CN114662760A - Robot-based distribution method and robot - Google Patents
Robot-based distribution method and robot Download PDFInfo
- Publication number
- CN114662760A CN114662760A CN202210295732.2A CN202210295732A CN114662760A CN 114662760 A CN114662760 A CN 114662760A CN 202210295732 A CN202210295732 A CN 202210295732A CN 114662760 A CN114662760 A CN 114662760A
- Authority
- CN
- China
- Prior art keywords
- distribution
- robot
- map data
- task
- obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application relates to the technical field of artificial intelligence, in particular to a robot-based distribution method and a robot. The distribution robot receives a distribution instruction which is sent by the main control robot and used for executing a distribution task; obtaining map data required by executing the distribution task from the master robot, and generating a navigation path according to the obtained map data and a distribution address corresponding to the distribution task; in the process of executing a distribution task according to the generated navigation path, acquiring an environment image of a distribution environment in real time through a camera, and identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a robot-based distribution method and a robot.
Background
The electronic commerce develops rapidly, and the demand of express logistics service is increasing day by day, which also promotes the rapid development of the logistics service; in addition, at the present generation of rapid development of artificial intelligence, the intelligent park develops rapidly, and the realization of unmanned distribution in the park is an important link for the development of the intelligent park.
With the continuous maturity of intelligent robot technology, in order to further reduce labor costs, an alternative approach is to use intelligent robots for goods delivery in an intelligent park. However, in an intelligent park, how to plan a navigation path by an intelligent robot, and article distribution based on the generated navigation path becomes an urgent technical problem to be solved.
Disclosure of Invention
The embodiment of the application provides a robot-based distribution method and a robot, which are used for flexibly planning a navigation path and distributing articles based on the generated navigation path.
In a first aspect, an embodiment of the present application provides a robot-based distribution method, including:
the distribution robot receives a distribution instruction which is sent by the main control robot and used for executing a distribution task; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task;
the distribution robot acquires map data required for executing the distribution task from the main control robot, and generates a navigation path according to the acquired map data and a distribution address corresponding to the distribution task; the map data is generated by the master robot in advance according to the collected environmental data;
the distribution robot acquires an environment image of a distribution environment in real time through a camera in the process of executing the distribution task according to the generated navigation path, and identifies each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
and the distribution robot updates the generated navigation path in real time according to the map data marked with the positions of the obstacles and distributes according to the updated navigation path.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the distribution robot acquires, from the master robot, map data required for executing the distribution task, and specifically includes:
the distribution robot receives outdoor map data sent by the main control robot and indoor map data of a building corresponding to the distribution address; or
The distribution robot receives outdoor map data sent by the main control robot; after the distribution robot moves to the building corresponding to the distribution address according to the outdoor map data and the distribution address, acquiring identification information corresponding to the building; and sending the identification information of the building to the master robot, and receiving indoor map data of the building returned by the master robot.
Optionally, the position information of each obstacle in the environment image is pixel coordinate information of each obstacle in the environment image;
the marking, in the map data, the position of each obstacle according to the position information of each obstacle in the environment image specifically includes:
the distribution robot converts the pixel coordinate information of each obstacle in the environment image into point cloud data matched with currently used map data;
and the distribution robot determines the positions of the obstacles in the map data according to the point cloud data corresponding to the obstacles obtained after conversion, and marks the positions in the map data.
Optionally, after the distribution robot marks the position of each obstacle in the map data, before the generated navigation path is updated in real time according to the map data marked with the position of each obstacle, the method further includes:
the distribution robot generates a thermal image corresponding to the environment image according to the position information of each obstacle in the environment image; wherein the thermal image is used to represent the distribution density of the obstacles in the environmental image;
the distribution robot determines the distribution state of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
the distribution robot updates the generated navigation path in real time according to the map data marked with the positions of the obstacles, and specifically includes:
and the distribution robot calls a path planning algorithm corresponding to the obstacle distribution state of the thermal image according to the determined obstacle distribution state of the thermal image, and updates the generated navigation path in real time according to the map data marked with the positions of the obstacles.
Optionally, the distribution robot determines the obstacle distribution state of the thermal image according to the pixel value of each pixel point in the thermal image, and specifically includes:
the distribution robot determines a target area with the maximum density of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
the distribution robot determines a difference value between a pixel value of a pixel point corresponding to the target area and a preset pixel value; if the difference value is not larger than a preset threshold value, determining that the obstacle distribution state of the thermal image is a dense state; the preset pixel value is a pixel value corresponding to a color feature which represents the maximum density of the obstacle in the thermodynamic diagram image.
Optionally, the distribution robot determines, according to the pixel value of each pixel point in the thermal image, a target area where the density of the obstacle in the thermal image is the maximum, and specifically includes:
and the distribution robot determines the difference value between the pixel value of each pixel point in the thermal image and a preset pixel value, and takes the position of the pixel point corresponding to the minimum difference value as the target area.
In a second aspect, an embodiment of the present application provides a robot-based distribution method, including:
when determining a distribution task to be executed, a master robot determines a distribution address corresponding to the distribution task to be executed;
the master robot determines a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution address and the position information of each distribution robot;
the main control robot sends a distribution instruction for executing a distribution task to a distribution robot executing the distribution task, and sends map data required by the distribution task to the distribution robot executing the distribution task, so that the distribution robot executing the distribution task can acquire an environment image of a distribution environment in real time through a camera in the process of executing the distribution task, mark the position of each obstacle in the map data, and update a navigation path in real time based on the map data marked with the position of each obstacle; the map data is generated by the main control robot in advance according to the collected environment data.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the master robot generates the map data according to the following modes:
responding to a control instruction triggered by a user, acquiring an environment image of an outdoor environment by the main control robot through a camera, and acquiring outdoor radar data of the outdoor environment through radar equipment; calling a SLAM algorithm to generate outdoor map data containing a plurality of buildings based on the collected environment image and the obtained outdoor radar data; and
the master robot respectively acquires indoor radar data inside each building through radar equipment; and calling a Cartogrer algorithm to respectively generate indoor map data corresponding to each building according to the indoor radar data in each building.
In a third aspect, an embodiment of the present application provides a delivery robot, where the delivery robot includes at least one processor, at least one camera, and an information transceiver unit;
the information receiving and sending unit is used for receiving a distribution instruction which is sent by the main control robot and used for executing a distribution task, and obtaining map data required for executing the distribution task from the main control robot; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task; the map data is generated by the main control robot in advance according to the collected environment data;
the camera is used for acquiring an environment image of a distribution environment in real time in the process of executing the distribution task according to the generated navigation path;
the processor is used for generating a navigation path according to the map data acquired by the information transceiving unit and the distribution address corresponding to the distribution task; after the camera collects the environment image, identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
In a fourth aspect, embodiments of the present application provide a robot-based delivery apparatus, including:
the receiving module is used for receiving a distribution instruction which is sent by the main control robot and used for executing a distribution task; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task;
the acquisition module is used for acquiring the map data required by executing the distribution task from the main control robot and generating a navigation path according to the acquired map data and the distribution address corresponding to the distribution task; the map data is generated by the main control robot in advance according to the collected environment data;
the processing module is used for acquiring an environment image of a distribution environment in real time through a camera in the process of executing the distribution task according to the generated navigation path and identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
and the generating module is used for updating the generated navigation path in real time according to the map data marked with the positions of the obstacles and distributing according to the updated navigation path.
