参数包括第一清洁参数,房间可以包括卧室、客厅、厨房或卫生间,清洁设备在不同类型的房间的清洁优先级、清洁程度等第一清洁参数可以不同。
通过上述方式,能够按照房间的类型,自适应地控制清洁设备的清洁方式,从而提高房间清洁的高效性、准确性。
在该实施例中,在房间为卧室或客厅的情况下,清洁优先级大于或等于第一阈值,基于房间为卫生间或厨房,清洁优先级小于第一阈值,也即卧室或客厅的清洁优先级大于卫生间或厨房的清洁优先级。
示例性地,如图16所示,房间可以包括卧室702、客厅704、厨房706和卫生间708,在确定房间为卧室702或客厅704时,可以对该房间进行优先清洁;在确定房间为卫生间708或厨房706时,可以在清洁完卧室702或客厅704后对卫生间708或厨房706 进行清洁。
通过上述方式,实现更加智能化、定制化的清洁。
在该实施例中,由于卫生间或厨房的脏污程度相比于卧室或客厅的脏污程度要大,所以对卫生间或厨房的清洁程度也要大,设置卫生间或厨房的清洁程度大于卧室或客厅的清洁程度。也就是说,在房间类型为卫生间或厨房的情况下,清洁程度大于或等于第二阈值,在房间类型为卧室或客厅的情况下,清洁程度小于第二阈值。
具体地,清洁程度可以表现为清洁次数、对地面的擦拭力度、是否喷洒清洁剂、消毒剂等。例如,在确定房间为厨房或卫生间时,清洁设备可以喷洒清洁剂、消毒剂等,以提高清洁程度。
通过上述方式,实现更加智能化、定制化的清洁。
可选地,在本公开的一些实施例中,在房间特征信息包括地面铺设材质的情况下,图12示出了清洁设备的控制方法的流程示意图之十。其中,如图12所示,该方法包括:
步骤1002,确定清洁设备待清洁房间的地面铺设材质以及待清洁房间内的物体的位置;
步骤1004,基于待清洁房间的地面铺设材质,确定第二清洁参数;
步骤1006,根据该第二清洁参数,控制清洁设备工作,并且在工作的过程中避开待清洁房间内的物体的位置。
其中,第二清洁参数包括出水量、清洁次数、风机吸力中至少一项。
在该技术方案中,房间特征信息可以包括地面铺设的材质,例如材质包括木质(例如地板)、瓷质、石质(例如地砖)、混凝土等。
清洁设备的清洁参数包括第二清洁参数,第二清洁参数可以为出水量、清洁次数、风机吸力中的至少一项。
具体地,基于房间的地面铺设的材质,对应确定清洁设备工作的出水量、清洁次数、风机吸力等。
通过上述方式,清洁设备能够基于房间内地面铺设的材质,对该房间实现更加个性化、智能化的清洁。
在该实施例中,地面铺设材质为木质时清洁设备的出水量小于地面铺设材质为瓷质或石质时清洁设备的出水量,地面铺设材质为瓷质或石质时清洁设备的出水量小于地面铺设材质为混凝土时清洁设备的出水量。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的出水量小于或等于第三阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的出水量大于第三阈值且小于或等于第四阈值;在地面铺设材质为混凝土的情况下,清洁设备的出水量大于第四阈值,其中第四阈值大于第三阈值。
具体地,如图16所示,房间可以包括卧室702、客厅704、厨房706、卫生间708和阳台710,其中卧室702、客厅704内地面铺设的材质为木质,厨房706、卫生间708内地面铺设的材质为瓷质或石质,阳台710内地面铺设的材质为混凝土。
如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以相对减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以控制清洁设备进行清洁时的出水量适中,从而提高对地砖的清洁程度,保证清洁效果。
如果识别到房间内地面铺设的材质为混凝土,也就是说,房间内铺设的是水泥,则可以相对增加清洁设备进行清洁时的出水量,从而提高对水泥地面的清洁程度,保证清洁效果。
在该实施例中,地面铺设材质为木质时清洁设备的清洁次数大于地面铺设材质为瓷质或石质时清洁设备的清洁次数,地面铺设材质为瓷质或石质时清洁设备的清洁次数大于地面铺设材质为混凝土时清洁设备的清洁次数。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的清洁次数大于或等于第五阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的清洁次数小于第五阈值且大于或等于第六阈值;在地面铺设材质为混凝土的情况下,清洁设备的清洁次数小于第六阈值,其中第六阈值小于第五阈值。
具体地,如果识别到房间内地面铺设的材质为木质,也就是说,房间内铺设的是地板,则可以相对减少清洁设备进行清洁时的出水量,从而减少水渍对地板的伤害、保护地板,同时增加清洁设备的清洁次数,以保证清洁效果。
如果识别到房间内地面铺设的材质为瓷质或石质,也就是说,房间内铺设的是地砖,则可以控制清洁设备进行清洁时的出水量、清洁次数适中,从而提高对地砖的清洁程度,保证清洁效果。
如果识别到房间内地面铺设的材质为混凝土,也就是说,房间内铺设的是水泥,则可以相对增加清洁设备进行清洁时的出水量,从而提高对水泥地面的清洁程度,保证清洁效果,同时相对减少清洁次数,以减少清洁设备的电能的浪费。
可选地,在本公开的一些实施例中,图13示出了清洁设备的控制方法的流程示意图之十一。其中,如图13所示,该方法包括:
步骤1102,确定清洁设备待清洁房间的房间特征信息以及待清洁房间内的物体的位置;
步骤1104,基于待清洁房间的房间特征信息,确定清洁参数;
步骤1106,确定物体与房间的地面之间的相对位置信息;
步骤1108,根据该清洁参数,控制清洁设备工作,并且在工作的过程中根据相对位置信息避开待清洁房间内的物体的位置。
在该技术方案中,确定房间内物体与地面之间的相对位置信息,该相对位置信息能够表示出物体与地面之间是否有空隙,以及在有空隙的情况下空隙的尺寸。进而根据是否有空隙或者有空隙时空隙的尺寸,控制清洁设备是否避开物体运动。
示例性地,如图17所示,房间地面局部区域铺设有地毯802,地毯802与地面之间 相当于没有空隙,则控制清洁设备避开该地毯进行清洁。对于房间内的桌椅等物体进行选择性的避开清洁,如图17所示,房间内放置有餐桌804,餐桌804的桌面与地面之间具有较大空隙,则控制清洁设备避开餐桌804的桌腿,而从餐桌804的桌面下穿过,也即并不是完全避开餐桌804。房间内还放置有沙发806,沙发806与地面之间具有较小空隙,则控制清洁设备避开沙发806,避免清洁设备进入小空隙中被困。
通过上述方式,实现对清洁设备避开物体的方式进行控制,提高对房间的清洁效果。
可选地,在本公开的一些实施例中,图14示出了清洁设备的控制方法的流程示意图之十二。其中,如图14所示,该方法包括:
步骤1202,采集待清洁房间的第一图像,根据第一图像识别待清洁房间;
步骤1204,根据待清洁房间与房间特征信息、物体的位置之间的预设对应关系,确定待清洁房间的房间特征信息以及待清洁房间内的物体的位置;
步骤1206,基于待清洁房间的房间特征信息,确定清洁参数;
步骤1208,根据该清洁参数,控制清洁设备工作,并且在工作的过程中避开待清洁房间内的物体的位置。
在该技术方案中,通过采集房间的第一图像,基于该第一图像明确清洁设备所进入的具体房间,进而根据房间与房间特征信息以及物体的位置之间的预设对应关系,确定与该房间所对应的房间特征信息、物体的位置。
也就是说,预先存储有房间与房间特征信息、物体的位置之间的预设对应关系,在根据第一图像明确了具体房间后,即可得到该房间所对应的房间特征信息和物体的位置。
通过上述方式,在明确了所进入的房间后即可根据预设对应关系,获得预先存储的房间特征信息和物体的位置,无需通过图像来识别房间特征信息和物体的位置,提高了房间特征信息和物体的位置获取的准确性和及时性。
可选地,在本公开的一些实施例中,在确定待清洁房间的房间特征信息以及待清洁房间内的物体的位置的步骤之前,还包括:控制清洁设备在房间内移动,并在移动过程中采集该房间的第二图像;识别该第二图像,获取该房间的房间特征信息和物体的位置,并建立该房间与房间特征信息、物体的位置之间的预设对应关系。
在该技术方案中,控制清洁设备在房间内移动,并在移动过程中获取该房间的第二图像,实现定位建图。进一步地,在第二图像中识别出该房间的房间特征信息以及物体的位置,并将房间名称与房间特征信息以及物体的位置对应存储,实现建立预设对应关系。
在清洁设备进行下次清扫时,根据预设对应关系,确定房间特征信息以及物体的位置,从而实现分类制定清洁方案,提高清洁设备的智能性。
可选地,在本公开的一些实施例中,以清洁设备为拖地机器人为例,图15示出了清洁设备的控制方法的流程示意图之十三。其中,如图15所示,该方法包括:
步骤1302,拖地机器人通过摄像头、雷达等设备,对房间进行首次定位建图;
步骤1304,在定位建图过程中,通过摄像头、超声波等设备,标记一些该房间的地面材质、房间类型、家具位置等环境属性;
步骤1306,在拖地机器人下次清扫时,根据标记的环境属性,分类制定拖地方案;
步骤1308,控制拖地机器人根据分类制定的拖地方案,完成清洁。
例如,对于木制地板拖地机器人的出水量要低,对于瓷砖地面拖地机器人的出水量适中,对于水泥地面拖地机器人的出水量要大。对于卧室、客厅优先拖扫,正常次数即可,对于厨房、卫生间最后拖扫,次数增加等。对于地毯需要进行避开,对于桌椅则进行选择性地避开。
通过上述方式,一方面,使得拖地机器人的清扫更具有针对性,使得拖地机品类决策规划方法,与扫地机呈现差异化;另一方面,使得拖地机器人的清扫更具有智能性,能够根据环境属性分类,自适应制定拖地方案,智能化程度较高。
可选地,在本公开的另外一些实施例中,清洁设备可以为清洁机器人,其中,根据障碍物参数控制所述清洁设备进行清洁的步骤,包括:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。
可见,在本公开的一些实施例中,根据障碍物参数对清洁设备进行控制,可以是对清洁机器人进行障碍躲避控制。
图18示出了可以应用本公开实施例的清洁机器人的障碍躲避方法或清洁机器人的障碍躲避的示例性***架构100的示意图。
如图18所示,***架构100可以包括清洁机器人110、120、130中的一种或多种,网络140和服务器150。网络140用以在清洁机器人110、120、130和服务器150之间提供通信链路的介质。网络140可以包括各种连接类型,例如有线、无线通信链路或者光纤电缆等等。
应该理解,图18中的清洁机器人、网络和服务器的数目仅仅是示意性的。根据实现需要,可以具有任意数目的清洁机器人、网络和服务器。比如服务器150可以是多个服务器组成的服务器集群等。
用户可以使用清洁机器人110、120、130通过网络140与服务器150交互,以接收或发送消息,采集图像等。清洁机器人110、120、130可以包括具有显示屏,摄像采集装置的各种电子设备。
本公开中的清洁机器人110、120、130可以为提供各种服务的清洁机器人。例如用户通过清洁机器人130(也可以是清洁机器人110或120)实现:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物 体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。
在此需要说明的是,本公开实施例所提供的清洁机器人的障碍躲避方法可以由清洁机器人110、120、130中的一个或多个,和/或,服务器150执行,相应地,本公开实施例所提供的清洁机器人的障碍躲避装置一般设置于对应清洁机器人中,和/或,服务器150中,但本公开不限于此。
图19示意性地示出了根据本公开实施方式的一种清洁机器人的障碍躲避方法的流程示意图。如图19所示,该方法应用于清洁机器人,包括:
S1901,获取运行指令后,以第一速率在目标区域启动清洁功能。
其中,清洁机器人是智能家用电器的一种,能凭借一定的人工智能,自动在区域内完成地板清理工作。一般采用刷扫和真空方式,将地面杂物先吸纳进入自身的垃圾收纳盒,从而完成地面清理的功能。
需要说明的是,本公开中的运行指令可以是由用户生成的,也可以为根据预设规则生成的。例如每隔一段时间即可指示机器人进行用于清扫室内的运行指令等等。
另外,需要说明的是,本公开不对目标区域进行限定。例如可以对应于卧室,也可以对应于厨房,还可以对应于办公区域等等。还有,本公开也不对第一速率进行限定,例如可以为一般运行速率,也可以为快速运行速率。
S1902,若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果。
相关技术中,传统的清洁机器人在进行室内清扫时,通常需要避开障碍物以免出现机器人不断碰壁的情况。相关技术中,清洁机器人通常为基于激光雷达,超声波等传感器感知的方式来进行障碍物识别。进一步的,例如对于激光雷达,超声波等传感器的扫地机障碍物检测方案经常存在不能准确躲避障碍物的情况。
针对上述问题,本公开提出一种在检测到前方存在障碍物的情况下,可以首先对该障碍物进行一个用于确定其物体类别的识别事件。以由此确定该障碍物的物体类别,可以理解的,后续即可以根据该物体类别的识别结果,选择指示清洁机器人实施不同的障碍躲避路线。
一种方式中,本公开在得到用于确定所述目标障碍物对应的物体类别的识别结果的过程中,可以通过于设置在清洁机器人上的摄像装置来对前方的障碍物进行拍摄图像,以由此得到目标障碍物图像;并在后续利用预设的图像检测分类模型,提取该目标障碍物图像的对应于大小特征、色彩特征以及轮廓特征的至少一种物体特征,以使后续根据该物体特征,确定目标障碍物对应的物体类别。
其中,本公开不对图像检测分类模型做具体限定。例如可以为卷积神经网络(Convolutional Neural Networks,CNN)。卷积神经网络是一类包含卷积计算且具有深度结构的前馈神经网络(Feedforward Neural Networks),是深度学***移不变分类。得益于CNN(卷积神经网络)对图像的强大特征表征能力,其在图像分类、目标检测、语义分割等领域都取得了令人瞩目的效果。
进一步的,本公开可以使用图像检测分类模型来检测清洁机器人携带的摄像装置所采集到的多张目标障碍物图像中的特征信息,进而对该特征信息进行特征识别,确定目标障碍物图像中对应的物体类别。具体的,需要将该待识别图像输入至预设的卷积神经网络模型中,并将卷积神经网络模型最后一层全连接层(FC,fully connected layer)的输出作为对该待识别图像对应的特征数据的识别结果。
其中,本公开不对目标障碍物对应的物体类别进行具体限定,例如可以为动物粪便,袜子,鞋,电线,凳子,床,垃圾桶,桌子,马桶等等。
S1903,基于识别结果,选取对应的目标障碍躲避路线,目标障碍躲避路线对应于更改当前前进方向以及不更改当前前进方向的其中一种。
可以理解的,基于该识别结果来说,可以分为两种情况,即能够识别出目标障碍物对应的物体类别的第一识别结果,以及不能够识别出目标障碍物对应的物体类别的第二识别结果。针对上述两种情况,本公开实施方式中可以采取不同的目标障碍躲避方案。具体为:
第一种情况:
若清洁机器人确定能够识别目标障碍物对应的物体类别,则可以选取用于指示清洁机器人在不更改当前前进方向的情况下,绕开目标障碍物的路线的第一障碍躲避路线,也即机器人在原有前进路线的情况下,选择一条可以绕开障碍物的路线。
进一步的,本公开实施例可以首先依据障碍物物体的类别与其对应的轮廓形状以及大小参数并基于预存的障碍物数据集合,计算得到所述目标障碍物的外切图像,并基于外切图像以及purePuresuit算法可以分成以下几类:
外切圆:如图20所示,如果多边形接近圆且障碍物是凳子腿,垃圾桶,桌子腿,马桶障碍物,则求外切圆,然后以直线距离为5CM确定轨迹点。
外切矩形:如果多边形接近矩形且障碍物为袜子,鞋,电线,桌子。则求外切矩形,然后以直线距离为5CM确定轨迹点。
包络体:如果多边形不是圆,且障碍物为动物粪便则求包络体,然后以直线距离为5CM确定轨迹点。
可以理解的,在生成轨迹点之后,即可以根据该轨迹点计算生成第一障碍躲避路线。
第二种情况:
若确定不能够识别目标障碍物对应的物体类别,则可以选取用于指示清洁机器人以绕开目标障碍物的情况下,以其他前进方向运行的路线的第二障碍躲避路线,也即机器人选择一条可以完全躲避障碍物的路线(例如原先前进方向为正北,第二障碍躲避路线的前进方向为正西)。
进一步的,由于在家居复杂的环境下,有许多未能识别物体分类的障碍物,本公开 可以采用实时躲避的方法。具体来说,当机器人行进过程中,需要首先触发减速,以实现机器人进行减速,并当检测到距离障碍物一定距离后,机器人从虚拟碰撞接口获得角度信息,机器参考返回的角度,按以下算法计算出机器与障碍物平行的角度,机器转到与障碍物平行,然后,进行转弧,沿着障碍物进行行走。当虚拟碰撞又发生时,机器再按计算的角度旋转,然后转弧,如此循环直到机器旋转360度或回到原点,机器退出实时避障功能。
机器旋转角度的设计:机器正前方为0度,往顺时针方向为:0~-180度,逆时针为:0~180度。一种方式中,第二障碍躲避路线可以如下:
a)当障碍物角度(Obs_Angle):-60度<Obs_Angle<-30度时:机器旋转角度(Rotate_Angle)Rotate_Angle=-Obs_Angle;
b)当障碍物角度(Obs_Angle):-30度<Obs_Angle<30度时:机器旋转角度(Rotate_Angle)Rotate_Angle=90-Obs_Angle;
c)当障碍物角度(Obs_Angle):30度<Obs_Angle<60度时:机器旋转角度(Rotate_Angle)Rotate_Angle=180-Obs_Angle。
S1904,基于目标障碍躲避路线,运行清洁机器人。
进一步的,本公开在确定目标障碍躲避路线后,即可以驱动机器人在该目标障碍躲避路线下运行,直至清洁机器人将目标区域清扫完毕。
本公开的实施例中,在获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果;基于识别结果,选取对应的目标障碍躲避路线,目标障碍躲避路线对应于更改当前前进方向以及不更改当前前进方向的其中一种;基于目标障碍躲避路线,运行清洁机器人。通过应用本公开的技术方案,可以在机器人检测到前方存在障碍物时,根据是否能对该障碍物的物体类别进行识别来对应选取不同的障碍躲避路线。从而实现依据不同类型的物体轮廓进行不同绕障方法的目的。进而提高清洁机器人的避障能力,实现免碰撞的功能,也就避免了由于机器人感知范围有限所导致的无法完全避开障碍物的问题。
可选的,在本公开一种可能的实施方式中,步骤S1903(基于识别结果,选取对应的目标障碍躲避路线),可包括:
若确定能够识别目标障碍物对应的物体类别,选取第一障碍躲避路线,第一障碍躲避路线为用于指示清洁机器人在不更改当前前进方向的情况下,绕开目标障碍物的路线;或,
若确定不能够识别目标障碍物对应的物体类别,选取第二障碍躲避路线,第二障碍躲避路线为用于指示清洁机器人以绕开目标障碍物的情况下,以其他前进方向运行的路线。
可选的一种方式中,本公开在确定能够识别目标障碍物对应的物体类别,选取第一障碍躲避路线,包括:
确定目标障碍物对应的物体类别,并基于预存的障碍物数据集合,得到物体类别对应的轮廓参数以及尺寸参数;
基于轮廓参数以及尺寸参数,计算得到目标障碍物的外切图像;
基于外切图像以及purePuresuit算法,计算生成第一障碍躲避路线。
可选的一种方式中,本公开在计算生成所述第一障碍躲避路线之后,还包括:
选取第一障碍躲避路线并运行清洁机器人;
当检测到清洁机器人绕开目标障碍物且朝向至当前前进方向前进时,确定清洁机器人的障碍躲避完成。
一种方式中,清洁机器人若能够确定障碍物对应的物体类别,那么则可以根据预存的障碍物数据集合,确定该障碍物的轮廓形状以及大小。并根据该轮廓形状以及大小,生成一条躲避该障碍物的路线。
可以理解的,例如对于垃圾桶障碍物来说,其对应的轮廓形状和大小参数大都为半径0.5米内的圆柱形。因此针对该半径0.5米内的圆柱形来说,本公开实施例中即可以基于外切图像以及purePuresuit算法,得到一个可以绕开该半径0.5米内的圆柱形的轨迹点,并在后续根据该轨迹点生成一个第一障碍躲避路线。从而保证机器人在原有前进路线(例如原有前进路线为正北,第一障碍躲避路线在绕开该垃圾桶后,前进方向仍然为正北)的情况下,选择一条可以绕开障碍物的路线。
另一种方式中,例如对于方桌障碍物来说,其对应的轮廓形状和大小参数大都为长宽在1.5米内的矩形。因此针对该长宽在1.5米内的矩形来说,本公开实施例中即可以基于外切图像以及purePuresuit算法,得到一个可以绕开该长宽在1.5米内的矩形的轨迹点,并在后续根据该轨迹点生成一个第一障碍躲避路线。从而保证机器人在原有前进路线(例如原有前进路线为正西,第一障碍躲避路线在绕开该方桌后,前进方向仍然为正西)的情况下,选择一条可以绕开障碍物的路线。
可选的一种方式中,本公开在确定不能够识别目标障碍物对应的物体类别,选取第二障碍躲避路线,包括:
若确定不能够识别目标障碍物对应的物体类别,获取目标障碍物与清洁机器人的平行角度差值;
基于平行角度差值,确定用于旋转清洁机器人前进方向的旋转角度,并基于旋转角度,计算生成第二障碍躲避路线。
可选的一种方式中,本公开在计算生成所述第二障碍躲避路线之后,还包括:
选取第二障碍躲避路线并运行清洁机器人;
当检测到清洁机器人朝向其他前进方向前进并且距离目标障碍物超过第二距离时,确定清洁机器人的障碍躲避完成。
进一步的,例如如图21所示,当前方的障碍物组合过多或过大或预先没有注入相关参数的情况下,将会导致清洁机器人无法识别该障碍物对应的物体类别。那么在此情况下,为了保证清洁机器人的正常运行,本公开实施例中即可以选择在确定不能够识别目标障碍物对应的物体类别后,获取目标障碍物与清洁机器人的平行角度差值,并基于该平行角度差值,确定用于旋转清洁机器人前进方向的旋转角度,并基于旋转角度,得到第二障碍躲避路线。
可以理解的,该旋转角度即可以确保清洁机器人更改其前进方向(例如旋转角度可以为190度,则可以使得请求人进行掉头),从而保证机器人完全绕开目标障碍物,以其他前进方向的路线继续运行。
一种方式中,旋转角度可以由目标障碍物与清洁机器人的平行角度差值来确定,即二者的平行角度差值越大,则可以生成旋转清洁机器人前进方向的旋转角度越小的指令。同样的,当二者的平行角度差值越小,则可以生成旋转清洁机器人前进方向的旋转角度越大的指令。
一种方式中,可以根据当障碍物角度(Obs_Angle):-60度<Obs_Angle<-30度时:机器旋转角度(Rotate_Angle)Rotate_Angle=-Obs_Angle。或当障碍物角度(Obs_Angle):-30度<Obs_Angle<30度时:机器旋转角度(Rotate_Angle)Rotate_Angle=90-Obs_Angle;c)。又或当障碍物角度(Obs_Angle):30度<Obs_Angle<60度时:机器旋转角度(Rotate_Angle)Rotate_Angle=180-Obs_Angle来运行。
可选的,在本公开一种可能的实施方式中,在S1901(以第一速率在目标区域启动清洁功能)之后,还包括:
若检测到当前前进方向的第二距离处存在有目标障碍物时,将第一速率切换为第二速率,其中,第二速率低于所述第一速率,第二距离大于第一距离;
检测目标障碍物是否位于当前前进方向的第一距离处。
例如以第一速为30cm/s来说,当清洁机器人以速度30cm/s运行时,当靠近障碍物时,清洁机器人即会减速到15cm/s(即第二速率)。可以理解的,上述减速方式可以避免机器人的用力碰撞障碍物。且更有利于机器人刹停,动作更流畅。还可以有利于利用摄像装置采集到更准确的图像数据(后续用于确定障碍物的物体类别)。
一种方式中,减速接口的设计如下,当障碍物落在减速距离阈值(Slowdown Distance),机身宽(Robot withd)构成的区域(即第二距离)内,则可以触发减速。
可选的,在本公开一种可能的实施方式中,在S1901(以第一速率在目标区域启动清洁功能)之前,还包括:
获取目标区域的初始栅格地图,机器姿态信息,样本障碍物信息,其述样本障碍物信息包括样本障碍物参数以及样本障碍物对应的物体类别;
通过Bresenham算法,将各个样本障碍物投影到初始栅格地图上,生成语义地图;
当获取到运行指令后,基于语义地图在目标区域启动清洁功能。
进一步的,图22示出了语义地图的生成流程图,本公开中提出的清洁机器人的障碍躲避方法的清洁机器人包含LDS_SLAM,Recognition,Perception3D,Semantic_Map,Planer五个节点,其中:
LDS_SLAM节点负责构建定位与建图。LDS_SLAM节点从IMU,Odometry,Lidar传感器获取数据,创建地图以及输出机器的位姿。解决“我在那里?”的问题。
其中,Recognition节点通过AI技术实现物体识别。Recognition节点主要实现动物粪便,袜子,鞋,电线,凳子,床,垃圾桶,桌子,马桶等九类物体的识别。解决“它是什么?”的问题。
其中,Perception3D节点负责输出障碍物的深度信息。解决“它在哪里?”的问题。
其中,Semntic_map节点从Recognition与Perception3D中获到障碍物的空间位姿以及障碍物的类型,组合LDS_SLAM的Pose,通过Bresenham算法,将障碍物投影到占用栅格地图上,并给对应栅格打上物体类型的信息,生成语义地图。
其中,Planner节点主要依据语义地图的信息来实现智能避障。
进一步的,本公开中的语义地图生成是planner的其中一个功能。具体来说,需要首先启动一个线程来接受全局的栅格地图,机器位姿,障碍物bounding box,障碍物类别以及障碍的3D点云信息。接着对满足条件的点云(如高度h,满足groud<h<robot_hight范围内的点)与Recognition返回障碍物的bounding box进行计算,得到每个点的类别,然后通过Bresennham算法,计算每个点落到栅格的位置及概率,并在对应的栅格上标记上障碍物的类别。至此就获得带有语义信息的占用栅格地图(即语义地图),并将其部署到清洁机器人上,以实现提供避障算法使用。
可选的,在本公开一种可能的实施方式中,在S1902(基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果)中,可以包括以下步骤:
利用摄像装置,获取目标障碍物图像;
利用图像检测分类模型,提取目标障碍物图像的物体特征,物体特征包括大小特征、色彩特征以及轮廓特征的至少一种;
确定存在物体特征,确定目标障碍物对应的物体类别的识别结果。
可选的,本公开在利用所述摄像装置,获取目标障碍物图像之前,还包括:
获取至少两个的样本图像,其中,样本图像中包括至少一个障碍物体特征;
基于障碍物的物体类别,对各个样本图像标注对应的类别标识;
利用标注有类别标识的样本图像,以及样本图像中包括的障碍物体特征,对预设的图像语义分割模型进行训练,得到满足预设条件的图像检测分类模型,图像检测分类模型用于确定目标障碍物对应的物体类别。
进一步的,本公开在利用预设的图像检测分类模型识别目标障碍物图像之前,首先需要训练得到该图像检测分类模型。具体而言,需要首先获取一定数量的,包括多个障碍物体特征的样本图像。并利用该多个样本图像对基础的空白图像语义分割模型进行训练,进而得到满足预设条件的第一图像检测分类模型。
需要说明的是,本公开需要障碍物的物体类别,对各个样本图像标注对应的类别标识。例如当样本图像中存在有垃圾桶的障碍物时,需要对其样本图像标注有障碍物为垃圾桶的类别标识。又或当样本图像中出现床架的障碍物时,需要对其样本图像标注有障碍物为床架的类别标识。
本公开可以通过预设的图像语义分割模型,来识别样本图像所包括的至少一个障碍物体特征(例如可以为大小特征,轮廓特征,色彩特征等等)。更进一步而言,图像语义分割模型还可以对样本图像中的各个障碍物体特征进行分类,并且将属于同一类别的样本特征分为同一类型的物体,这样,样本图像进行语义分割之后所得到的多个样本特征可以为多个不同类型所组成的样本特征。
需要说明的是,神经网络图像分类模型对样本图像进行语义分割处理时,对样本图像中的像素点分类越准确,则识别样本图像中的标记对象的准确率越高。其中需要说明的是,预设条件可以是自定义设定的。
例如,可以设定预设条件为:对像素点的分类准确率达到70%以上,那么,多个样本图像对图像检测分类模型进行反复训练,在神经网络图像分类模型对像素点的分类准确率达到70%以上时,则此时该图像检测分类模型可以应用在本公开实施例中,对清洁机器人中摄像装置拍摄的多张障碍物图像进行图像特征识别。
更进一步的,如图23所示,为本公开提出的清洁机器人的运行方法的整体流程图,其中包括:
本公开中,在获取运行指令后,以第一速率在目标区域启动清洁功能,并在当检测到当前前进方向第一距离处存在有目标障碍物,基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果。
进一步的,还需要基于识别结果,选取对应的目标障碍躲避路线,目标障碍躲避路线对应于更改当前前进方向以及不更述当前前进方向的其中一种;最后,则需要基于目标障碍躲避路线,运行清洁机器人。