In a fifth aspect, an embodiment of the present application provides a master robot, where the master robot includes at least one processor and a transceiver unit;
the processor is used for determining a delivery address corresponding to the delivery task to be executed when the delivery task to be executed is determined; determining a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution address and the position information of each distribution robot;
the receiving and sending unit is used for sending a distribution instruction for executing a distribution task to a distribution robot executing the distribution task, sending map data required by the distribution task to the distribution robot executing the distribution task, enabling the distribution robot executing the distribution task to acquire an environment image of a distribution environment in real time through a camera in the process of executing the distribution task, marking the position of each obstacle in the map data, and updating a navigation path in real time based on the map data marked with the position of each obstacle; the map data is generated by the master robot in advance according to the collected environment data.
In a sixth aspect, an embodiment of the present application provides a robot-based dispensing device, including:
the system comprises a determining module, a sending module and a sending module, wherein the determining module is used for determining a sending address corresponding to a sending task to be executed when the sending task to be executed is determined;
the selecting module is used for determining a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution address and the position information of each distribution robot;
the sending module is used for sending a distribution instruction for executing a distribution task to a distribution robot executing the distribution task, sending map data required by the distribution task to the distribution robot executing the distribution task, enabling the distribution robot executing the distribution task to acquire an environment image of a distribution environment in real time through a camera in the process of executing the distribution task, marking the position of each obstacle in the map data, and updating a navigation path in real time based on the map data marked with the position of each obstacle; the map data is generated by the main control robot in advance according to the collected environment data.
In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for performing the robot-based distribution method provided in the present application.
Because the robot-based distribution scheme of the embodiment of the application comprises the master control robot and the distribution robot, the master control robot generates map data in advance according to the collected environment data; after the distribution tasks to be executed are determined, the main control robot determines a distribution robot executing the distribution tasks according to the distribution addresses corresponding to the distribution tasks to be executed, and sends map data required by the execution of the distribution tasks to the distribution robot; according to the distribution scheme, the master robot is responsible for total distribution scheduling and map data generation in advance, for example, for the distribution scheme in the intelligent park, the master robot generates the map data of the park in advance for the whole intelligent park, so that the map data do not need to be generated temporarily in the distribution task process of the distribution robot, path planning only needs to be carried out according to the acquired map data, and distribution efficiency is effectively improved. In addition, during the process of executing the distribution task, the distribution robot acquires the environment image of the distribution environment in real time through the camera, identifies each obstacle in the distribution environment through identifying the environment image, and marks the position of each obstacle in the map data according to the position information of each obstacle in the environment image, so that the distribution robot can generate new map data according to the actual distribution environment, the new map data is marked with the obstacle existing in the current distribution environment, and the configuration robot can re-plan the navigation path based on the map data marked with the obstacle position, so that the navigation path is updated in real time along with the obstacle existing in the distribution environment, and the distribution accuracy can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments of the present invention will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of an optional application scenario in an embodiment of the present application;
fig. 2 is a schematic structural diagram of a master robot according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a dispensing robot according to an embodiment of the present disclosure;
FIG. 4 is a flowchart of a robot-based distribution method according to an embodiment of the present disclosure;
fig. 5 is a schematic storage structure diagram of indoor map data of n buildings generated according to an embodiment of the present application;
FIG. 6A is a schematic view of a building n according to an embodiment of the present application;
fig. 6B is indoor map data corresponding to floor 1 of building n according to the embodiment of the present application;
fig. 6C is indoor map data corresponding to floor 2 of building n according to the embodiment of the present application;
fig. 6D is indoor map data corresponding to floor 3 of building n according to the embodiment of the present application;
fig. 7 is a flowchart of a method for updating map data by a distribution robot according to an embodiment of the present application;
FIG. 8 is a flowchart illustrating an overall method for robot-based distribution according to an embodiment of the present disclosure;
FIG. 9 is a schematic structural diagram of a dispensing robot according to an embodiment of the present disclosure;
FIG. 10 is a schematic view of a robot-based dispensing apparatus according to an embodiment of the present disclosure;
fig. 11 is a schematic structural diagram of a master robot according to an embodiment of the present application;
fig. 12 is a schematic view of another robot-based dispensing apparatus according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, some terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.
1. The term "RGBD" in the embodiments of the present application: RGBD includes RGB maps and Depth maps; the RGB color scheme is a color standard in the industry, and various colors are obtained by changing three color channels of red (R), green (G) and blue (B) and superimposing the three color channels on each other, where RGB represents colors of the three channels of red, green and blue, and the color standard almost includes all colors that can be perceived by human vision, and is one of the most widely used color systems at present. In 3D computer graphics, a Depth Map is an image or image channel containing information about the distance of the surface of a scene object of a viewpoint; where the Depth Map is similar to a grayscale image except that each pixel value thereof is the actual distance of the sensor from the object. Usually, the RGB image and the Depth image are registered, so that there is a one-to-one correspondence between pixel points.
2. The term "radar" in the embodiments of the present application: is the transliteration of radio, derived from the acronym radio detection and ranging, and means radio detection and ranging, i.e. finding objects and determining their spatial position by radio, and thus Radar is also called "radiolocation". The radar is an electronic device for detecting a target by using an electromagnetic wave, and the radar emits the electromagnetic wave to irradiate the target and receives an echo of the electromagnetic wave, so that information such as a distance from the target to an electromagnetic wave emission point, a distance change rate (radial speed), an azimuth, and an altitude is obtained.
3. The term "IMU (Inertial Measurement Unit)" in the embodiments of the present application: for measuring the three-axis attitude angle (or angular velocity) and acceleration of the object. The gyroscope and the accelerometer are main elements of the IMU, the accelerometer detects acceleration signals of the object on three independent axes of a carrier coordinate system, the gyroscope detects angular velocity signals of the carrier relative to a navigation coordinate system, the angular velocity and the acceleration of the object in a three-dimensional space are measured, and the posture of the object is calculated according to the angular velocity and the acceleration.
4. The term "SLAM (Simultaneous Localization and Mapping) algorithm" in the embodiments of the present application: SLAM is mainly used for solving the problems of positioning navigation and map construction when the mobile robot runs in an unknown environment; SLAM typically includes several components, feature extraction, data association, state estimation, state update, and feature update.