通过应用本公开的技术方案,可以在机器人检测到前方存在障碍物时,根据是否能对该障碍物的物体类别进行识别来对应选取不同的障碍躲避路线。从而实现依据不同类型的物体轮廓进行不同绕障方法的目的。进而提高清洁机器人的避障能力,实现免碰撞的功能,也就避免了由于机器人感知范围有限所导致的无法完全避开障碍物的问题。
可选地,在本公开的一些实施例中,清洁设备可以为机器人,机器人安装有第一激光传感器和第二激光传感器,第一激光传感器在机器人上的倾角和第二激光传感器在机器人上的倾角不同,且第一激光传感器在机器人上的安装高度和第二激光传感器在机器人上的安装高度也不同,其中,根据障碍物参数控制所述清洁设备进行清洁的步骤,可包括:通过所述第一激光传感器获取第一传感距离,所述第一传感距离为所述第一激光传感器发射的激光的光斑落点与所述第一激光传感器的距离;通过所述第二激光传感器获取第二传感距离,所述第二传感距离为所述第二激光传感器发射的激光的光斑落点与所述第二激光传感器的距离;根据所述第一激光传感器在所述机器人的安装高度、倾角以及所述第一传感距离,确定第一落点坐标,所述第一落点坐标为所述第一激光传感器发射的激光的光斑落点的坐标;根据所述第二激光传感器在所述机器人的安装高度、倾角以及所述第二传感距离,确定第二落点坐标,所述第二落点坐标为所述第二激光传感器发射的激光的光斑落点的坐标;根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,所述目标区域为所述第一落点坐标和所述第二落点坐标所在的区域;根据所述障碍物类型控制所述机器人的运动。
也就是说,在本实施例中,根据障碍物参数对清洁设备进行控制的步骤,可以是通过识别目标区域对应的障碍物类型,来控制机器人的运动。
由于使用悬崖传感器识别机器人前方的障碍物类型时,难以快速识别出台阶这一类型,以及难以准确区分出当前的障碍物类型是台阶还是下坡道,因此,本公开实施例提供了一种机器人控制方法。
在该机器人控制方法中,将两个激光传感器安装在机器人前进方向的那侧,这样,这 两个激光传感器能够向机器人的前方发射激光。根据这两个激光传感器在机器人上的安装高度、倾角以及检测到的距离,机器人能够计算出不同激光传感器对应的光斑落点的坐标,进而能够根据得到的两个光斑落点的坐标以及预设的允许越障高度,识别出两个光斑落点所在区域对应的障碍物类型。
图24示出了本公开实施例提供的第一种机器人控制方法的流程图,该机器人控制方法应用于安装有第一激光传感器和第二激光传感器的机器人。其中,第一激光传感器在该机器人本体上的倾角与该第二激光传感器在该机器人本体上的倾角不相等,且该第一激光传感器在该机器人本体上的安装高度和该第二激光传感器在该机器人本体上的安装高度也不相等,详述如下:
步骤S11,通过该第一激光传感器获取第一传感距离,该第一传感距离为该第一激光传感器发射的激光的光斑落点与该第一激光传感器的距离。
具体地,第一激光传感器发射激光,当激光被遮挡时,将在遮挡物上形成光斑落点。由于光的传播速度是固定的,因此,根据光的传播速度以及其传播时间能够计算出第一激光传感器与对应的光斑落点的距离。
需要指出的是,本公开实施例的第一传感距离可由第一激光传感器计算得到,并由该第一激光传感器发送给机器人,也可由机器人计算得到。
本公开实施例的机器人可为用于清洁的清洁机器人等清洁设备。
步骤S12,通过该第二激光传感器获取第二传感距离,该第二传感距离为该第二激光传感器发射的激光的光斑落点与该第二激光传感器的距离。
其中,第二传感距离的计算方式与第一传感距离的计算方式相同,此处不再赘述。
步骤S13,根据该第一激光传感器在该机器人的安装高度、倾角以及该第一传感距离,确定第一落点坐标,该第一落点坐标为该第一激光传感器发射的激光的光斑落点的坐标。
其中,第一激光传感器在机器人的安装高度,是指该第一激光传感器安装在机器人上的安装位置到地面的距离。
其中,第一激光传感器在机器人的倾角,是指该第一激光传感器的激光发射口与机器人的夹角中小于90°的夹角。
如图25所示,第一激光传感器的激光发射点为A1,该A1的光斑落点为A2,该第一激光传感器的倾角为α,第一激光传感器在该机器人的安装高度为H1,第一传感距离为A1A2所对应的边的长度。第二激光传感器的激光发射点为B1,该B1的光斑落点为B2,该第二激光传感器的倾角为β,第一激光传感器在该机器人的安装高度为H2,第一传感距离为B1B2。
根据图25中的直角三角形的斜边(如A1A2)的长度以及倾角(如α)能够确定直角三角形中水平方向的直角边的长度,进而确定A2中的横坐标。另外,根据直角三角形的斜边的长度以及倾角能够确定直角三角形中垂直方向的直角边的长度,将该直角边的长度与安装高度H1结合,能够计算出A2的纵坐标。
步骤S14,根据该第二激光传感器在该机器人的安装高度、倾角以及该第二传感距离,确定第二落点坐标,该第二落点坐标为该第二激光传感器发射的激光的光斑落点的坐标。
其中,第二落点坐标的计算方式与第一落点坐标的计算方式相同,此处不再赘述。
步骤S15,根据该第一落点坐标、该第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,该目标区域为该第一落点坐标和该第二落点坐标所在的区域。
其中,预设的允许越障高度是指机器人能够翻越的最高的障碍高度。
其中,上述的障碍物类型包括:大台阶。
本实施例中,由于两个相近位置在垂直方向的信息和水平方向的信息能够反应这两个相近位置所在的区域的障碍物类型,比如,在两个相近位置所在的区域的障碍物类型为大台阶这一类型时,这两个相近位置在垂直方向的值的绝对值通常远大于允许越障高度,因此,通过上述方式,能够准确识别对应区域的障碍物类型。
步骤S16,根据该障碍物类型控制该机器人的运动。
本实施例中,机器人根据不同的障碍物类型控制其自身执行对应的运动,以提高控制的精度。
本公开实施例中,由于第一激光传感器安装在机器人上的倾角与第二激光传感器安装在机器人上的倾角不相等,且该第一激光传感器在该机器人的安装高度也与该第二激光传感器在该机器人的安装高度不相等,因此,基于第一激光传感器所得到的第一落点坐标和基于第二激光传感器所得到的第二落点坐标为两个不同位置对应的坐标。而由于两个不同位置的坐标能够反映这两个位置的高度差,因此,再结合预设的允许越障高度能够快速、准确地识别出这两个不同位置所在的区域对应的障碍物类型,比如识别该障碍物类型是否为机器人能够翻越的台阶。例如,能够在机器人到达台阶之前即可识别出前方是否有台阶,而无需在到达台阶时才能识别前方是否有台阶。
图26示出了本公开实施例提供的第二种机器人控制方法的流程图,本实施例中,步骤S31、步骤S32、步骤S33、步骤S34分别与上述实施例的步骤S11、步骤S12、步骤S13、步骤S14相同,步骤S37和步骤S38分别与上述实施例的步骤S15、步骤S16相同,此处不再赘述。
在本实施例中,第一激光传感器在机器人上的安装高度大于该第二激光传感器在机器 人上的安装高度,且从该第一激光传感器发射出来的激光所能够到达的距离大于从该第二激光传感器中发射出来的激光所能够到达的距离,详述如下:
步骤S31,通过该第一激光传感器获取第一传感距离,该第一传感距离为该第一激光传感器发射的激光的光斑落点与该第一激光传感器的距离。
步骤S32,通过该第二激光传感器获取第二传感距离,该第二传感距离为该第二激光传感器发射的激光的光斑落点与该第二激光传感器的距离。
步骤S33,根据该第一激光传感器在该机器人的安装高度、倾角以及该第一传感距离,确定第一落点坐标,该第一落点坐标为该第一激光传感器发射的激光的光斑落点的坐标。
步骤S34,根据该第二激光传感器在该机器人的安装高度、倾角以及该第二传感距离,确定第二落点坐标,该第二落点坐标为该第二激光传感器发射的激光的光斑落点的坐标。
步骤S35,将Ya的绝对值与该允许越障高度比较。
本公开实施例中,假设第一落点坐标的横坐标为Xa,纵坐标为Ya。
其中,Ya是第一落点坐标的纵坐标,其值可能大于0,也可能小于0。
其中,允许越障高度为大于0的值。
步骤S36,若该Ya的绝对值大于该允许越障高度,则控制该机器人暂停运动。
本实施例中,若Ya大于0,则在Ya大于该允许越障高度时,表明机器人的前方可能存在较高的障碍物,此时,先控制机器人停止运动,能够给机器人后续的控制留出足够的时间。
同理,若Ya小于0,则在Ya小于允许越障高度的负数时,表明机器人的前方可能存在较低的台阶(如向下的台阶),此时,先控制机器人停止运动,能够给机器人后续的控制留出足够的时间。
步骤S37,根据该第一落点坐标、该第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,该目标区域为该第一落点坐标和该第二落点坐标所在的区域。
步骤S38,根据该障碍物类型控制该机器人的运动。
本公开实施例中,由于Ya为从第一激光传感器中发射出来的激光所对应的光斑落点,而第一激光传感器在机器人上的安装位置高于第二激光传感器在机器人上的安装高度,且从该第一激光传感器中发射出来的激光所能够到达的距离大于从该第二激光传感器中发射出来的激光所能够到达的距离,因此,与第二落点坐标相比,第一落点坐标的Ya能够反映机器人前方更远的位置的障碍物信息,进而有利于机器人更早地做出反映。同时,由于在Ya的绝对值大于允许越障高度时,表明机器人的前方可能存在向上的台阶或障碍物,或者,可能存在向下的台阶,因此,先控制机器人停止运动,并在判断出障碍物类型后再继续控 制机器人运动,能够使得机器人在无法通过障碍物时具有足够的时间改变其运动,进而能够有效降低机器人发生意外的概率。
在一些实施例中,第一激光传感器可以为线激光传感器,第二激光传感器可以为激光测距传感器。
由于在识别障碍物类型时首先选择第一激光传感器对应的第一落点坐标进行处理,而线激光传感器对应的扫描区域大于激光测距传感器对应的扫描区域,因此,将第一激光传感器设置为线激光传感器,将第二激光传感器设置为激光测距传感器,不仅能够提高扫描到障碍物的概率,也能降低成本。
在一些实施例中,假设第二落点坐标的横坐标为Xb,纵坐标为Yb,允许越障高度为h,该步骤S37包括:
A1、若该Ya小于-h,且该Yb不大于该Ya,则判定该目标区域对应的障碍物类型为大台阶。
本实施例中,在Ya<-h(即Ya的绝对值大于h)时,若判断出Yb≤Ya,则判定机器人前方为大台阶。此时,机器人可后退然后转向以更换路径。
A2、若该Ya小于该-h,且该Yb小于0但大于该Ya,则判定该目标区域对应的障碍物类型为下坡道。
本实施例中,如图27所示,在Ya<-h(即Ya的绝对值大于h)时,若判断出Ya<Yb<0,则判定机器人前方为下坡道。
A3、若该Ya小于该-h,且该Yb不小于0,则判定该目标区域对应的障碍物类型为大台阶。
如图28所示,在Ya<-h(即Ya的绝对值大于h)时,若判断出Yb≥0,则判定机器人前方为大台阶。此时,机器人可后退然后转向以更换路径。
根据图27和图28中第一落点坐标和第二落点坐标的关系可知,本公开实施例所采用的判断方法能够准确判断出障碍物类型是否为大台阶,或者,是否为下坡道。
在一些实施例中,该障碍物类型为下坡道,该步骤S38具体包括:
B1、确定该下坡道对应的角度。
其中,下坡道对应的角度可根据第一落点坐标和第二落点坐标计算得到。
B2、根据该下坡道对应的角度和预设的允许爬坡度数,控制该机器人的运动。
具体地,在下坡道对应的角度不大于预设的允许爬坡度数时,机器人继续前行并下坡。而在下坡道对应的角度大于预设的允许爬坡度数时,机器人后退然后转向,以更换路径。
本公开实施例中,由于机器人在设计后,通常不能翻越角度较大的坡道(如不能超出 预设的允许爬坡度数),因此,当判断出机器人前方存在下坡道时,需要结合下坡道对应的角度以及预设的允许爬坡度数,选择对应的运动,以免在下坡道对应的角度过大时,机器人仍前行所导致的倾翻。
在一些实施例中,假设第二落点坐标为(Xb,Yb),预设的允许越障高度为h,该步骤S37包括:
C1、若该Ya大于该h,且该Xb不小于该Xa,则判定该目标区域对应的障碍物类型为高障碍物。
如图29所示,若Ya>h(即Ya的绝对值大于h)时,又判断出Xb≥Xa,则认为机器人的前方存在高障碍物,此时,机器人可后退然后转向,以更换路径。
C2、若该Ya大于该h,且该Xb小于该Xa,则判定该目标区域对应的障碍物类型为上坡道。
如图30所示,若Ya>h(即Ya的绝对值大于h)时,又判断出Xb<Xa,则认为机器人的前方是一个上坡道。
根据图29和图30中第一落点坐标和第二落点坐标的关系可知,本公开实施例所采用的判断方法能够准确判断出障碍物类型是否为高障碍物,或者,是否为上坡道。
在一些实施例中,该障碍物类型为上坡道,该该步骤S38具体包括:
D1、确定该上坡道对应的角度。
具体地,根据第一落点坐标和第二落点坐标能够计算出上坡道对应的角度。
D2、根据该上坡道对应的角度和预设的允许爬坡度数,控制该机器人的运动。
具体地,在上坡道对应的角度不大于预设的允许爬坡度数时,机器人继续前行并上坡。而在上坡道对应的角度大于预设的允许爬坡度数时,机器人后退然后转向,以更换路径。
本公开实施例中,由于在判断出机器人前方存在上坡道时,结合上坡道对应的角度以及预设的允许爬坡度数,选择对应的运动,因此,能够避免在上坡道对应的角度过大时,机器人仍前行所导致的倾翻。
在一些实施例中,该第一激光传感器的安装高度大于该第二激光传感器的安装高度、该第一激光传感器发射的激光能够到达的距离大于该第二激光传感器发射的激光能够到达的距离、该第一落点坐标为(Xa,Ya),且该允许越障高度为h,该方法还包括:
E1、若该Ya大于目标高度且不大于该h,则控制该机器人从正常模式切换至低速模式,该目标高度大于0且小于该h,该低速模式的速度小于该正常模式的速度。
在一些实施例中,目标高度可设置为h/2。
由于当判断出Ya具有一定的高度时,表明机器人前方可能存在其不能翻越的区域,而 低速模式中的速度较低,即其对应的惯性也越小,因此,将机器人从正常模式先切换至低速模式,能够通过提前预判来降低机器人发生意外的概率,从而提高对机器人的控制的准确度。
E2、若该Ya不小于该目标高度的负数且不大于该目标高度,则控制该机器人以该正常模式运动。
由于目标高度在0和h之间,因此,当判断出Ya不小于该目标高度的负数且不大于该目标高度时,表明机器人前方的区域为机器人能够翻越的区域的概率较高,此时,只需要控制机器人以正常模式运动即可,以保证机器人能够顺利执行任务。
E3、若该Ya不小于该h的负数且小于该目标高度的负数,则控制该机器人从正常模式切换至低速模式。
由于当判断出Ya小于目标高度的负数时,表明第一落点坐标所在的位置的地势较低,也即,表明机器人前方存在其不能翻越的区域的概率较高,而低速模式中的速度较低,即其对应的惯性也越小,因此,将机器人从正常模式先切换至低速模式,能够通过提前预判来降低机器人发生意外的概率,从而提高对机器人的控制的准确度。