5. The term "thermodynamic diagram" in the embodiments of the present application: heat maps (also known as thermodynamic maps) are graphical representations of a user's page click position or the position of the user's page in a particularly highlighted form; in the thermodynamic diagram, a red area indicates that the density of analysis elements is high, and a blue area indicates that the density of analysis points is low, and a cluster area is formed as long as the points are dense.
In order to make the purpose, technical solution and beneficial effects of the present application more clear and more obvious, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be implemented in sequences other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The following briefly introduces the design concept of the embodiments of the present application:
an intelligent park can be understood as an intelligent park which gathers a plurality of buildings (office buildings), and the intelligent park comprises a plurality of buildings and facilities such as roads, green areas, parking areas and the like among the buildings. Because the intelligence garden generally is comparatively confined office space, if adopt the conventionality drive the delivery vehicle by the delivery personnel and carry out the article delivery in the garden, there may be the potential safety hazard. In addition, with the maturity of artificial intelligence technology, intelligent robots play a tremendous role in various fields, so an alternative way is to use robots to deliver items in an intelligent park. When a robot is used to deliver an article, how the robot plans a navigation path is a technical problem to be solved.
The embodiment of the application provides a robot-based distribution method, in the method, a main control robot issues a distribution instruction, and a distribution robot completes distribution; in the embodiment of the application, when the main control robot determines the distribution tasks to be executed, the main control robot determines the distribution addresses corresponding to the distribution tasks to be executed; the main control robot determines a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots; and the main control robot sends a distribution instruction for executing the distribution task to the distribution robot executing the distribution task, and sends the map data required by the distribution task to the distribution robot executing the distribution task. After the distribution robot acquires the map data required by executing the distribution task from the main control robot, a navigation path is generated according to the acquired map data and the distribution address corresponding to the distribution task; in the process of executing a distribution task according to the generated navigation path, acquiring an environment image of a distribution environment in real time through a camera, and identifying each barrier in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
Because the robot-based distribution scheme of the embodiment of the application comprises the master control robot and the distribution robot, the master control robot generates map data in advance according to the collected environment data; after the distribution tasks to be executed are determined, the main control robot determines a distribution robot executing the distribution tasks according to the distribution addresses corresponding to the distribution tasks to be executed, and sends map data required by the execution of the distribution tasks to the distribution robot; according to the distribution scheme, the master robot is responsible for total distribution scheduling and map data generation in advance, for example, for the distribution scheme in the intelligent park, the master robot generates the map data of the park in advance for the whole intelligent park, so that the map data do not need to be generated temporarily in the distribution task process of the distribution robot, path planning only needs to be carried out according to the acquired map data, and distribution efficiency is effectively improved. In addition, during the process of executing the distribution task, the distribution robot acquires the environment image of the distribution environment in real time through the camera, identifies each obstacle in the distribution environment through identifying the environment image, and marks the position of each obstacle in the map data according to the position information of each obstacle in the environment image, so that the distribution robot can generate new map data according to the actual distribution environment, the new map data is marked with the obstacle existing in the current distribution environment, and the configuration robot can re-plan the navigation path based on the map data marked with the obstacle position, so that the navigation path is updated in real time along with the obstacle existing in the distribution environment, and the distribution accuracy can be greatly improved.
After introducing the design concept of the embodiment of the present application, some simple descriptions are provided below for application scenarios to which the technical solution of the embodiment of the present application can be applied, and it should be noted that the application scenarios described below are only used for describing the embodiment of the present application and are not limited. In the specific implementation process, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.
Fig. 1 is a schematic diagram of an alternative application scenario of the embodiment of the present application, which includes a master robot 10 and a plurality of delivery robots 11;
when determining a distribution task to be executed, the master robot 10 determines a distribution address corresponding to the distribution task to be executed; determining a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots; sending a distribution instruction for executing the distribution task to a distribution robot executing the distribution task, and sending map data required by the distribution task to the distribution robot executing the distribution task;
the distribution robot 11 executing the current distribution task receives a distribution instruction for executing the distribution task sent by the master robot 10; obtaining map data required for executing the distribution task from the master robot 10, and generating a navigation path according to the obtained map data and a distribution address corresponding to the distribution task; in the process of executing a distribution task according to the generated navigation path, acquiring an environment image of a distribution environment in real time through a camera, and identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
For example, the master robot shown in fig. 2 includes a processor 20, an edge calculation unit 21, two RGBD cameras 22, two radar devices 23, four ultrasonic ranging sensors 24, an environment sensing unit 25, and an information transceiving unit 26;
the processor 20, the edge calculating unit 21 and the information transceiving unit 26 are arranged on the inner side of the robot body, the two RGBD cameras 22 are respectively positioned on the front side of the main control robot body, the two radar devices 23 are arranged on the top of the main control robot chassis, the four ultrasonic ranging sensors 24 are respectively arranged at four corners of the main control robot chassis, and the environment sensing unit 25 is arranged below the radar devices 23; the main control robot of the embodiment of the application is provided with the ROS operating system.
The dispensing robot shown in fig. 3 comprises a processor 30, an edge calculating unit 31, an RGBD camera 32, a radar device 33, two ultrasonic ranging sensors 34, an environment sensing unit 35, and an information transceiving unit 36;
the processor 30, the edge calculating unit 31 and the information transceiving unit 36 are arranged on the inner side of the robot body, the RGBD camera 32 is located on the front side of the main robot body, the radar device 33 is installed on the top of the chassis of the distribution robot, the two ultrasonic ranging sensors 24 are respectively installed on the chassis of the distribution robot, and the environment sensing unit 35 is installed below the radar device 33.
In the following, a robot-based distribution method provided by an exemplary embodiment of the present application is described with reference to the following drawings in conjunction with the application scenarios described above. It should be noted that the above application scenarios are only presented to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
As shown in fig. 4, a flowchart of a robot-based distribution method in the embodiment of the present application may specifically include the following steps:
step S401, when the main control robot determines the distribution tasks to be executed, determining the distribution addresses corresponding to the distribution tasks to be executed;
step S402, the main control robot determines a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots;
step S403, the main control robot sends a distribution instruction for executing the distribution task to the distribution robot executing the distribution task, and sends the map data required by the distribution task to the distribution robot executing the distribution task;
step S404, the distribution robot generates a navigation path according to the acquired map data and a distribution address corresponding to the distribution task;
s405, the distribution robot collects an environment image of a distribution environment in real time through a camera in the process of executing a distribution task according to the generated navigation path, and identifies each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
step S406, the distribution robot updates the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributes the navigation path according to the updated navigation path.
The main control robot can be used for generating map data, the distribution robot obtains the map data needed by executing distribution tasks from the main control robot, a navigation path is generated based on the obtained map data, and distribution is carried out based on the generated navigation path. Therefore, the present embodiment relates to a scheme in which the master robot generates map data and a scheme in which the delivery robot executes a delivery task, and the following describes each of these two parts.
Firstly, the master robot generates map data.
The map data according to the embodiment of the present application includes outdoor map data and indoor map data of each building, and the following describes the generation methods of these two types of map data.
1. The master robot generates outdoor map data.
In an optional implementation manner, in response to a control instruction triggered by a user, the master robot acquires an environment image of the outdoor environment through the camera, and acquires outdoor radar data of the outdoor environment through the radar equipment; and calling an SLAM algorithm to generate outdoor map data containing a plurality of buildings based on the acquired environment images and the acquired outdoor radar data.
In implementation, a user can operate the master robot to traverse the whole area needing to be distributed by the distribution robot, so that the master robot can obtain the environment image and the outdoor radar data of the whole outdoor environment;
the master robot can acquire an environment image of an outdoor environment through the RGBD camera, acquire outdoor radar data of the outdoor environment through the radar equipment, combine the environment image acquired by the RGBD camera with the outdoor radar data, and generate outdoor map data containing a plurality of buildings based on an SLAM algorithm.
2. The master robot generates indoor map data.
In an optional implementation manner, the master robot respectively acquires indoor radar data inside each building through radar equipment; and calling a Cartographer algorithm to respectively generate indoor map data corresponding to each building according to the indoor radar data in each building.
In implementation, aiming at any building, the master robot acquires indoor radar data in the building through radar equipment; the indoor radar data inside the building can be indoor radar data of each floor of the building. After the master robot acquires indoor radar data inside the building, indoor map data corresponding to the building are generated based on a Cartogrer algorithm.
In addition, after the indoor map data and the outdoor map data are generated in the embodiment of the application, the storage order of the map data may be that the outdoor map data is taken as subgraph 0, each building in the indoor map data corresponds to one subgraph, assuming that the buildings are buildings 1 to n, the indoor map data corresponding to the building 1 is taken as subgraph 1, and so on, and the indoor map data corresponding to the building n is taken as subgraph n.
It should be noted that, in the embodiment of the present application, when storing the indoor map data, the master robot binds the indoor map data of the building with the corresponding building identification information; the indoor map data corresponding to one building comprises indoor map data corresponding to each floor, and the indoor map data of each floor in the building is bound with the identification information of the floor.
In implementation, the indoor map data of different buildings can be stored according to different building categories. For example, the building a includes 10 floors, each floor corresponds to one piece of sub-indoor map data, the sub-indoor map data corresponding to each of the 10 floors is used as the indoor map data corresponding to the building a, and a binding relationship between the building a and the indoor map data is established.
For example, as shown in fig. 5, it is assumed that a master robot generates indoor map data of n buildings, the indoor map data corresponding to the building 1 is sub-graph 1, the sub-graph 1 includes indoor map data corresponding to each floor in the building 1, and the sub-graph 1 is bound with two-dimensional code information of the building 1; the indoor map data corresponding to the building 2 is sub-graph 2, the sub-graph 2 comprises indoor map data corresponding to each floor in the building 2, and the sub-graph 2 is bound with the two-dimensional code information of the building 2; and analogizing in sequence, the indoor map data corresponding to the building n is a subgraph n, the subgraph n comprises the indoor map data corresponding to each floor in the building n, and the subgraph n is bound with the two-dimensional code information of the building n.
As shown in fig. 6A, assuming that a building n includes three floors, indoor map data corresponding to the building n includes indoor map data corresponding to a floor 1, indoor map data corresponding to a floor 2, and indoor map data corresponding to a floor 3; it is assumed that the indoor map data corresponding to the floor 1 is shown in fig. 6B, the indoor map data corresponding to the floor 2 is shown in fig. 6C, and the indoor map data corresponding to the floor 3 is shown in fig. 6D. The indoor map data corresponding to the building n includes the map data shown in fig. 6B, 6C, and 6D.
And secondly, generating a navigation path by the delivery robot based on the map data, and delivering according to the generated navigation path.
When determining the distribution tasks to be executed, the main control robot determines the distribution addresses corresponding to the distribution tasks to be executed; determining a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots;
in implementation, an optional implementation manner is that when the master robot determines a distribution task to be executed, the master robot may obtain location information of each distribution robot through a GPS; after the position information of each distribution robot is determined, the distribution robot closest to the distribution address is selected from the plurality of distribution robots based on the shortest path principle to execute the distribution task.
After the main control robot determines the distribution robot executing the distribution task, the main control robot can send the map data required by the distribution task to the distribution robot executing the distribution task in various ways;
in the method 1, the main control robot transmits a distribution instruction for executing the distribution task to the distribution robot executing the distribution task, and simultaneously transmits all the map data required for the distribution task to the distribution robot executing the distribution task.
All the map data required for the current distribution task include, but are not limited to, outdoor map data and indoor map data of a building corresponding to the distribution address;
the indoor map data of the building corresponding to the delivery address may be indoor map data of all floors of the building, or the indoor map data of the building corresponding to the delivery address may be indoor map data of a floor where the delivery address is located in the building.
In the mode 2, the main control robot sends outdoor map data required by the current distribution task to a distribution robot executing the current distribution task; and after receiving the building identification information transmitted by the distribution robot executing the current distribution task, transmitting the indoor map data of the building corresponding to the building identification information to the distribution robot executing the current distribution task.
According to the mode 2, the main control robot sends outdoor map data required by the current distribution task to the distribution robot executing the current distribution task, and the distribution robot generates an outdoor navigation path according to the outdoor map data and the distribution address;
the distribution robot acquires building identification information of a building after driving to the building corresponding to the distribution address according to the outdoor navigation path; one optional mode is that two-dimension code information can be pasted at an entrance of a building, and after a distribution robot runs at the entrance of the building, building identification information is obtained in a mode of scanning the two-dimension code information;
the distribution robot sends the obtained building identification information to the main control robot, the main control robot obtains indoor map data corresponding to the building identification information from map data generated in advance, and the indoor map data corresponding to the building identification information is sent to the distribution robot.
After receiving the map data sent by the master control robot, the distribution robot stores the received map data according to the following steps:
step 2, importing the received map data into a new map container;
and 3, aiming at the received map data, executing the launch file of the map-ID to be switched, thereby switching the navigation map data.
After acquiring the map data required for executing the distribution tasks, the distribution robot drives outdoors according to outdoor map data in the map data; when the mobile terminal drives to a building, indoor map data corresponding to the building are obtained by scanning two-dimensional code information at an entrance of the building; in addition, after the elevator runs to a floor, the elevator runs to an elevator entrance according to the indoor map data corresponding to the floor, and the indoor map data corresponding to the floor are obtained by scanning the two-dimensional code information at the elevator entrance.
In addition, after scanning the two-dimensional code information at the entrance of the building or the two-dimensional code information of each floor, the distribution robot calibrates the position of the distribution robot according to the position information corresponding to the preset two-dimensional code information.