应理解,上述实施例中各步骤的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本公开实施例的实施过程构成任何限定。
在本公开的一些实施例中,还提出了一种清洁设备的控制装置,该控制装置包括:检测设备和控制设备,检测设备用于对所述清洁设备的运行环境进行检测,获取环境特征参数,其中,所述环境特征参数包括房间特征参数和障碍物参数中的至少一个;控制设备用于根据所述房间特征参数和所述障碍物参数中的至少一个,控制所述清洁设备进行清洁。
进一步地,在本公开的一些实施例中,清洁设备可以为清洁机器人,如图31所示,控制设备可以是清洁机器人的障碍躲避装置2000,其包括第一获取模块2001、第一检测模块2002、第一选取模块2003、第一运行模块2004,其中,
第一获取模块2001,被设置为获取运行指令后,以第一速率在目标区域启动清洁功能;
第一检测模块2002,被设置为若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;
第一选取模块2003,被设置为基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;
第一运行模块2004,被设置为基于所述目标障碍躲避路线,运行所述清洁机器人。
本公开中,在获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在清洁机器人上的摄像装置,得到用于确定目标障碍物对应的物体类别的识别结果;基于识别结果,选取对应的目标障碍躲避路线,目标障碍躲避路线对应于更改当前前进方向以及不更改当前前进方向的其中一种;基于目标障碍躲避路线,运行清洁机器人。通过应用本公开的技术方案,可以在机器人检测到前方存在障碍物时,根据是否能对该障碍物的物体类别进行识别来对应选取不同的障碍躲避路线。从而实现依据不同类型的物体轮廓进行不同绕障方法的目的。进而提高清洁机器人的避障能力,实现免碰撞的功能,也就避免了由于机器人感知范围有限所导致的无法完全避开障碍物的问题。
在本公开的另一种实施方式中,第一选取模块2003,还被配置为:
若确定能够识别所述目标障碍物对应的物体类别,选取第一障碍躲避路线,所述第一障碍躲避路线为用于指示所述清洁机器人在不更改当前前进方向的情况下,绕开所述目标障碍物的路线;或,
若确定不能够识别所述目标障碍物对应的物体类别,选取第二障碍躲避路线,所述第二障碍躲避路线为用于指示所述清洁机器人以绕开所述目标障碍物的情况下,以其他前进方向运行的路线。
在本公开的另一种实施方式中,第一选取模块2003,还被配置为:
确定所述目标障碍物对应的物体类别,并基于预存的障碍物数据集合,得到所述物体类别对应的轮廓参数以及尺寸参数;
基于所述轮廓参数以及尺寸参数,计算得到所述目标障碍物的外切图像;
基于所述外切图像以及purePuresuit算法,计算生成所述第一障碍躲避路线。
在本公开的另一种实施方式中,第一选取模块2003,被配置为:
选取所述第一障碍躲避路线并运行所述清洁机器人;
当检测到所述清洁机器人绕开所述目标障碍物且朝向至所述当前前进方向前进时,确定所述清洁机器人的障碍躲避完成。
在本公开的另一种实施方式中,第一选取模块2003,被配置为:
若确定不能够识别所述目标障碍物对应的物体类别,获取所述目标障碍物与所述清洁机器人的平行角度差值;
基于所述平行角度差值,确定用于旋转所述清洁机器人前进方向的旋转角度,并基于所述旋转角度,计算生成所述第二障碍躲避路线。
可选地,在基于本公开上述方法的另一个实施例中,在所述计算生成所述第二障碍躲 避路线之后,还包括:
选取所述第二障碍躲避路线并运行所述清洁机器人;
当检测到所述清洁机器人朝向所述其他前进方向前进并且距离所述目标障碍物超过第二距离时,确定所述清洁机器人的障碍躲避完成。
在本公开的另一种实施方式中,第一检测模块2002,被配置为:
若检测到当前前进方向的第二距离处存在有所述目标障碍物时,将所述第一速率切换为第二速率,其中,所述第二速率低于所述第一速率,所述第二距离大于所述第一距离;
检测所述目标障碍物是否位于所述当前前进方向的第一距离处。
在本公开的另一种实施方式中,第一获取模块2001,被配置为:
获取所述目标区域的初始栅格地图,机器姿态信息,样本障碍物信息,其中所述样本障碍物信息包括样本障碍物的参数以及所述样本障碍物对应的物体类别;
通过Bresenham算法,将各个样本障碍物投影到所述初始栅格地图上,生成语义地图;
所述获取运行指令后,以第一速率在目标区域启动清洁功能,包括:
当获取到所述运行指令后,基于所述语义地图以所述第一速率在所述目标区域启动清洁功能。
在本公开的另一种实施方式中,第一检测模块2002,被配置为:
利用所述摄像装置,获取所述目标障碍物图像;
利用图像检测分类模型,提取所述目标障碍物图像的物体特征,所述物体特征包括大小特征、色彩特征以及轮廓特征的至少一种;
确定存在所述物体特征,确定所述目标障碍物对应的物体类别的识别结果。
可选地,在基于本公开上述方法的另一个实施例中,在所述利用所述摄像装置,获取所述目标障碍物图像之前,还包括:
获取至少两个的样本图像,其中,所述样本图像中包括至少一个障碍物体特征;
基于所述障碍物的物体类别,对各个所述样本图像标注对应的类别标识;
利用所述标注有类别标识的样本图像,以及所述样本图像中包括的障碍物体特征,对预设的图像语义分割模型进行训练,得到满足预设条件的所述图像检测分类模型,所述图像检测分类模型用于确定所述目标障碍物对应的物体类别。
图32是根据一示例性实施例示出的一种电子设备的逻辑结构框图。例如,电子设备3000可以是移动电话,计算机,数字广播终端,消息收发设备,游戏控制台,平板设备,医疗设备,健身设备,个人数字助理等。
参照图32,电子设备3000可以包括以下一个或多个组件:处理器3001和存储器3002。
处理器3001可以包括一个或多个处理核心,比如4核心处理器、8核心处理器等。处理器3001可以采用DSP(Digital Signal Processing,数字信号处理)、FPGA(Field-Programmable Gate Array,现场可编程门阵列)、PLA(Programmable Logic Array,可编程逻辑阵列)中的至少一种硬件形式来实现。处理器3001也可以包括主处理器和协处理器,主处理器是用于对在唤醒状态下的数据进行处理的处理器,也称CPU(Central Processing Unit,中央处理器);协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中,处理器3001可以在集成有GPU(Graphics Processing Unit,图像处理器),GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中,处理器3001还可以包括AI(Artificial Intelligence,人工智能)处理器,该AI处理器用于处理有关机器学习的计算操作。
存储器3002可以包括一个或多个计算机可读存储介质,该计算机可读存储介质可以是非暂态的。存储器3002还可包括高速随机存取存储器,以及非易失性存储器,比如一个或多个磁盘存储设备、闪存存储设备。在一些实施例中,存储器3002中的非暂态的计算机可读存储介质用于存储至少一个指令,该至少一个指令用于被处理器3001所执行以实现本公开中方法实施例提供的障碍躲避方法。
在一些实施例中,电子设备3000还可选包括有:***设备接口3003和至少一个***设备。处理器3001、存储器3002和***设备接口3003之间可以通过总线或信号线相连。各个***设备可以通过总线、信号线或电路板与***设备接口3003相连。具体地,***设备包括:射频电路3004、触摸显示屏3005、摄像头3006、音频电路3007、定位组件3008和电源3009中的至少一种。
***设备接口3003可被用于将I/O(Input/Output,输入/输出)相关的至少一个***设备连接到处理器3001和存储器3002。在一些实施例中,处理器3001、存储器3002和***设备接口3003被集成在同一芯片或电路板上;在一些其他实施例中,处理器3001、存储器3002和***设备接口3003中的任意一个或两个可以在单独的芯片或电路板上实现,本实施例对此不加以限定。
射频电路3004用于接收和发射RF(Radio Frequency,射频)信号,也称电磁信号。射频电路3004通过电磁信号与通信网络以及其他通信设备进行通信。射频电路3004将电信号转换为电磁信号进行发送,或者,将接收到的电磁信号转换为电信号。可选地,射频电路3004包括:天线***、RF收发器、一个或多个放大器、调谐器、振荡器、数字信号处理器、编解码芯片组、用户身份模块卡等等。射频电路3004可以通过至少一种无线通信协 议来与其它终端进行通信。该无线通信协议包括但不限于:城域网、各代移动通信网络(2G、3G、4G及5G)、无线局域网和/或WiFi(Wireless Fidelity,无线保真)网络。在一些实施例中,射频电路3004还可以包括NFC(Near Field Communication,近距离无线通信)有关的电路,本公开对此不加以限定。
显示屏3005用于显示UI(User Interface,用户界面)。该UI可以包括图形、文本、图标、视频及其它们的任意组合。当显示屏3005是触摸显示屏时,显示屏3005还具有采集在显示屏3005的表面或表面上方的触摸信号的能力。该触摸信号可以作为控制信号输入至处理器3001进行处理。此时,显示屏3005还可以用于提供虚拟按钮和/或虚拟键盘,也称软按钮和/或软键盘。在一些实施例中,显示屏3005可以为一个,设置电子设备3000的前面板;在另一些实施例中,显示屏3005可以为至少两个,分别设置在电子设备3000的不同表面或呈折叠设计;在再一些实施例中,显示屏3005可以是柔性显示屏,设置在电子设备3000的弯曲表面上或折叠面上。甚至,显示屏3005还可以设置成非矩形的不规则图形,也即异形屏。显示屏3005可以采用LCD(Liquid Crystal Display,液晶显示屏)、OLED(Organic Light-Emitting Diode,有机发光二极管)等材质制备。
摄像头组件3006用于采集图像或视频。可选地,摄像头组件3006包括前置摄像头和后置摄像头。通常,前置摄像头设置在终端的前面板,后置摄像头设置在终端的背面。在一些实施例中,后置摄像头为至少两个,分别为主摄像头、景深摄像头、广角摄像头、长焦摄像头中的任意一种,以实现主摄像头和景深摄像头融合实现背景虚化功能、主摄像头和广角摄像头融合实现全景拍摄以及VR(Virtual Reality,虚拟现实)拍摄功能或者其它融合拍摄功能。在一些实施例中,摄像头组件3006还可以包括闪光灯。闪光灯可以是单色温闪光灯,也可以是双色温闪光灯。双色温闪光灯是指暖光闪光灯和冷光闪光灯的组合,可以用于不同色温下的光线补偿。
音频电路3007可以包括麦克风和扬声器。麦克风用于采集用户及环境的声波,并将声波转换为电信号输入至处理器3001进行处理,或者输入至射频电路3004以实现语音通信。出于立体声采集或降噪的目的,麦克风可以为多个,分别设置在电子设备3000的不同部位。麦克风还可以是阵列麦克风或全向采集型麦克风。扬声器则用于将来自处理器3001或射频电路3004的电信号转换为声波。扬声器可以是传统的薄膜扬声器,也可以是压电陶瓷扬声器。当扬声器是压电陶瓷扬声器时,不仅可以将电信号转换为人类可听见的声波,也可以将电信号转换为人类听不见的声波以进行测距等用途。在一些实施例中,音频电路3007还可以包括耳机插孔。
定位组件3008用于定位电子设备3000的当前地理位置,以实现导航或LBS(Location Based Service,基于位置的服务)。定位组件3008可以是基于美国的GPS(Global Positioning System,全球定位***)、中国的北斗***、俄罗斯的格雷纳斯***或欧盟的伽利略***的定位组件。
电源3009用于为电子设备3000中的各个组件进行供电。电源3009可以是交流电、直流电、一次性电池或可充电电池。当电源3009包括可充电电池时,该可充电电池可以支持有线充电或无线充电。该可充电电池还可以用于支持快充技术。
在一些实施例中,电子设备3000还包括有一个或多个传感器4100。该一个或多个传感器4100包括但不限于:加速度传感器4101、陀螺仪传感器4102、压力传感器4103、指纹传感器4104、光学传感器4105以及接近传感器4106。
加速度传感器4101可以检测以电子设备3000建立的坐标系的三个坐标轴上的加速度大小。比如,加速度传感器4101可以用于检测重力加速度在三个坐标轴上的分量。处理器3001可以根据加速度传感器4101采集的重力加速度信号,控制触摸显示屏3005以横向视图或纵向视图进行用户界面的显示。加速度传感器4101还可以用于游戏或者用户的运动数据的采集。
陀螺仪传感器4102可以检测电子设备3000的机体方向及转动角度,陀螺仪传感器4102可以与加速度传感器4101协同采集用户对电子设备3000的3D动作。处理器3001根据陀螺仪传感器4102采集的数据,可以实现如下功能:动作感应(比如根据用户的倾斜操作来改变UI)、拍摄时的图像稳定、游戏控制以及惯性导航。
压力传感器4103可以设置在电子设备3000的侧边框和/或触摸显示屏3005的下层。当压力传感器4103设置在电子设备3000的侧边框时,可以检测用户对电子设备3000的握持信号,由处理器3001根据压力传感器4103采集的握持信号进行左右手识别或快捷操作。当压力传感器4103设置在触摸显示屏3005的下层时,由处理器3001根据用户对触摸显示屏3005的压力操作,实现对UI界面上的可操作性控件进行控制。可操作性控件包括按钮控件、滚动条控件、图标控件、菜单控件中的至少一种。
指纹传感器4104用于采集用户的指纹,由处理器3001根据指纹传感器4104采集到的指纹识别用户的身份,或者,由指纹传感器4104根据采集到的指纹识别用户的身份。在识别出用户的身份为可信身份时,由处理器3001授权该用户执行相关的敏感操作,该敏感操作包括解锁屏幕、查看加密信息、下载软件、支付及更改设置等。指纹传感器4104可以被设置电子设备3000的正面、背面或侧面。当电子设备3000上设置有物理按键或厂商Logo时,指纹传感器4104可以与物理按键或厂商Logo集成在一起。