After receiving the map data sent by the master robot, the distribution robot generates a navigation path according to the received map data and a distribution address, and the distribution robot runs based on the generated navigation path;
the method comprises the following steps that in the process that a distribution robot executes distribution based on a generated navigation path, an environment image of a distribution environment is collected in real time through a camera, and each obstacle in the environment image is identified; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
in implementation, the embodiment of the present application may mark the position of each obstacle in the map data according to the following manner:
as shown in fig. 7, a flowchart of a method for marking a position of each obstacle in map data according to an embodiment of the present application may specifically include the following steps:
step S701, the distribution robot collects an environment image in a distribution environment in real time through a camera in the process of executing a distribution task according to the generated navigation path;
the distribution robot can acquire a depth image of a distribution environment through the RGBD camera.
Step S702, identifying each obstacle in the environment image by the delivery robot based on the trained target detection model;
in implementation, the trained target detection model of the embodiment of the present application may be a YOLOV3 model; the distribution robot inputs the collected environment images into a trained Yolov3 model, performs target detection on the environment images based on the Yolov3 model, and identifies obstacles in the environment images;
obstacles in the embodiments of the present application include, but are not limited to, people, vehicles, articles;
the YOLOV3 model may mark obstacles in the environment image in the form of rectangular boxes when identifying the environment image.
Step S703, the distribution robot determines the pixel coordinate information of each identified obstacle in the environment image, and converts the pixel coordinate information of each obstacle in the environment image into point cloud data matched with the currently used map data;
in implementation, a pixel coordinate system is established according to the position of the current distribution robot, and the pixel coordinate information of each obstacle is determined respectively by identifying the left and right offset and the depth offset of the obstacle relative to the distribution robot.
After recognizing each obstacle in the environment image, the distribution robot respectively determines the pixel coordinate information of each obstacle in the environment image;
in addition, when the map data is generated, the map data is generated based on the three-dimensional point cloud data; therefore, when the identified obstacle needs to be updated to the map data, the pixel coordinate information of the obstacle in the environment image needs to be converted into point cloud data.
Step S704, the distribution robot determines the positions of the obstacles in the map data according to the point cloud data corresponding to the obstacles obtained after conversion, and marks the obstacles in the map data;
according to the embodiment of the application, when the Map data is updated according to the positions of all obstacles in the Map data, the generated point cloud data has semantic information, the point cloud data containing the semantic information can be used as a Grid Map at the current moment, and the point cloud data with the semantic information participates in a Global SLAM link in a Cartographer algorithm, so that the positions of all obstacles are marked in the Map data.
After the distribution robot marks the positions of all obstacles in the map data, generating a thermal image corresponding to an environment image; wherein the thermal image is used to represent the distribution density of various obstacles in the environmental image.
In implementation, after each obstacle in the environment image is detected, the coordinate information of the center position of each obstacle is stored;
for example, coordinate information of the center position of each obstacle can be stored in a list type variable data; that is, data ═ x1, y1, (x2, y2) … … ], where (xi, yi) represents coordinate information of the center position of the obstacle in the environment image.
Presetting a thermal gradient r when a thermal image corresponding to the environment image is generated; taking the center position of the obstacle as the center, taking the thermal gradient r as the detection radius, and if the two detection areas are crossed, superposing the heat of the crossed areas;
in implementation, thermodynamic diagram rendering is performed based on a HeatMap function in Opencv, so that a thermodynamic image corresponding to the environment image is generated.
The method comprises the steps that if an obstacle in an environment image collected by a distribution robot is a person, the distribution robot detects the person in the environment image to generate a thermal image; the color in the thermodynamic image mainly represents the crowd density represented by the pixel points, and the color depth in the thermodynamic diagram is in direct proportion to the crowd density.
After the distribution robot generates the thermodynamic diagram, determining the obstacle distribution state of the thermodynamic image according to the pixel values of all pixel points in the thermodynamic image; wherein, the obstacle distribution state of the thermal image comprises a dense state and a sparse state;
specifically, the distribution robot determines a target area with the maximum density of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
wherein the target area is a position where the density of the obstacles in the thermal image is the maximum.
In implementation, the distribution robot determines a difference value between a pixel value of each pixel point in the thermal image and a preset pixel value, and the position of the pixel point corresponding to the minimum difference value is used as a target area.
Because the red area in the thermal image represents the area with the maximum obstacle density, the preset pixel value can be set as the pixel value corresponding to the red pixel point; in implementation, the pixel value of each pixel point in the thermal image is subtracted from the pixel value corresponding to the red pixel point, and the pixel point with the minimum difference value is determined, namely the pixel point which is close to red is determined;
for example, the pixel value of a pixel point in a thermal image is represented by (R)(i,j),G(i,j),B(i,j)) The pixel value corresponding to the red pixel point is (255, 0, 0);
A(i,j)=[255,0,0]-[R(i,j),G(i,j),B(i,j)]=[255-R(i,j),-G(i,j),-B(i,j)];
wherein A is(i,j)And the difference value between the pixel value of the pixel point in the thermal image and the pixel value corresponding to the red pixel point is represented, and i and j are the serial numbers of the horizontal and vertical coordinates of the pixel point in the thermal image.
To A(i,j)The absolute values of the three elements are summed to obtain K(i,j);
K(i,j)=|255-R(i,j)|+|-G(i,j)|+|-B(i,j)|;
A plurality of K obtained from calculation(i,j)Selecting the minimum value, K(i,j)And the corresponding i and j are the positions of the pixel points corresponding to the minimum difference.
After the distribution robot determines a target area with the maximum density of the obstacles in the thermal image, the distribution robot determines a difference value between a pixel value of a pixel point corresponding to the target area and a preset pixel value; and if the difference is not greater than the preset threshold, determining that the obstacle distribution state of the thermal image is a dense state, otherwise, determining that the obstacle distribution state of the thermal image is a sparse state.
According to the distribution state of the obstacles of the thermal image, the distribution robot calls a path planning algorithm corresponding to the distribution state of the obstacles of the thermal image, and generates a navigation path according to the updated map data and the distribution address corresponding to the distribution task.
In implementation, if the distribution state of the obstacles is a dense state, calling a D-star algorithm, and generating a navigation path according to the updated map data and the distribution address corresponding to the distribution task; and if the distribution state of the obstacles is a sparse state, calling an A-star algorithm, and generating a navigation path according to the updated map data and the distribution address corresponding to the distribution task.
As shown in fig. 8, the overall flowchart of the robot-based distribution method in the embodiment of the present application may specifically include the following steps:
step S801, responding to a control instruction triggered by a user, acquiring an environment image of an outdoor environment through a camera by a main control robot, and acquiring outdoor radar data of the outdoor environment through radar equipment;
s802, calling an SLAM algorithm by the main control robot to generate outdoor map data containing a plurality of buildings based on the collected environment image and the obtained outdoor radar data;
step S803, the master robot respectively acquires indoor radar data inside each building through radar equipment;
step S804, the main control robot calls a Cartogrer algorithm to respectively generate indoor map data corresponding to each building according to indoor radar data inside each building;
it should be noted that, the sequence of the steps executed between the step of constructing the outdoor map data by the master robot in the steps S801 and S802 and the step of constructing the indoor map data by the master robot in the steps S803 and S804 is not limited;
step S805, when determining a distribution task to be executed, the master robot determines a distribution address corresponding to the distribution task to be executed;
step 806, the main control robot determines a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots;
step S807, the main control robot sends a distribution instruction for executing the distribution task to the distribution robot executing the distribution task;
step S808, the distribution robot acquires map data required for executing the distribution task from the master control robot;
step S809, the distribution robot generates a navigation path according to the acquired map data and a distribution address corresponding to the distribution task;
step S810, in the process that the distribution robot executes the distribution task according to the generated navigation path, the environment image of the distribution environment is collected in real time through a camera, and each obstacle in the environment image is identified;
step S811, the distribution robot determines the pixel coordinate information of each identified obstacle in the environment image, and converts the pixel coordinate information of each obstacle in the environment image into point cloud data matched with the currently used map data;
step S812, the distribution robot determines the positions of the obstacles in the map data according to the point cloud data corresponding to the obstacles obtained after conversion, and marks the obstacles in the map data;
step S813, generating a thermal image corresponding to the environment image by the distribution robot according to the position of each obstacle in the environment image;
step S814, determining the obstacle distribution state of the thermal image by the distribution robot according to the pixel value of each pixel point in the thermal image;
step S815, the distribution robot calls a path planning algorithm corresponding to the obstacle distribution state of the thermal image according to the determined obstacle distribution state of the thermal image, and updates the generated navigation path in real time according to the map data marked with the positions of the obstacles;
and step S816, the distribution robot carries out distribution according to the updated navigation path.
Based on the same inventive concept, as shown in fig. 9, an embodiment of the present application provides a distribution robot 900, which includes at least one processor 901, at least one camera 902, and an information transceiver unit 903;
the information transceiver 903 is configured to receive a distribution instruction sent by a master robot to execute a distribution task, and acquire map data required to execute the distribution task from the master robot; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task; the map data is generated by the master robot in advance according to the collected environmental data;
the camera 902 is used for acquiring an environment image of a distribution environment in real time in the process of executing the distribution task according to the generated navigation path;
a processor 901, configured to generate a navigation path according to the map data acquired by the information transceiver and the delivery address corresponding to the delivery task; after the camera collects the environment image, identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the processor 901 is specifically configured to:
receiving outdoor map data sent by the master robot and indoor map data of a building corresponding to the distribution address through an information transceiving unit 903; or
Receiving outdoor map data sent by the master robot through an information receiving and sending unit 903; after the distribution robot moves to the building corresponding to the distribution address according to the outdoor map data and the distribution address, acquiring identification information corresponding to the building; the identification information of the building is sent to the master robot through the information transceiver unit 903, and the indoor map data of the building returned by the master robot is received through the information transceiver unit 903.
Optionally, the position information of each obstacle in the environment image is pixel coordinate information of each obstacle in the environment image;
the processor 901 is specifically configured to: converting the pixel coordinate information of each obstacle in the environment image into point cloud data matched with currently used map data; and determining the position of each obstacle in the map data according to the point cloud data corresponding to each obstacle obtained after conversion, and marking in the map data.
Optionally, the processor 901 is further configured to: after the positions of the obstacles are marked in the map data, generating a thermal image corresponding to the environment image according to the position information of the obstacles in the environment image before the generated navigation path is updated in real time according to the map data marked with the positions of the obstacles; wherein the thermal image is used to represent the distribution density of the obstacles in the environmental image; determining the obstacle distribution state of the thermal image according to the pixel value of each pixel point in the thermal image;
the processor 901 is specifically configured to:
and calling a path planning algorithm corresponding to the obstacle distribution state of the thermal image according to the determined obstacle distribution state of the thermal image, and updating the generated navigation path in real time according to the map data marked with the positions of all the obstacles.
Optionally, the processor 901 is specifically configured to:
determining a target area with the maximum density of obstacles in the thermal image according to the pixel value of each pixel point in the thermal image; determining a difference value between a pixel value of a pixel point corresponding to the target area and a preset pixel value; if the difference value is not larger than a preset threshold value, determining that the obstacle distribution state of the thermal image is a dense state; the preset pixel value is a pixel value corresponding to a color feature which represents the maximum density of the obstacle in the thermodynamic diagram image.
Optionally, the processor 901 is specifically configured to:
and determining a difference value between the pixel value of each pixel point in the thermal image and a preset pixel value, and taking the position of the pixel point corresponding to the minimum difference value as the target area.
As shown in fig. 10, a robot-based dispensing apparatus 1000 according to an embodiment of the present application includes:
a receiving module 1001, configured to receive a distribution instruction for executing a distribution task sent by a master robot; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task;
an obtaining module 1002, configured to obtain, from the master robot, map data required to execute the distribution task of this time, and generate a navigation path according to the obtained map data and a distribution address corresponding to the distribution task; the map data is generated by the main control robot in advance according to the collected environment data;
the processing module 1003 is configured to acquire an environment image of a distribution environment in real time through a camera and identify each obstacle in the environment image in the process of executing the distribution task according to the generated navigation path; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
the generating module 1004 is configured to update the generated navigation path in real time according to the map data marked with the positions of the obstacles, and deliver the navigation path according to the updated navigation path.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the obtaining module 1002 is specifically configured to:
receiving outdoor map data sent by the main control robot and indoor map data of a building corresponding to the distribution address; or
Receiving outdoor map data sent by the master robot; after the distribution robot moves to the building corresponding to the distribution address according to the outdoor map data and the distribution address, acquiring identification information corresponding to the building; and sending the identification information of the building to the master robot, and receiving indoor map data of the building returned by the master robot.
Optionally, the position information of each obstacle in the environment image is pixel coordinate information of each obstacle in the environment image;
the processing module 1003 is specifically configured to:
converting the pixel coordinate information of each obstacle in the environment image into point cloud data matched with currently used map data;
and determining the position of each obstacle in the map data according to the point cloud data corresponding to each obstacle obtained after conversion, and marking in the map data.
Optionally, after the processing module 1003 marks the position of each obstacle in the map data, before the generating module 1004 updates the generated navigation path in real time according to the map data marked with the position of each obstacle, the generating module 1004 is further configured to:
generating a thermal image corresponding to the environment image according to the position information of each obstacle in the environment image; wherein the thermal image is used to represent the distribution density of the obstacles in the environmental image;
determining the distribution state of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
the generating module 1004 is specifically configured to:
and calling a path planning algorithm corresponding to the obstacle distribution state of the thermal image according to the determined obstacle distribution state of the thermal image, and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles.