光学传感器4105用于采集环境光强度。在一个实施例中,处理器3001可以根据光学 传感器4105采集的环境光强度,控制触摸显示屏3005的显示亮度。具体地,当环境光强度较高时,调高触摸显示屏3005的显示亮度;当环境光强度较低时,调低触摸显示屏3005的显示亮度。在另一个实施例中,处理器3001还可以根据光学传感器4105采集的环境光强度,动态调整摄像头组件3006的拍摄参数。
接近传感器4106,也称距离传感器,通常设置在电子设备3000的前面板。接近传感器4106用于采集用户与电子设备3000的正面之间的距离。在一个实施例中,当接近传感器4106检测到用户与电子设备3000的正面之间的距离逐渐变小时,由处理器3001控制触摸显示屏3005从亮屏状态切换为息屏状态;当接近传感器4106检测到用户与电子设备3000的正面之间的距离逐渐变大时,由处理器3001控制触摸显示屏3005从息屏状态切换为亮屏状态。
本领域技术人员可以理解,图32中示出的结构并不构成对电子设备3000的限定,可以包括比图示更多或更少的组件,或者组合某些组件,或者采用不同的组件布置。
在示例性实施例中,还提供了一种包括指令的非临时性计算机可读存储介质,例如包括指令的存储器3002,上述指令可由电子设备3000的处理器3001执行以完成上述清洁机器人的障碍躲避方法,该方法包括:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。可选地,上述指令还可以由电子设备3000的处理器3001执行以完成上述示例性实施例中所涉及的其他步骤。例如,所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在示例性实施例中,还提供了一种应用程序/计算机程序产品,包括一条或多条指令,该一条或多条指令可以由电子设备3000的处理器3001执行,以完成上述清洁机器人的障碍躲避方法,该方法包括:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。可选地,上述指令还可以由电子设备3000的处理器3001执行以完成上述示例性实施例中所 涉及的其他步骤。
可选地,在本公开的一些实施例中,清洁设备可以为机器人,控制设备可以是机器人控制装置,如图33所示,该机器人控制装置8应用于机器人,该机器人安装有第一激光传感器和第二激光传感器,该第一激光传感器在该机器人本体上的倾角和该第二激光传感器在该机器人本体上的倾角不同,且该第一激光传感器在该机器人本体上的安装高度和该第二激光传感器在该机器人本体上的安装高度也不同,该机器人控制装置8包括:第一距离获取模块81、第二距离获取模块82、第一落点坐标确定模块83、第二落点坐标确定模块84、障碍物类型识别模块85、运动控制模块86。其中:
第一距离获取模块81,用于通过该第一激光传感器获取第一传感距离,该第一传感距离为该第一激光传感器发射的激光的光斑落点与该第一激光传感器的距离。
具体地,第一激光传感器发射激光,当激光被遮挡时,将在遮挡物上形成光斑落点。由于光的传播速度是固定的,因此,根据光的传播速度以及其传播时间能够计算出第一激光传感器与对应的光斑落点的距离。
需要指出的是,本公开实施例的第一传感距离可由第一激光传感器计算得到,并由该第一激光传感器发送给机器人,也可由机器人计算得到。
本公开实施例的机器人可为用于清洁的清洁机器人等清洁设备。
第二距离获取模块82,用于通过该第二激光传感器获取第二传感距离,该第二传感距离为该第二激光传感器发射的激光的光斑落点与该第二激光传感器的距离。
其中,第二传感距离的计算方式与第一传感距离的计算方式相同,此处不再赘述。
第一落点坐标确定模块83,用于根据该第一激光传感器在该机器人的安装高度、倾角以及该第一传感距离,确定第一落点坐标,该第一落点坐标为该第一激光传感器发射的激光的光斑落点的坐标。
其中,第一激光传感器在机器人的安装高度,是指该第一激光传感器在机器人的安装位置到地面的距离。
其中,第一激光传感器在机器人的倾角,是指该第一激光传感器的激光发射口与机器人的夹角中小于90°的夹角。
如图25所示,第一激光传感器的激光发射点为A1,该A1的光斑落点为A2,该第一激光传感器的倾角为,第一激光传感器在该机器人的安装高度为H1,第一传感距离为A1A2。第二激光传感器的激光发射点为B1,该B1的光斑落点为B2,该第一激光传感器的倾角为,第一激光传感器在该机器人的安装高度为H2,第一传感距离为B1B2。
根据图25中的直角三角形的斜边(如A1A2)的长度以及倾角(如)能够确定直角三 角形中水平方向的直角边的长度,进而确定A2中的横坐标。另外,根据直角三角形的斜边的长度以及倾角能够确定直角三角形中垂直方向的直角边的长度,将该直角边的长度与安装高度H1结合,能够计算出A2的纵坐标。
第二落点坐标确定模块84,用于根据该第二激光传感器在该机器人的安装高度、倾角以及该第二传感距离,确定第二落点坐标,该第二落点坐标为该第二激光传感器发射的激光的光斑落点的坐标。
其中,第二落点坐标的计算方式与第一落点坐标的计算方式相同,此处不再赘述。
障碍物类型识别模块85,用于根据该第一落点坐标、该第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,该目标区域为该第一落点坐标和该第二落点坐标所在的区域。
其中,预设的允许越障高度是指机器人能够翻越的最高的障碍高度。
本实施例中,由于两个相近位置在垂直方向的信息和水平方向的信息能够反应这两个相近位置所在的区域的障碍物类型,比如,在两个相近位置所在的区域的障碍物类型为大台阶时,这两个相近位置在垂直方向的值通常远小于允许越障高度,因此,通过上述方式,能够准确识别对应区域的障碍物类型。
运动控制模块86,用于根据该障碍物类型控制该机器人的运动。
本实施例中,机器人根据不同的障碍物类型控制其自身执行对应的运动,以提高控制的精度。
本公开实施例中,由于机器人安装的第一激光传感器和第二激光传感器的倾角不同,且该第一激光传感器在该机器人的安装高度和该第二激光传感器在该机器人的安装高度也不同,因此,基于第一激光传感器和第二激光传感器所得到的第一落点坐标和第二落点坐标为两个不同位置对应的坐标。而由于两个不同位置的坐标能够反映这两个位置的高度差,因此,再结合预设的允许越障高度能够快速、准确地识别出这两个不同位置所在的区域对应的障碍物类型,比如识别该障碍物类型是否为机器人能够翻越的台阶。比如,能够在机器人到达台阶之前即可识别出前方是否有台阶,而无需在到达台阶时才能识别前方是否有台阶。
在一些实施例中,该第一激光传感器的安装高度大于该第二激光传感器的安装高度,且该第一激光传感器发射的激光能够到达的距离大于该第二激光传感器发射的激光能够到达的距离,该第一落点坐标为(Xa,Ya),该机器人控制装置8,还包括:
绝对值比较模块,用于将该Ya的绝对值与该允许越障高度比较。
其中,Ya是第一落点坐标的纵坐标,其值可能大于0,也可能小于0。
其中,允许越障高度为大于0的值。
暂停控制模块,用于若该Ya的绝对值大于该允许越障高度,则控制该机器人暂停运动。
本实施例中,若Ya大于0,则在Ya大于该允许越障高度时,表明机器人的前方可能存在较高的障碍物,此时,先控制机器人停止运动,能够给机器人后续的控制留出足够的时间。
同理,若Ya小于0,则在Ya小于允许越障高度的负数时,表明机器人的前方可能存在较低的台阶(如向下的台阶),此时,先控制机器人停止运动,能够给机器人后续的控制留出足够的时间。
本公开实施例中,由于Ya为从第一激光传感器中发射出来的激光对应的光斑落点,而第一激光传感器在机器人上的安装位置要高于第二激光传感器在机器人上的安装高度,而且,从该第一激光传感器中发射出来的激光所能够到达的距离要大于该从第二激光传感器中发射出来的激光所能够到达的距离,因此,与第二落点坐标相比,第一落点坐标的Ya能够反映机器人前方更远的位置的障碍物信息,进而有利于机器人更早地做出反映。同时,由于在Ya的绝对值比预设的允许越障高度大时,表明机器人的前方可能存在向上的台阶或障碍物,或者,可能存在向下的台阶,因此,先控制机器人停止运动,并在判断出障碍物类型后再继续控制机器人运动,能够使得机器人在无法通过障碍物时具有足够的时间改变其运动,进而能够有效降低机器人发生意外的概率。
在一些实施例中,第一激光传感器可以为线激光传感器,第二激光传感器可以为激光测距传感器。
由于在识别障碍物类型时首先选择第一激光传感器对应的第一落点坐标进行处理,而线激光传感器对应的扫描区域大于激光测距传感器对应的扫描区域,因此,将第一激光传感器以及第二激光传感器分别设置为线激光传感器和激光测距传感器,不仅能够提高扫描到障碍物的概率,也能降低成本。
在一些实施例中,假设第二落点坐标的横坐标为Xb,纵坐标为Yb,允许越障高度为h,该障碍物类型识别模块85具体用于:
若该Ya小于-h,且该Yb不大于该Ya,则判定该目标区域对应的障碍物类型为大台阶;
本实施例中,在Ya<-h(即Ya的绝对值大于h)时,若判断出Yb≤Ya,则判定机器人前方为大台阶。此时,机器人可后退然后转向以更换路径。
若该Ya小于该-h,且该Yb小于0但大于该Ya,则判定该目标区域对应的障碍物类型为下坡道;
本实施例中,如图27所示,在Ya<-h(即Ya的绝对值大于h)时,若判断出Ya<Yb<0, 则判定机器人前方为下坡道。
若该Ya小于该-h,且该Yb不小于0,则判定该目标区域对应的障碍物类型为大台阶。
如图28所示,在Ya<-h(即Ya的绝对值大于h)时,若判断出Yb≥0,则判定机器人前方为大台阶。此时,机器人可后退然后转向以更换路径。
根据图27和图28中第一落点坐标与第二落点坐标的关系可知,本公开实施例所采用的判断方法能够准确判断出障碍物类型是否为大台阶,或者,是否为下坡道。
在一些实施例中,若障碍物类型为下坡道,则根据该障碍物类型控制该机器人的运动,包括:
确定该下坡道对应的角度;根据该下坡道对应的角度和预设的允许爬坡度数,控制该机器人的运动。
本实施例中,下坡道对应的角度可根据第一落点坐标以及第二落点坐标的关系计算得到。在下坡道对应的角度不大于预设的允许爬坡度数时,机器人继续前行并下坡。而在下坡道对应的角度大于预设的允许爬坡度数时,机器人后退然后转向,以更换路径。
本公开实施例中,由于机器人在设计后,通常不能翻越角度较大的坡道(如不能超出预设的允许爬坡度数),因此,当判断出机器人前方存在下坡道时,需要结合下坡道对应的角度以及预设的允许爬坡度数,选择对应的运动,以免在下坡道对应的角度过大时,机器人仍前行所导致的倾翻。
在一些实施例中,假设第二落点坐标的横坐标为Xb,纵坐标为Yb,该允许越障高度为h,该障碍物类型识别模块85还具体用于:
若该Ya大于该h,且该Xb不小于该Xa,则判定该目标区域对应的障碍物类型为高障碍物;
本实施例中,如图29所示,若Ya>h(即Ya的绝对值大于h)时,又判断出Xb≥Xa,则认为机器人的前方存在高障碍物,此时,机器人可后退然后转向,以更换路径。
若该Ya大于该h,且该Xb小于该Xa,则判定该目标区域对应的障碍物类型为上坡道。
本实施例中,若Ya>h(即Ya的绝对值大于h)时,又判断出Xb<Xa,则认为机器人的前方是一个上坡道。
根据图29和图30中第一落点坐标以及第二落点坐标的关系可知,本公开实施例所采用的判断方法能够准确判断出障碍物类型是否为高障碍物,或者,是否为上坡道。
在一些实施例中,假设障碍物类型为上坡道,则根据该障碍物类型控制该机器人的运动,包括:
确定该上坡道对应的角度;根据该上坡道对应的角度和预设的允许爬坡度数,控制该 机器人的运动。
本实施例中,根据第一落点坐标以及第二落点坐标能够计算出上坡道对应的角度。在上坡道对应的角度不大于预设的允许爬坡度数时,机器人继续前行并上坡。而在上坡道对应的角度大于预设的允许爬坡度数时,机器人后退然后转向,以更换路径。
本公开实施例中,由于在判断出机器人前方存在上坡道时,结合上坡道对应的角度以及预设的允许爬坡度数,选择对应的运动,因此,能够避免在上坡道对应的角度过大时,机器人仍前行所导致的倾翻。
在一些实施例中,第一激光传感器在机器人上的安装高度大于该第二激光传感器在机器人上的安装高度、从该第一激光传感器中发射出来的激光所能够到达的距离大于从该第二激光传感器中发射出来的激光所能够到达的距离、该第一落点坐标为(Xa,Ya),并且该允许越障高度为h,该机器人控制装置8还包括模式切换模块,该模式切换模块用于:
若该Ya大于目标高度且不大于该h,则控制该机器人从正常模式切换至低速模式,该目标高度大于0且小于该h,该低速模式的速度小于该正常模式的速度;
本公开一些实施例中,目标高度可设置为h/2。
由于当判断出Ya具有一定的高度时,表明机器人前方可能存在其不能翻越的区域,而低速模式中的速度较低,即其对应的惯性也越小,因此,将机器人从正常模式先切换至低速模式,能够通过提前预判来降低机器人发生意外的概率,从而提高对机器人的控制的准确度。
若该Ya不小于该目标高度的负数且不大于该目标高度,则控制该机器人以该正常模式运动;
本实施例中,由于目标高度在0和h之间,因此,当判断出Ya在该目标高度的负数和该目标高度之间时,表明机器人前方的区域为机器人能够翻越的区域的概率较高,此时,只需要控制机器人采用正常模式运动即可,以保证机器人能够顺利执行任务。
若该Ya不小于该h的负数且小于该目标高度的负数,则控制该机器人从正常模式切换至低速模式。
本实施例中,由于当判断出Ya小于目标高度的负数时,表明第一落点坐标所在的位置的地势较低,也即,表明机器人前方存在其不能翻越的区域的概率较高,而低速模式中的速度较低,即其对应的惯性也越小,因此,将机器人从正常模式先切换至低速模式,能够通过提前预判来降低机器人发生意外的概率,从而提高对机器人的控制的准确度。
需要说明的是,上述装置/单元之间的信息交互、执行过程等内容,由于与本公开方法实施例基于同一构思,其具体功能及带来的技术效果,具体可参见方法实施例部分,此处 不再赘述。
图34为本公开一实施例提供的机器人的结构示意图。如图34所示,该实施例的机器人9000包括:至少一个处理器9100(图34中仅示出一个处理器)、存储器9101以及存储在该存储器9101中并可在该至少一个处理器9100上运行的计算机程序9102,该处理器9100执行该计算机程序9102时实现上述任意各个方法实施例中的步骤。
该机器人可包括,但不仅限于,处理器9100、存储器9101。本领域技术人员可以理解,图34仅仅是机器人9000的举例,并不构成对机器人9000的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件,比如还可以包括输入输出设备、网络接入设备等。
所称处理器9100可以是中央处理单元(Central Processing Unit,CPU),该处理器9100还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
该存储器9101在一些实施例中可以是该机器人9000的内部存储单元,比如机器人9000的硬盘或内存。该存储器9101在另一些实施例中也可以是该机器人9000的外部存储设备,例如该机器人9000上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。进一步地,该存储器9101还可以既包括该机器人9000的内部存储单元也包括外部存储设备。该存储器9101用于存储操作***、应用程序、引导装载程序(BootLoader)、数据以及其他程序等,例如该计算机程序的程序代码等。该存储器91还可以用于暂时地存储已经输出或者将要输出的数据。
所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,仅以上述各功能单元、模块的划分进行举例说明,实际应用中,可以根据需要而将上述功能分配由不同的功能单元、模块完成,即将该装置的内部结构划分成不同的功能单元或模块,以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中,上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。另外,各功能单元、模块的具体名称也只是为了便于相互区分,并不用于限制本公开的保护范围。上述***中单元、模块的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
本公开实施例还提供了一种网络设备,该网络设备包括:至少一个处理器、存储器以 及存储在该存储器中并可在该至少一个处理器上运行的计算机程序,该处理器执行该计算机程序时实现上述任意各个方法实施例中的步骤。
本公开实施例还提供了一种计算机可读存储介质,该计算机可读存储介质存储有计算机程序,该计算机程序被处理器执行时实现可实现上述各个方法实施例中的步骤。
本公开实施例提供了一种计算机程序产品,当计算机程序产品在移动终端上运行时,使得移动终端执行时实现可实现上述各个方法实施例中的步骤。
可选地,在本公开的一些实施例中,房间特征参数包括房间的房间特征信息,障碍物参数包括所述房间内的物体的位置,其中,控制设备还用于,
根据所述房间特征信息确定清洁参数;
控制所述清洁设备避开所述物体的位置,并按照所述清洁参数工作。
即言,在本公开的一些实施例中,提出了一种清洁设备的控制装置,图35示出了一种清洁设备的控制装置9200的示意框图。其中,该清洁设备的控制装置9200包括第二获取模块9202、第二确定模块9204和第二控制模块9206。
其中,第二获取模块9202能够获取清洁设备待清洁房间的房间特征信息以及待清洁房间内的物体的位置;第二确定模块9204能够基于待清洁房间的房间特征信息,确定清洁参数;第二控制模块9206能够根据该清洁参数,控制清洁设备工作,并且在工作的过程中避开待清洁房间内的物体的位置。
在该技术方案中,清洁设备可以为扫地机器人、拖地机器人、扫拖一体机等设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,清洁设备上安装有摄像头、红外线传感器等设备,能够采集房间内的房间特征信息以及房间内的固定物体的具***置,该物体的位置特征信息能够表示出房间类型、房间内的地面铺设等情况。
进一步地,根据该房间内的房间特征信息确定对应的清洁参数,根据固定物体的具***置确定清洁设备的路线,使得清洁设备能够避开固定物体的具***置移动,且按照该控制信息进行清洁工作。
通过上述方式,清洁设备能够基于房间的具体情况,自适应设置合理的清洁方式,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
在该技术方案中,房间特征信息可以包括房间的类型,进而使得第二确定模块9204能够根据房间的类型对应确定清洁设备的第一清洁参数。其中,清洁设备的清洁参数包括第一清洁参数,房间可以包括卧室、客厅、厨房或卫生间,清洁设备在不同类型的房间的清洁优先级、清洁程度等第一清洁参数可以不同。通过上述方式,能够按照房间的类型,自适应地控制清洁设备的清洁方式,从而提高房间清洁的高效性、准确性。
在该技术方案中,在房间为卧室或客厅的情况下,清洁优先级大于或等于第一阈值,基于房间为卫生间或厨房,清洁优先级小于第一阈值。
在该技术方案中,由于卫生间或厨房的脏污程度相比于卧室或客厅的脏污程度要 大,所以对卫生间或厨房的清洁程度也要大。也就是说,在房间类型为卫生间或厨房的情况下,清洁程度大于或等于第二阈值,在房间类型为卧室或客厅的情况下,清洁程度小于第二阈值。
在该技术方案中,房间特征信息可以包括地面铺设的材质,例如材质包括木质(例如地板)、瓷质、石质(例如地砖)、混凝土等。清洁设备的清洁参数包括第二清洁参数,第二清洁参数可以为出水量、清洁次数、风机吸力中的至少一项。具体地,第二确定模块9204能够基于房间的地面铺设的材质,对应确定清洁设备工作的出水量、清洁次数、风机吸力等。通过上述方式,清洁设备能够基于房间内地面铺设的材质,对该房间实现更加个性化、智能化的清洁。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的出水量小于或等于第三阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的出水量大于第三阈值且小于或等于第四阈值;在地面铺设材质为混凝土的情况下,清洁设备的出水量大于第四阈值,其中第四阈值大于第三阈值。
在该技术方案中,在地面铺设材质为木质的情况下,清洁设备的清洁次数大于或等于第五阈值;在地面铺设材质为瓷质或石质的情况下,清洁设备的清洁次数小于第五阈值且大于或等于第六阈值;在地面铺设材质为混凝土的情况下,清洁设备的清洁次数小于第六阈值,其中第六阈值小于第五阈值。
在该技术方案中,第二确定模块9204还能够确定房间内物体与地面之间的相对位置信息,该相对位置信息能够表示出物体与地面之间是否有空隙,以及在有空隙的情况下空隙的尺寸。第二确定模块9204根据是否有空隙或者有空隙时空隙的尺寸,从而第二控制模块9206能够基于相对位置信息控制清洁设备是否避开物体运动。通过上述方式,实现对清洁设备避开物体的方式进行控制,提高对房间的清洁效果。
在该技术方案中,清洁设备的控制装置9200还包括采集模块,能够采集房间的第一图像,第二确定模块9204基于该第一图像明确清洁设备所进入的具体房间,进而根据房间与房间特征信息以及物体的位置之间的预设对应关系,确定与该房间所对应的房间特征信息、物体的位置。
在该技术方案中,第二控制模块9206还用于控制清洁设备在房间内移动,采集模块还用于在清洁设备移动过程中获取该房间的第二图像,实现定位建图。进一步地,第二控制模块9206还用于在第二图像中识别出该房间的房间特征信息以及物体的位置,并将房间名称与房间特征信息以及物体的位置对应存储,实现建立预设对应关系。
可选地,本公开实施例,还提出了一种清洁设备,图36示出了本公开实施例的清洁设备1001的示意框图。其中,该清洁设备1001包括存储器1002和处理器1004。
其中,存储器1002中存储有程序或指令,处理器1004执行程序或指令时实现如上述任一技术方案的清洁设备的控制方法的步骤。存储器1002和处理器1004可以通过总线或者其它方式连接。处理器1004可包括一个或多个处理单元,处理器1004可以为中央处理器(Central Processing Unit,CPU)、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field Programmable Gate Array,FPGA)等芯片。
本公开提供的清洁设备1001,程序或指令被处理器1004执行时实现如上述任一技术方案的清洁设备的控制方法的步骤,因此该清洁设备1001包括上述任一技术方案的清洁设备的控制方法的全部有益效果。
在上述技术方案中,清洁设备1001可以为拖地机或扫拖一体机。
可选地,本公开实施例,还提出了一种清洁设备,图37示出了本公开实施例的清洁设备1100的示意框图。其中,该清洁设备1100包括如上述技术方案的清洁设备的控制装置9200。
本公开提供的清洁设备1100包括如上述技术方案的清洁设备的控制装置9200,因此该清洁设备1100包括上述任一技术方案的清洁设备的控制装置9200的全部有益效果。
本公开实施例,提出了一种可读存储介质,其上存储有程序或指令,程序或指令被处理器执行时实现如上述任一技术方案的清洁设备的控制方法的步骤。
其中,可读存储介质包括只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等。
本公开提供的可读存储介质,程序或指令被处理器执行时实现如上述任一技术方案的清洁设备的控制方法的步骤,因此该可读存储介质包括上述任一技术方案的清洁设备的控制方法的全部有益效果。
可选地,在本公开的一些实施例中,所述房间特征参数包括房间的地面特征信息,其中,所述控制设备还用于,根据所述地面特征信息确定控制信息,并根据所述控制信息控制所述清洁设备工作。
即言,在本公开的一些实施例中,提出了一种可移动设备的控制装置,图38示出了本公开一个实施例的可移动设备的控制装置4000的示意框图。其中,该可移动设备的控制装置4000包括第三获取模块4002和第三控制模块4004。
其中,第三获取模块4002能够获取房间的地面特征信息,第三控制模块4004能够基于该地面特征信息,确定对可移动设备的控制信息,并控制可移动设备,按照该控制信息工作。
在该技术方案中,可移动设备可以为扫地机器人、拖地机器人、扫拖一体机等清洁设备,可以在多个房间内进行移动,从而实现在不同房间进行清洁的目的。
具体地,可移动设备上安装有摄像头、红外线传感器等设备,能够采集房间内的地面特征信息,该地面特征信息能够表示出房间内的地面铺设情况。进一步地,根据该房间内的地面特征信息确定对应的控制信息,从而使得可移动设备按照该控制信息进行清洁工作。
通过上述方式,可移动设备能够基于房间的地面情况,实现更加智能化、定制化的清洁,提高房间清洁的高效性、准确性。
在本公开的一些实施例中,提出了一种可移动设备,图39示出了本公开一个实施例的可移动设备1400的示意框图。其中,该可移动设备1400包括存储器1402和处理器1404。
存储器1402,用于存储程序或指令;处理器1404,执行程序或指令时实现如上述任一技术方案的可移动设备的控制方法的步骤。
存储器1402和处理器1404可以通过总线或者其它方式连接。处理器1404可包括一个或多个处理单元,处理器1404可以为中央处理器(Central Processing Unit,CPU)、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Applicat ion Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field Programmable Gate Array,FPGA)等芯片。
本公开提供的可移动设备1400,程序或指令被处理器1404执行时实现如上述任一技术方案的可移动设备的控制方法的步骤,因此该可移动设备1400包括上述任一技术方案的可移动设备的控制方法的全部有益效果。
可选地,在本公开的一些实施例,提出了一种可移动设备,图40示出了本公开一个实施例的可移动设备1500的示意框图。其中,该可移动设备1500包括如上述技术方案的可移动设备的控制装置4000。
本公开提供的可移动设备1500包括如上述技术方案的可移动设备的控制装置4000,因此该可移动设备1500包括上述任一技术方案的可移动设备的控制装置4000的全部有益效果。
本公开实施例,还提出了一种可读存储介质,其上存储有程序或指令,程序或指令被处理器执行时实现如上述任一技术方案的可移动设备的控制方法的步骤。
其中,可读存储介质包括只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等。
本公开提供的可读存储介质,程序或指令被处理器执行时实现如上述任一技术方案的可移动设备的控制方法的步骤,因此该可读存储介质包括上述任一技术方案的可移动设备的控制方法的全部有益效果。
在本公开的描述中,需要理解的是,术语“中心”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系,仅是为了便于描述本公开和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本公开的限制。
需要说明的是,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。进一步地,在本公开的描述中,除非另有说明,“多个”的含义是两个或两个以上。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示意性实施例”、“示 例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本公开的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不一定指的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。
尽管已经示出和描述了本公开的实施例,本领域的普通技术人员可以理解:在不脱离本公开的原理和宗旨的情况下可以对这些实施例进行多种变化、修改、替换和变型,本公开的范围由权利要求及其等同物限定。
Claims (44)
- 一种清洁设备的控制方法,其特征在于,所述方法包括:对所述清洁设备的运行环境进行检测,获取环境特征参数,其中,所述环境特征参数包括房间特征参数和障碍物参数中的至少一个;根据所述房间特征参数和所述障碍物参数中的至少一个,控制所述清洁设备进行清洁。
- 根据权利要求1所述的方法,其特征在于,所述房间特征参数包括房间的地面特征信息,其中,根据所述房间特征参数,控制所述清洁设备进行清洁,包括:根据所述地面特征信息确定控制信息,并根据所述控制信息控制所述清洁设备工作。
- 根据权利要求2所述的方法,其特征在于,所述地面特征信息包括地面铺设材质,所述根据所述地面特征信息确定控制信息,包括:确定与所述地面铺设材质对应的第一控制信息;其中,所述第一控制信息包括以下至少一项:出水量、清洁次数、风机吸力、移动速度。
- 根据权利要求3所述的方法,其特征在于,所述地面铺设材质为木质情况下的所述出水量小于所述地面铺设材质为瓷质或石质情况下的所述出水量;和/或所述地面铺设材质为木质情况下的所述清洁次数大于所述地面铺设材质为瓷质或石质情况下的所述清洁次数。