Optionally, the generating module 1004 is specifically configured to:
determining a target area with the maximum density of obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
determining a difference value between a pixel value of a pixel point corresponding to the target area and a preset pixel value; if the difference value is not larger than a preset threshold value, determining that the obstacle distribution state of the thermal image is a dense state; the preset pixel value is a pixel value corresponding to a color feature which represents the maximum density of the obstacle in the thermodynamic diagram image.
Optionally, the generating module 1004 is specifically configured to:
and determining a difference value between the pixel value of each pixel point in the thermal image and a preset pixel value, and taking the position of the pixel point corresponding to the minimum difference value as the target area.
Based on the same inventive concept, as shown in fig. 11, an embodiment of the present application provides a master robot 1100, which includes at least one processor 1101, an information transceiving unit 1102;
a processor 1101, configured to determine a delivery address corresponding to a delivery task to be executed when determining the delivery task to be executed; determining a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution address and the position information of each distribution robot;
an information transceiver unit 1102, configured to send a distribution instruction for executing a distribution task to a distribution robot that executes the distribution task, and send map data required by the distribution task to the distribution robot that executes the distribution task, so that the distribution robot that executes the distribution task acquires an environment image of a distribution environment in real time through a camera in a process of executing the distribution task, marks positions of the obstacles in the map data, and updates a navigation path in real time based on the map data marked with the positions of the obstacles; the map data is generated by the main control robot in advance according to the collected environment data.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the master robot 1100 further comprises a camera 1103 and a radar device 1104;
the camera 1103 is used for responding to a control instruction triggered by a user and acquiring an environment image of an outdoor environment through image acquisition equipment;
a radar device 1104 for acquiring outdoor radar data of an outdoor environment and acquiring indoor radar data of the inside of each building;
the processor 1101 is specifically configured to generate the map data according to the following manner:
calling a SLAM algorithm to generate outdoor map data containing a plurality of buildings based on the collected environment image and the obtained outdoor radar data; and calling a Cartogrer algorithm to respectively generate indoor map data corresponding to each building according to the indoor radar data in each building.
As shown in fig. 12, an embodiment of the present application provides a robot-based dispenser 1200, including:
a determining module 1201, configured to determine, when determining a delivery task to be executed, a delivery address corresponding to the delivery task to be executed;
a selecting module 1202, configured to determine, according to the distribution address and the location information of each distribution robot, a distribution robot that executes the distribution task from the multiple distribution robots;
a sending module 1203, configured to send a distribution instruction for executing a distribution task to a distribution robot that executes the distribution task, and send map data required by the distribution task to the distribution robot that executes the distribution task, so that the distribution robot that executes the distribution task obtains an environment image of a distribution environment in real time through a camera in a process of executing the distribution task, marks positions of the obstacles in the map data, and updates a navigation path in real time based on the map data marked with the positions of the obstacles; the map data is generated by the master robot in advance according to the collected environment data.
Optionally, the map data includes outdoor map data and indoor map data of each building;
the robot-based delivery apparatus 1200 further comprises a generation module 1204;
the generating module 1204 is specifically configured to generate the map data according to the following ways:
responding to a control instruction triggered by a user, acquiring an environment image of the outdoor environment through a camera, and acquiring outdoor radar data of the outdoor environment through radar equipment; calling an SLAM algorithm to generate outdoor map data containing a plurality of buildings based on the acquired environment image and the acquired outdoor radar data; and
respectively acquiring indoor radar data inside each building through radar equipment; and calling a Cartogrer algorithm to respectively generate indoor map data corresponding to each building according to the indoor radar data in each building.
As will be appreciated by one skilled in the art, each aspect of the present application may be embodied as a system, method or program product. Accordingly, each aspect of the present application may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
In some possible embodiments, each aspect of the robot-based distribution method provided by the present application may also be implemented in the form of a program product comprising program code for causing a computer device to perform the steps of the robot-based distribution method according to various exemplary embodiments of the present application described above in this specification when the program product is run on the computer device, for example, the computer device may perform the steps as shown in fig. 4 or fig. 7 or fig. 8.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A robot-based distribution method, the method comprising:
the distribution robot receives a distribution instruction which is sent by the main control robot and used for executing a distribution task; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task;
the distribution robot acquires map data required for executing the distribution task from the main control robot, and generates a navigation path according to the acquired map data and a distribution address corresponding to the distribution task; the map data is generated by the main control robot in advance according to the collected environment data;
the distribution robot acquires an environment image of a distribution environment in real time through a camera in the process of executing the distribution task according to the generated navigation path, and identifies each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image;
and the distribution robot updates the generated navigation path in real time according to the map data marked with the positions of the obstacles and distributes according to the updated navigation path.
2. The method of claim 1, wherein the map data includes outdoor map data and indoor map data of respective buildings;
the distribution robot obtains the map data required for executing the distribution task from the master robot, and the method specifically comprises the following steps:
the distribution robot receives outdoor map data sent by the main control robot and indoor map data of a building corresponding to the distribution address; or
The distribution robot receives outdoor map data sent by the master robot; after the distribution robot moves to the building corresponding to the distribution address according to the outdoor map data and the distribution address, acquiring identification information corresponding to the building; and sending the identification information of the building to the master robot, and receiving indoor map data of the building returned by the master robot.
3. The method according to claim 1, wherein the position information of each obstacle in the environment image is pixel coordinate information of each obstacle in the environment image;
the marking, in the map data, the position of each obstacle according to the position information of each obstacle in the environment image specifically includes:
the distribution robot converts the pixel coordinate information of each obstacle in the environment image into point cloud data matched with currently used map data;
and the distribution robot determines the positions of the obstacles in the map data according to the point cloud data corresponding to the obstacles obtained after conversion, and marks the obstacles in the map data.
4. The method as set forth in claim 3, wherein after the distribution robot marks the positions of the respective obstacles in the map data, the method further comprises, before the generated navigation path is updated in real time based on the map data marked with the positions of the respective obstacles:
the distribution robot generates a thermal image corresponding to the environment image according to the position information of each obstacle in the environment image; wherein the thermal image is used to represent the distribution density of the respective obstacles in the environmental image;
the distribution robot determines the distribution state of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
the distribution robot updates the generated navigation path in real time according to the map data marked with the positions of the obstacles, and specifically includes:
and the distribution robot calls a path planning algorithm corresponding to the obstacle distribution state of the thermal image according to the determined obstacle distribution state of the thermal image, and updates the generated navigation path in real time according to the map data marked with the positions of all the obstacles.