- 根据权利要求2所述的方法,其特征在于,所述地面特征信息包括地面铺设方向,所述根据所述地面特征信息确定控制信息,包括:确定与所述地面铺设方向对应的第二控制信息;其中,所述第二控制信息为所述清洁设备的清洁方向与所述地面铺设方向一致。
- 根据权利要求2-5中任一项所述的方法,其特征在于,所述地面特征信息包括地面尺寸,所述根据所述地面特征信息确定控制信息,包括:根据所述地面尺寸确定所述房间的类型;确定与所述房间的类型对应的第三控制信息。
- 根据权利要求6所述的方法,其特征在于,所述房间的类型包括以下至少一项:卧室、客厅、厨房、卫生间;所述第三控制信息包括以下至少一项:房间清洁顺序、清洁剂量、消毒剂量。
- 根据权利要求2-5中任一项所述的方法,其特征在于,所述地面特征信息包括插座位置,所述根据所述地面特征信息确定控制信息,包括:确定与所述插座位置对应的第四控制信息。
- 根据权利要求8所述的方法,其特征在于,所述第四控制信息为所述清洁设备的清洁范围为所述插座位置的预设范围外。
- 根据权利要求2-5中任一项所述的方法,其特征在于,所述地面特征信息包括所述房间的房间分界特征,所述根据所述地面特征信息确定控制信息,包括:基于所述房间分界特征的高度小于或等于预设阈值,确定与所述房间分界特征对应的控制信息。
- 根据权利要求2-5中任一项所述的方法,其特征在于,获取所述房间的地面特征信息,包括:获取所述房间的房间分界特征;基于所述清洁设备经过所述房间分界特征进入所述房间,获取所述房间的地面特征信息。
- 根据权利要求1所述的方法,其特征在于,所述房间特征参数包括房间的房间特征信息,所述障碍物参数包括所述房间内的物体的位置,其中,根据所述房间特征参数和所述障碍物参数,控制所述清洁设备进行清洁,包括:根据所述房间特征信息确定清洁参数;控制所述清洁设备避开所述物体的位置,并按照所述清洁参数工作。
- 根据权利要求12所述的方法,其特征在于,所述房间特征信息包括房间类型,所述根据所述房间特征信息确定清洁参数,包括:确定与所述房间类型对应的第一清洁参数;其中,所述第一清洁参数包括以下至少一项:清洁优先级、清洁程度。
- 根据权利要求13所述的方法,其特征在于,所述房间类型为卧室或客厅情况下的清洁优先级,大于所述房间类型为卫生间或厨房情况下的清洁优先级;和/或所述房间类型为卫生间或厨房情况下的清洁程度,大于所述房间类型为卧室或客厅情况下的清洁程度。
- 根据权利要求12所述的方法,其特征在于,所述房间特征信息包括地面铺设材质,所述根据所述房间特征信息确定清洁参数,包括:确定与所述地面铺设材质对应的第二清洁参数;其中,所述第二清洁参数包括以下至少一项:出水量、清洁次数、风机吸力。
- 根据权利要求15所述的方法,其特征在于,所述地面铺设材质为木质情况下的出水量、所述地面铺设材质为瓷质或石质情况下的出水量、所述地面铺设材质为混凝土情况下的出水量依次增大;和/或所述地面铺设材质为木质情况下的清洁次数、所述地面铺设材质为瓷质或石质情况下的清洁次数、所述地面铺设材质为混凝土情况下的清洁次数依次减小。
- 根据权利要求12-16中任一项所述的方法,其特征在于,所述控制所述清洁设备避开所述物体的位置,包括:确定所述物体与所述房间的地面的相对位置信息;根据所述相对位置信息,控制所述清洁设备避开所述物体的位置。
- 根据权利要求12-16中任一项所述的方法,其特征在于,获取环境特征参数,包括:采集所述房间的第一图像,根据所述第一图像识别所述房间;根据预设对应关系,确定与所述房间对应的所述房间特征信息以及所述物体的位置。
- 根据权利要求18所述的方法,其特征在于,在获取环境特征参数之前,所述方法还包括:控制所述清洁设备在所述房间内移动并采集所述房间的第二图像;根据所述第二图像,确定所述房间特征信息和所述物体的位置,并建立所述预设对应关系。
- 根据权利要求1所述的方法,其特征在于,所述清洁设备为清洁机器人,其中,根据所述障碍物参数,控制所述清洁设备进行清洁,包括:获取运行指令后,以第一速率在目标区域启动清洁功能;若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;基于所述目标障碍躲避路线,运行所述清洁机器人。
- 根据权利要求20所述的方法,其特征在于,所述基于所述识别结果,选取对应的目标障碍躲避路线,包括:若确定能够识别所述目标障碍物对应的物体类别,选取第一障碍躲避路线,所述第一障碍躲避路线为用于指示所述清洁机器人在不更改当前前进方向的情况下,绕开所述目标障碍物的路线;或,若确定不能够识别所述目标障碍物对应的物体类别,选取第二障碍躲避路线,所述第二障碍躲避路线为用于指示所述清洁机器人以绕开所述目标障碍物的情况下,以其他前进方向运行的路线。
- 根据权利要求21所述的方法,其特征在于,所述若确定能够识别所述目标障碍物对应的物体类别,选取第一障碍躲避路线,包括:确定所述目标障碍物对应的物体类别,并基于预存的障碍物数据集合,得到所述物体类别对应的轮廓参数以及尺寸参数;基于所述轮廓参数以及尺寸参数,计算得到所述目标障碍物的外切图像;基于所述外切图像以及purePuresuit算法,计算生成所述第一障碍躲避路线。
- 根据权利要求22所述的方法,其特征在于,在所述计算生成所述第一障碍躲避路线之后,所述方法还包括:选取所述第一障碍躲避路线并运行所述清洁机器人;当检测到所述清洁机器人绕开所述目标障碍物且朝向至所述当前前进方向前进时,确定所述清洁机器人的障碍躲避完成。
- 根据权利要求21所述的方法,其特征在于,所述若确定不能够识别所述目标障碍物对应的物体类别,选取第二障碍躲避路线,包括:若确定不能够识别所述目标障碍物对应的物体类别,获取所述目标障碍物与所述清洁机器人的平行角度差值;基于所述平行角度差值,确定用于旋转所述清洁机器人前进方向的旋转角度,并基于所述旋转角度,计算生成所述第二障碍躲避路线。
- 根据权利要求24所述的方法,其特征在于,在所述计算生成所述第二障碍躲避路线之后,所述方法还包括:选取所述第二障碍躲避路线并运行所述清洁机器人;当检测到所述清洁机器人朝向所述其他前进方向前进并且距离所述目标障碍物超过第二距离时,确定所述清洁机器人的障碍躲避完成。
- 根据权利要求20所述的方法,其特征在于,在所述以第一速率在目标区域启动清洁功能之后,所述方法还包括:若检测到当前前进方向的第二距离处存在有所述目标障碍物时,将所述第一速率切换为第二速率,其中,所述第二速率低于所述第一速率,所述第二距离大于所述第一距离;检测所述目标障碍物是否位于所述当前前进方向的第一距离处。
- 根据权利要求20所述的方法,其特征在于,在所述以第一速率在目标区域启动清洁功能之前,所述方法还包括:获取所述目标区域的初始栅格地图,机器姿态信息,样本障碍物信息,其中所述样本障碍物信息包括样本障碍物的参数以及所述样本障碍物对应的物体类别;通过Bresenham算法,将各个样本障碍物投影到所述初始栅格地图上,生成语义地图;其中,所述获取运行指令后,以第一速率在目标区域启动清洁功能,包括:当获取到所述运行指令后,基于所述语义地图以所述第一速率在所述目标区域启动清洁功能。
- 根据权利要求20所述的方法,其特征在于,所述基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果,包括:利用所述摄像装置,获取所述目标障碍物图像;利用图像检测分类模型,提取所述目标障碍物图像的物体特征,所述物体特征包括大小特征、色彩特征以及轮廓特征的至少一种;确定存在所述物体特征,确定所述目标障碍物对应的物体类别的识别结果。
- 根据权利要求28所述的方法,其特征在于,在所述利用所述摄像装置,获取所述目标障碍物图像之前,所述方法还包括:获取至少两个的样本图像,其中,所述样本图像中包括至少一个障碍物体特征;基于所述障碍物的物体类别,对各个所述样本图像标注对应的类别标识;利用所述标注有类别标识的样本图像,以及所述样本图像中包括的障碍物体特征,对预设的图像语义分割模型进行训练,得到满足预设条件的所述图像检测分类模型,所述图像检测分类模型用于确定所述目标障碍物对应的物体类别。
- 根据权利要求1所述的方法,其特征在于,所述清洁设备为机器人,所述机器人安装有第一激光传感器和第二激光传感器,所述第一激光传感器在所述机器人上的倾角和所述第二激光传感器在所述机器人上的倾角不同,且所述第一激光传感器在所述机器人上的安装高度和所述第二激光传感器在所述机器人上的安装高度也不同,其中,根据所述障碍物参数,控制所述清洁设备进行清洁,包括:通过所述第一激光传感器获取第一传感距离,所述第一传感距离为所述第一激光传感器发射的激光的光斑落点与所述第一激光传感器的距离;通过所述第二激光传感器获取第二传感距离,所述第二传感距离为所述第二激光传感器发射的激光的光斑落点与所述第二激光传感器的距离;根据所述第一激光传感器在所述机器人的安装高度、倾角以及所述第一传感距离,确定第一落点坐标,所述第一落点坐标为所述第一激光传感器发射的激光的光斑落点的坐标;根据所述第二激光传感器在所述机器人的安装高度、倾角以及所述第二传感距离,确定第二落点坐标,所述第二落点坐标为所述第二激光传感器发射的激光的光斑落点的坐标;根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,所述目标区域为所述第一落点坐标和所述第二落点坐标所在的区域;根据所述障碍物类型控制所述机器人的运动。
- 根据权利要求30所述的方法,其特征在于,所述第一激光传感器的安装高度大于所述第二激光传感器的安装高度,且所述第一激光传感器发射的激光能够到达的距离大于所述第二激光传感器发射的激光能够到达的距离,所述第一落点坐标为(Xa,Ya),在所述识别目标区域对应的障碍物类型之前,所述方法还包括:将所述Ya的绝对值与所述允许越障高度比较;若所述Ya的绝对值大于所述允许越障高度,则控制所述机器人暂停运动。
- 根据权利要求31所述的方法,其特征在于,所述第二落点坐标为(Xb,Yb),所述允许越障高度为h,所述根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,包括:若所述Ya小于-h,且所述Yb不大于所述Ya,则判定所述目标区域对应的障碍物类型为大台阶;若所述Ya小于所述-h,且所述Yb小于0但大于所述Ya,则判定所述目标区域对应的障碍物类型为下坡道;若所述Ya小于所述-h,且所述Yb不小于0,则判定所述目标区域对应的障碍物类型为大台阶。
- 根据权利要求32所述的方法,其特征在于,所述障碍物类型为下坡道,所述根据所述障碍物类型控制所述机器人的运动,包括:确定所述下坡道对应的角度;根据所述下坡道对应的角度和预设的允许爬坡度数,控制所述机器人的运动。
- 根据权利要求31所述的方法,其特征在于,所述第二落点坐标为(Xb,Yb),所述允许越障高度为h,所述根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,包括:若所述Ya大于所述h,且所述Xb不小于所述Xa,则判定所述目标区域对应的障碍物类型为高障碍物;若所述Ya大于所述h,且所述Xb小于所述Xa,则判定所述目标区域对应的障碍物类型为上坡道。
- 根据权利要求34所述的方法,其特征在于,所述障碍物类型为上坡道,所述根据所述障碍物类型控制所述机器人的运动,包括:确定所述上坡道对应的角度;根据所述上坡道对应的角度和预设的允许爬坡度数,控制所述机器人的运动。
- 根据权利要求30所述的方法,其特征在于,所述第一激光传感器的安装高度大于所述第二激光传感器的安装高度、所述第一激光传感器发射的激光能够到达的距离大于所述第二激光传感器发射的激光能够到达的距离、所述第一落点坐标为(Xa,Ya),且所述允许越障高度为h,所述方法还包括:若所述Ya大于目标高度且不大于所述h,则控制所述机器人从正常模式切换至低速模式,所述目标高度大于0且小于所述h,所述低速模式的速度小于所述正常模式的速度;若所述Ya不小于所述目标高度的负数且不大于所述目标高度,则控制所述机器人以所述正常模式运动;若所述Ya不小于所述h的负数且小于所述目标高度的负数,则控制所述机器人从正常模式切换至低速模式。
- 根据权利要求30-36中任一项所述的方法,其特征在于,所述第一激光传感器为线激光传感器,所述第二激光传感器为激光测距传感器。
- 一种清洁设备的控制装置,其特征在于,包括:检测设备,用于对所述清洁设备的运行环境进行检测,获取环境特征参数,其中,所述环境特征参数包括房间特征参数和障碍物参数中的至少一个;控制设备,用于根据所述房间特征参数和所述障碍物参数中的至少一个,控制所述清洁设备进行清洁。
- 根据权利要求38所述的装置,其特征在于,所述清洁设备为清洁机器人,其中,所述控制设备包括:第一获取模块,被设置为获取运行指令后,以第一速率在目标区域启动清洁功能;第一检测模块,被设置为若检测到当前前进方向第一距离处存在有目标障碍物,基于设置在所述清洁机器人上的摄像装置,得到用于确定所述目标障碍物对应的物体类别的识别结果;第一选取模块,被设置为基于所述识别结果,选取对应的目标障碍躲避路线,所述目标障碍躲避路线对应于更改所述当前前进方向以及不更改所述当前前进方向的其中一种;第一运行模块,被设置为基于所述目标障碍躲避路线,运行所述清洁机器人。
- 根据权利要求38所述的装置,其特征在于,所述清洁设备为机器人,所述机器人安装有第一激光传感器和第二激光传感器,所述第一激光传感器在所述机器人的倾角和所述第二激光传感器在所述机器人的倾角不同,且所述第一激光传感器在所述机器人的安装高度和所述第二激光传感器在所述机器人的安装高度也不同,所述控制设备包括:第一距离获取模块,用于通过所述第一激光传感器获取第一传感距离,所述第一传感距离为所述第一激光传感器发射的激光的光斑落点与所述第一激光传感器的距离;第二距离获取模块,用于通过所述第二激光传感器获取第二传感距离,所述第二传感距离为所述第二激光传感器发射的激光的光斑落点与所述第二激光传感器的距离;第一落点坐标确定模块,用于根据所述第一激光传感器在所述机器人的安装高度、倾角以及所述第一传感距离,确定第一落点坐标,所述第一落点坐标为所述第一激光传感器发射的激光的光斑落点的坐标;第二落点坐标确定模块,用于根据所述第二激光传感器在所述机器人的安装高度、倾角以及所述第二传感距离,确定第二落点坐标,所述第二落点坐标为所述第二激光传感器发射的激光的光斑落点的坐标;障碍物类型识别模块,用于根据所述第一落点坐标、所述第二落点坐标以及预设的允许越障高度,识别目标区域对应的障碍物类型,所述目标区域为所述第一落点坐标和所述第二落点坐标所在的区域;运动控制模块,用于根据所述障碍物类型控制所述机器人的运动。
- 根据权利要求38所述的装置,其特征在于,所述房间特征参数包括房间的地面特征信息,其中,所述控制设备还用于,根据所述地面特征信息确定控制信息,并根据所述控制信息控制所述清洁设备工作。
- 根据权利要求38所述的装置,其特征在于,所述房间特征参数包括房间的房间特征信息,所述障碍物参数包括所述房间内的物体的位置,其中,所述控制设备还用于,根据所述房间特征信息确定清洁参数;控制所述清洁设备避开所述物体的位置,并按照所述清洁参数工作。
- 一种清洁设备,其特征在于,包括:存储器,用于存储程序或指令;处理器,所述处理器执行所述程序或指令时实现根据权利要求1-37中任一项所述的清洁设备的控制方法的步骤。
- 一种可读存储介质,其上存储有程序或指令,其特征在于,所述程序或指令被处理器执行时实现根据权利要求1-37中任一项所述的清洁设备的控制方法的步骤。
Applications Claiming Priority (8)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111633171.4 | 2021-12-28 | ||
CN202111633171.4A CN116352696A (zh) | 2021-12-28 | 2021-12-28 | 机器人控制方法、装置及机器人 |
CN202210018305.X | 2022-01-07 | ||
CN202210018305.XA CN114391777B (zh) | 2022-01-07 | 2022-01-07 | 清洁机器人的障碍躲避方法、装置、电子设备及介质 |
CN202210145556.4A CN114569003A (zh) | 2022-02-17 | 2022-02-17 | 可移动设备的控制方法、装置、可移动设备和存储介质 |
CN202210145455.7A CN114468857A (zh) | 2022-02-17 | 2022-02-17 | 清洁设备的控制方法、装置、清洁设备和可读存储介质 |
CN202210145556.4 | 2022-02-17 | ||
CN202210145455.7 | 2022-02-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023125698A1 true WO2023125698A1 (zh) | 2023-07-06 |
Family
ID=86998004
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/142944 WO2023125698A1 (zh) | 2021-12-28 | 2022-12-28 | 清洁设备及其控制方法和控制装置 |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2023125698A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117351065A (zh) * | 2023-12-05 | 2024-01-05 | 武汉市品持科技有限公司 | 一种清洁方法及装置、存储介质和电子设备 |
CN117468941A (zh) * | 2023-12-28 | 2024-01-30 | 四川省铁路建设有限公司 | 基于智能自检台车的隧道缺陷检测方法及自检台车 |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014014456A (ja) * | 2012-07-06 | 2014-01-30 | Nikon Corp | 掃除システム、掃除装置、浴室、制御方法、及びプログラム |
CN107569181A (zh) * | 2016-07-04 | 2018-01-12 | 九阳股份有限公司 | 一种智能清洁机器人及清扫方法 |
CN109452914A (zh) * | 2018-11-01 | 2019-03-12 | 北京石头世纪科技有限公司 | 智能清洁设备,清洁模式选择方法,计算机存储介质 |
CN109998429A (zh) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | 用于情境感知的移动清洁机器人人工智能 |
CN110623601A (zh) * | 2018-06-21 | 2019-12-31 | 科沃斯机器人股份有限公司 | 地面材质识别方法、装置、扫地机器人和存储介质 |
US20200178748A1 (en) * | 2018-12-06 | 2020-06-11 | Samsung Electronics Co., Ltd. | Robot vacuum cleaner and cleaning route planning method thereof |
CN111839371A (zh) * | 2020-08-21 | 2020-10-30 | 苏州三六零机器人科技有限公司 | 地面清扫方法、装置、扫地机和计算机存储介质 |
CN112401763A (zh) * | 2020-11-27 | 2021-02-26 | 深圳市杉川致行科技有限公司 | 扫地机器人的控制方法、扫地机器人以及计算机可读存储介质 |
CN112704437A (zh) * | 2020-12-23 | 2021-04-27 | 炬星科技(深圳)有限公司 | 扫地机器人控制方法、设备及存储介质 |
CN112828879A (zh) * | 2019-11-25 | 2021-05-25 | 上海高仙自动化科技发展有限公司 | 一种任务管理方法、装置、智能机器人和介质 |
US11019972B2 (en) * | 2015-10-27 | 2021-06-01 | Samsung Electronics Co., Ltd. | Cleaning robot and method for controlling same |
CN114391777A (zh) * | 2022-01-07 | 2022-04-26 | 美智纵横科技有限责任公司 | 清洁机器人的障碍躲避方法、装置、电子设备及介质 |
CN114468857A (zh) * | 2022-02-17 | 2022-05-13 | 美智纵横科技有限责任公司 | 清洁设备的控制方法、装置、清洁设备和可读存储介质 |
CN114569003A (zh) * | 2022-02-17 | 2022-06-03 | 美智纵横科技有限责任公司 | 可移动设备的控制方法、装置、可移动设备和存储介质 |
-
2022
- 2022-12-28 WO PCT/CN2022/142944 patent/WO2023125698A1/zh unknown
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014014456A (ja) * | 2012-07-06 | 2014-01-30 | Nikon Corp | 掃除システム、掃除装置、浴室、制御方法、及びプログラム |
US11019972B2 (en) * | 2015-10-27 | 2021-06-01 | Samsung Electronics Co., Ltd. | Cleaning robot and method for controlling same |
CN107569181A (zh) * | 2016-07-04 | 2018-01-12 | 九阳股份有限公司 | 一种智能清洁机器人及清扫方法 |
CN109998429A (zh) * | 2018-01-05 | 2019-07-12 | 艾罗伯特公司 | 用于情境感知的移动清洁机器人人工智能 |
CN110623601A (zh) * | 2018-06-21 | 2019-12-31 | 科沃斯机器人股份有限公司 | 地面材质识别方法、装置、扫地机器人和存储介质 |
CN109452914A (zh) * | 2018-11-01 | 2019-03-12 | 北京石头世纪科技有限公司 | 智能清洁设备,清洁模式选择方法,计算机存储介质 |
US20200178748A1 (en) * | 2018-12-06 | 2020-06-11 | Samsung Electronics Co., Ltd. | Robot vacuum cleaner and cleaning route planning method thereof |
CN112828879A (zh) * | 2019-11-25 | 2021-05-25 | 上海高仙自动化科技发展有限公司 | 一种任务管理方法、装置、智能机器人和介质 |
CN111839371A (zh) * | 2020-08-21 | 2020-10-30 | 苏州三六零机器人科技有限公司 | 地面清扫方法、装置、扫地机和计算机存储介质 |
CN112401763A (zh) * | 2020-11-27 | 2021-02-26 | 深圳市杉川致行科技有限公司 | 扫地机器人的控制方法、扫地机器人以及计算机可读存储介质 |
CN112704437A (zh) * | 2020-12-23 | 2021-04-27 | 炬星科技(深圳)有限公司 | 扫地机器人控制方法、设备及存储介质 |
CN114391777A (zh) * | 2022-01-07 | 2022-04-26 | 美智纵横科技有限责任公司 | 清洁机器人的障碍躲避方法、装置、电子设备及介质 |
CN114468857A (zh) * | 2022-02-17 | 2022-05-13 | 美智纵横科技有限责任公司 | 清洁设备的控制方法、装置、清洁设备和可读存储介质 |
CN114569003A (zh) * | 2022-02-17 | 2022-06-03 | 美智纵横科技有限责任公司 | 可移动设备的控制方法、装置、可移动设备和存储介质 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117351065A (zh) * | 2023-12-05 | 2024-01-05 | 武汉市品持科技有限公司 | 一种清洁方法及装置、存储介质和电子设备 |
CN117351065B (zh) * | 2023-12-05 | 2024-02-23 | 武汉市品持科技有限公司 | 一种清洁方法及装置、存储介质和电子设备 |
CN117468941A (zh) * | 2023-12-28 | 2024-01-30 | 四川省铁路建设有限公司 | 基于智能自检台车的隧道缺陷检测方法及自检台车 |
CN117468941B (zh) * | 2023-12-28 | 2024-03-12 | 四川省铁路建设有限公司 | 基于智能自检台车的隧道缺陷检测方法及自检台车 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023125698A1 (zh) | 清洁设备及其控制方法和控制装置 | |
CN108247647B (zh) | 一种清洁机器人 | |
US11709497B2 (en) | Method for controlling an autonomous mobile robot | |
US20230409032A1 (en) | Method for controlling an autonomous, mobile robot | |
CN112739244B (zh) | 移动机器人清洁*** | |
JP7139226B2 (ja) | 状況認識のためのモバイル清掃ロボット人工知能 | |
KR102616863B1 (ko) | 로봇 청소기 및 로봇 청소기의 청소 경로 계획 방법 | |
CN109998421B (zh) | 移动清洁机器人组合及持久性制图 | |
CN109947109B (zh) | 机器人工作区域地图构建方法、装置、机器人和介质 | |
US10265858B2 (en) | Auto-cleaning system, cleaning robot and method of controlling the cleaning robot | |
US11467603B2 (en) | Moving robot and control method thereof | |
JP7311172B2 (ja) | リモートロボット制御を提供する方法及びシステム | |
US10660496B2 (en) | Cleaning robot and method of controlling the cleaning robot | |
US20210244250A1 (en) | Self-actuated cleaning head for an autonomous vacuum | |
US20200064857A1 (en) | Robotic Cleaning Device with Operating Speed Variation Based on Environment | |
WO2021047348A1 (zh) | 可通行区域图的建立方法、处理方法、装置和可移动设备 | |
CN114391777B (zh) | 清洁机器人的障碍躲避方法、装置、电子设备及介质 | |
JP2010231359A (ja) | 遠隔操作装置 | |
US20230389762A1 (en) | Visual fiducial for behavior control zone | |
JP7519579B2 (ja) | 掃除機システム、および、危険位置掲示方法 | |
WO2024104381A1 (en) | Carpet cleaning method based on user editing, device, and computer-readable storage medium | |
WO2024145776A1 (zh) | 扫地机器人的控制方法、装置、扫地机器人、***及存储介质 | |
JP2022025721A (ja) | 掃除機システム、および掃除機 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22914949 Country of ref document: EP Kind code of ref document: A1 |