5. The method according to claim 4, wherein the determining, by the distribution robot, the obstacle distribution state of the thermal image according to the pixel values of the respective pixel points in the thermal image specifically comprises:
the distribution robot determines a target area with the maximum density of the obstacles in the thermal image according to the pixel value of each pixel point in the thermal image;
the distribution robot determines a difference value between a pixel value of a pixel point corresponding to the target area and a preset pixel value; if the difference value is not larger than a preset threshold value, determining that the obstacle distribution state of the thermal image is a dense state; the preset pixel value is a pixel value corresponding to a color feature which represents the maximum density of the obstacle in the thermodynamic diagram image.
6. The method according to claim 5, wherein the determining, by the distribution robot, the target area with the maximum density of the obstacles in the thermal image according to the pixel values of the respective pixel points in the thermal image specifically comprises:
and the distribution robot determines the difference value between the pixel value of each pixel point in the thermal image and a preset pixel value, and takes the position of the pixel point corresponding to the minimum difference value as the target area.
7. A robot-based distribution method, the method comprising:
when determining a distribution task to be executed, a master robot determines a distribution address corresponding to the distribution task to be executed;
the main control robot determines a distribution robot executing the distribution task from the plurality of distribution robots according to the distribution address and the position information of each distribution robot;
the main control robot sends a distribution instruction for executing a distribution task to a distribution robot executing the distribution task, and sends map data required by the distribution task to the distribution robot executing the distribution task, so that the distribution robot executing the distribution task can acquire an environment image of a distribution environment in real time through a camera in the process of executing the distribution task, mark the position of each obstacle in the map data, and update a navigation path in real time based on the map data marked with the position of each obstacle; the map data is generated by the main control robot in advance according to the collected environment data.
8. The method of claim 7, wherein the map data includes outdoor map data and indoor map data of respective buildings;
the master robot generates the map data according to the following modes:
responding to a control instruction triggered by a user, acquiring an environment image of an outdoor environment by the main control robot through a camera, and acquiring outdoor radar data of the outdoor environment through radar equipment; calling a SLAM algorithm to generate outdoor map data containing a plurality of buildings based on the collected environment image and the obtained outdoor radar data; and
the master robot respectively acquires indoor radar data inside each building through radar equipment; and calling a Cartogrer algorithm to respectively generate indoor map data corresponding to each building according to the indoor radar data in each building.
9. A delivery robot is characterized in that the delivery robot comprises at least one processor, at least one camera and an information transceiving unit;
the information receiving and sending unit is used for receiving a distribution instruction which is sent by the main control robot and used for executing a distribution task, and obtaining map data required for executing the distribution task from the main control robot; the distribution instruction is sent after the main control robot determines a distribution robot executing the current distribution task from a plurality of distribution robots according to the position information of each distribution robot and the distribution address corresponding to the distribution task; the map data is generated by the main control robot in advance according to the collected environment data;
the camera is used for acquiring an environment image of a distribution environment in real time in the process of executing the distribution task according to the generated navigation path;
the processor is used for generating a navigation path according to the map data acquired by the information transceiving unit and the distribution address corresponding to the distribution task; after the camera collects the environment image, identifying each obstacle in the environment image; marking the position of each obstacle in the map data according to the position information of each obstacle in the environment image; and updating the generated navigation path in real time according to the map data marked with the positions of the obstacles, and distributing according to the updated navigation path.
10. A master robot is characterized by comprising at least one processor and a transceiver unit;
the processor is used for determining a delivery address corresponding to the delivery task to be executed when the delivery task to be executed is determined; determining a distribution robot for executing the distribution task from the plurality of distribution robots according to the distribution addresses and the position information of the distribution robots;
the receiving and sending unit is used for sending a distribution instruction for executing a distribution task to a distribution robot executing the distribution task, sending map data required by the distribution task to the distribution robot executing the distribution task, enabling the distribution robot executing the distribution task to acquire an environment image of a distribution environment in real time through a camera in the process of executing the distribution task, marking the position of each obstacle in the map data, and updating a navigation path in real time based on the map data marked with the position of each obstacle; the map data is generated by the main control robot in advance according to the collected environment data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210295732.2A CN114662760A (en) | 2022-03-23 | 2022-03-23 | Robot-based distribution method and robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210295732.2A CN114662760A (en) | 2022-03-23 | 2022-03-23 | Robot-based distribution method and robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114662760A true CN114662760A (en) | 2022-06-24 |
Family
ID=82030932
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210295732.2A Pending CN114662760A (en) | 2022-03-23 | 2022-03-23 | Robot-based distribution method and robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114662760A (en) |
-
2022
- 2022-03-23 CN CN202210295732.2A patent/CN114662760A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Martin-Martin et al. | Jrdb: A dataset and benchmark of egocentric robot visual perception of humans in built environments | |
Harapanahalli et al. | Autonomous Navigation of mobile robots in factory environment | |
Montemerlo et al. | Large-scale robotic 3-d mapping of urban structures | |
WO2019173547A1 (en) | Odometry system and method for tracking traffic lights | |
CN107478214A (en) | A kind of indoor orientation method and system based on Multi-sensor Fusion | |
US20230064071A1 (en) | System for 3d surveying by an autonomous robotic vehicle using lidar-slam and an estimated point distribution map for path planning | |
CN110211228A (en) | For building the data processing method and device of figure | |
AU2012376428A1 (en) | Map data creation device, autonomous movement system and autonomous movement control device | |
CN110986920B (en) | Positioning navigation method, device, equipment and storage medium | |
CN107972027B (en) | Robot positioning method and device and robot | |
CN112518739A (en) | Intelligent self-navigation method for reconnaissance of tracked chassis robot | |
CN214520204U (en) | Port area intelligent inspection robot based on depth camera and laser radar | |
CN106501829A (en) | A kind of Navigation of Pilotless Aircraft method and apparatus | |
CN107562054A (en) | The independent navigation robot of view-based access control model, RFID, IMU and odometer | |
CN109839118A (en) | Paths planning method, system, robot and computer readable storage medium | |
An et al. | Development of mobile robot SLAM based on ROS | |
CN104729499A (en) | Bluetooth technology-based method for positioning mobile terminal by indoor robot | |
CN110392908A (en) | For generating the electronic equipment and its operating method of map datum | |
CN115718298A (en) | System for UGV and UAV automatically provide lidar data reference thereof for 3D detection | |
CN113607166B (en) | Indoor and outdoor positioning method and device for autonomous mobile robot based on multi-sensor fusion | |
CN114662760A (en) | Robot-based distribution method and robot | |
CN116007623A (en) | Robot navigation method, apparatus and computer readable storage medium | |
US20220108471A1 (en) | Method for coupling co-ordinate systems, and computer-assisted system | |
Faria et al. | Implementation of an autonomous ROS-based mobile robot with AI depth estimation | |
Noaman et al. | Landmarks exploration algorithm for mobile robot indoor localization using VISION sensor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |