CN111752285A - Autonomous navigation method and device for quadruped robot, computer equipment and storage medium - Google Patents
Autonomous navigation method and device for quadruped robot, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111752285A CN111752285A CN202010833431.1A CN202010833431A CN111752285A CN 111752285 A CN111752285 A CN 111752285A CN 202010833431 A CN202010833431 A CN 202010833431A CN 111752285 A CN111752285 A CN 111752285A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- acquiring
- outdoor environment
- information
- scheme
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000007689 inspection Methods 0.000 claims abstract description 98
- 230000004888 barrier function Effects 0.000 claims abstract description 26
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 6
- 230000009191 jumping Effects 0.000 description 6
- 241001465754 Metazoa Species 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000282326 Felis catus Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D57/00—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track
- B62D57/02—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members
- B62D57/032—Vehicles characterised by having other propulsion or other ground- engaging means than wheels or endless track, alone or in addition to wheels or endless track with ground-engaging propulsion means, e.g. walking members with alternately or sequentially lifted supporting base and legs; with alternately or sequentially lifted feet or skid
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of automatic cruising, in particular to a four-foot robot autonomous navigation method, a device, computer equipment and a storage medium, wherein the four-foot robot autonomous navigation method comprises the following steps: acquiring outdoor environment data through a laser radar technology, and constructing an outdoor map in real time based on the outdoor environment data; acquiring current position information and destination information of the quadruped robot, and generating a routing inspection path in the outdoor map; acquiring an outdoor environment type from the outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type; and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme. This application utensil can promote the in-process that patrols and examines the robot and keep away the effect of barrier cruising.
Description
Technical Field
The invention relates to the technical field of automatic cruising, in particular to an autonomous navigation method and device for a quadruped robot, computer equipment and a storage medium.
Background
At present, the application of the robot intelligent cruise technology is quite wide, and especially in the application scene of indoor inspection, for example, inspection is performed in a large machine room or a sweeping robot is applied indoors.
In the existing robot intelligent cruise technology, an intelligent robot is usually placed indoors, an indoor single and consistent indoor map is constructed through the intelligent robot, and then an indoor routing inspection or walking route is made according to a set inspiration position and a destination position.
Aiming at the related technologies, the inventor thinks that the defect that the obstacle avoidance effect is poor when the intelligent robot automatically walks exists.
Disclosure of Invention
The application aims to provide a four-legged robot autonomous navigation method, device, computer equipment and storage medium for improving the obstacle avoidance effect of an inspection robot in the cruising process.
The above object of the present invention is achieved by the following technical solutions:
a quadruped robot autonomous navigation method, comprising:
acquiring outdoor environment data through a laser radar technology, and constructing an outdoor map in real time based on the outdoor environment data;
acquiring current position information and destination information of the quadruped robot, and generating a routing inspection path in the outdoor map;
acquiring an outdoor environment type from the outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
By adopting the technical scheme, the outdoor environment data is acquired in real time, the outdoor map is acquired in real time, and the map to be inspected can be generated in real time according to the outdoor condition, so that the inspection robot can conveniently inspect; the corresponding obstacle avoiding model is obtained according to the outdoor environment type, so that the obstacle can be scanned in the routing inspection path in time, and an obstacle avoiding scheme for the existing obstacle can be generated in time; meanwhile, the characteristics of the quadruped robot are utilized, when the quadruped robot encounters an obstacle, the robot can detour the obstacle, and can simulate the mode that an animal crosses the obstacle to cross the obstacle, so that the quadruped robot is beneficial to adapting to more environments for field inspection.
The present application may be further configured in a preferred example to: the method for acquiring outdoor environment data through the laser radar technology specifically comprises the following steps:
acquiring the average walking speed of the four-legged robot, setting a laser scanning radius, and setting a scanning period according to the average walking speed;
and acquiring the outdoor environment data within the laser scanning radius according to the scanning period.
By adopting the technical scheme, the size of the constructed outdoor map can be reasonably planned under the condition that the calculation capacity for constructing the quadruped robot is limited by setting the laser scanning radius, so that the calculation precision for constructing the outdoor map is improved, and the efficiency for judging the barrier is facilitated; meanwhile, the laser scanning radius and the corresponding scanning period are set by combining the average traveling speed of the quadruped robot, so that the timeliness of the outdoor map is guaranteed while the times of constructing the outdoor map are reduced.
The present application may be further configured in a preferred example to: before the obtaining an outdoor environment type from the outdoor environment data and obtaining a preset obstacle avoidance model according to the outdoor environment type, the autonomous navigation method for the quadruped robot further includes:
acquiring corresponding obstacle information to be identified according to the outdoor environment type, and forming an obstacle information set to be identified by the obstacle information to be identified;
setting at least one image acquisition direction, and acquiring an obstacle image set corresponding to each obstacle to be identified in the obstacle information set to be identified according to the obstacle information set to be identified;
and training the obstacle image set corresponding to each outdoor environment type to obtain the obstacle avoidance model corresponding to each outdoor environment type.
By adopting the technical scheme, the fitting degree of the obstacle avoidance model and the actual environment can be higher by training the obstacle avoidance models of different outdoor environment types, so that the obstacle avoidance effect of the obstacle avoidance model on different outdoor environments is improved; the efficiency of obtaining the obstacles can be improved by obtaining the obstacle image set consisting of the obstacles in different image acquisition directions.
The present application may be further configured in a preferred example to: generating a corresponding inspection obstacle avoidance scheme according to the obstacle information, wherein the inspection obstacle avoidance scheme comprises an obstacle detouring scheme and an obstacle crossing scheme, and specifically comprises:
obtaining the size of the obstacle from the obstacle information;
acquiring a preset obstacle size standard, and comparing the obstacle size with the obstacle size standard to obtain a corresponding comparison result;
and if the small obstacle information is obtained from the comparison result, generating the obstacle crossing scheme, otherwise, generating the obstacle bypassing scheme.
By adopting the technical scheme, the obstacle size and the corresponding obstacle size standard are judged, whether the quadruped robot can cross the obstacle or not can be judged, and the obstacle crossing scheme is generated for the obstacle which can cross, so that the time for replanning the routing inspection path is reduced, and the adaptive capacity to the environment and the terrain is favorably improved.
The present application may be further configured in a preferred example to: patrol and examine and keep away the barrier scheme and still include the barrier scheme of keeping away, according to barrier information generates the corresponding scheme of keeping away the barrier of patrolling and examining, still includes:
setting an environment acquisition time period, and acquiring via environment images in real time in the environment acquisition time period to form a via environment image set;
acquiring concentratedly evadible position information in the passing environment image in real time;
if the dynamic obstacle information is acquired, acquiring the movement direction of the obstacle from the dynamic obstacle information;
and generating the obstacle avoidance scheme according to the obstacle movement direction and the avoidable position information.
By adopting the technical scheme, the passing-through environment images during routing inspection are stored in the environment acquisition time period, the passing-through environment image set is formed, the elusive position information is acquired in the passing-through environment image set in real time, the obstacle elusion scheme can be generated in time according to the movement direction of the obstacle when the sudden dynamic obstacle appears, the flexibility of the quadruped robot is utilized, and the quadruped robot is controlled to face the elusive obstacle according to the elusive position information.
The second purpose of the present application is achieved by the following technical scheme:
a four-footed robot autonomous navigation apparatus comprising:
the map building and positioning module is used for obtaining outdoor environment data through a laser radar technology and building an outdoor map in real time based on the outdoor environment data;
the route planning module is used for acquiring the current position information and the destination information of the quadruped robot and generating a routing inspection route in the outdoor map;
the obstacle identification module is used for acquiring an outdoor environment type from the outdoor environment data and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and the obstacle avoidance module is used for scanning in the routing inspection path by using the obstacle avoidance model, and generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information if the obstacle information is scanned, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
By adopting the technical scheme, the outdoor environment data is acquired in real time, the outdoor map is acquired in real time, and the map to be inspected can be generated in real time according to the outdoor condition, so that the inspection robot can conveniently inspect; the corresponding obstacle avoiding model is obtained according to the outdoor environment type, so that the obstacle can be scanned in the routing inspection path in time, and an obstacle avoiding scheme for the existing obstacle can be generated in time; meanwhile, the characteristics of the quadruped robot are utilized, when the quadruped robot encounters an obstacle, the robot can detour the obstacle, and can simulate the mode that an animal crosses the obstacle to cross the obstacle, so that the quadruped robot is beneficial to adapting to more environments for field inspection.
The third purpose of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the above-mentioned autonomous navigation method of a quadruped robot when executing said computer program.
The fourth purpose of the present application is achieved by the following technical solutions:
a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above-described autonomous navigation method of a quadruped robot.
In summary, the present application includes at least one of the following beneficial technical effects:
1. by acquiring outdoor environment data in real time and acquiring an outdoor map in real time, a map to be inspected can be generated in real time according to outdoor conditions, so that the inspection robot can conveniently perform inspection; the corresponding obstacle avoiding model is obtained according to the outdoor environment type, so that the obstacle can be scanned in the routing inspection path in time, and an obstacle avoiding scheme for the existing obstacle can be generated in time;
2. the characteristics of the quadruped robot are utilized, when the quadruped robot encounters an obstacle, the robot can detour the obstacle, and can simulate a mode that an animal crosses the obstacle to cross the obstacle, so that the quadruped robot is beneficial to adapting to more environments for field inspection;
3. by setting the laser scanning radius, the size of the constructed outdoor map can be reasonably planned under the condition that the computing capacity for constructing the quadruped robot is limited, so that the computing precision for constructing the outdoor map is improved, and the efficiency for judging the barrier is facilitated; meanwhile, the laser scanning radius and the corresponding scanning period are set by combining the average traveling speed of the quadruped robot, so that the timeliness of the outdoor map is guaranteed while the times of constructing the outdoor map are reduced;
4. the passing-through environment images during routing inspection are stored in the environment acquisition time period, a passing-through environment image set is formed, the shelterable position information is acquired in the passing-through environment image set in real time, when a sudden dynamic barrier appears, the barrier sheltering scheme can be generated in time according to the movement direction of the barrier, the flexibility of the quadruped robot is utilized, and the quadruped robot is controlled to face the shelterable position information to shelter from the sudden barrier.
Drawings
FIG. 1 is a flow chart of the autonomous navigation method of the quadruped robot in one embodiment of the present invention;
FIG. 2 is a flowchart of the step S10 in the autonomous navigation method of the quadruped robot according to one embodiment of the present invention;
FIG. 3 is a flow chart of another implementation of the autonomous navigation method of the quadruped robot in an embodiment of the present invention;
FIG. 4 is a flowchart of the step S40 in the autonomous navigation method of the quadruped robot in one embodiment of the present invention;
FIG. 5 is a flowchart of another implementation of step S40 in the autonomous navigation method of the quadruped robot in an embodiment of the present invention;
FIG. 6 is a schematic block diagram of an autonomous navigation apparatus of a quadruped robot in an embodiment of the present invention;
fig. 7 is a schematic diagram of an apparatus in an embodiment of the invention.
Detailed Description
The present application is described in further detail below with reference to the attached drawings.
The current autonomous navigation technologies mainly comprise inertial navigation, magnetic navigation, distance sensor navigation, visual navigation, GPS navigation and the like. The existing inertial navigation has low precision, the magnetic navigation needs to lay a magnetic tape on the ground, the application range is limited, the distance sensor has good effects in map construction and positioning, but the real-time obstacle avoidance effect is general, the visual navigation senses the surrounding environment by using a camera installed on a robot, and the obstacle avoidance and navigation are realized by performing feature extraction, detection and identification on the environment, but the contained information is very rich, the calculated amount is very large, and the real-time performance is not good.
In one embodiment, as shown in fig. 1, the present application discloses a quadruped robot autonomous navigation method, which specifically includes the following steps:
s10: outdoor environment data are obtained through a laser radar technology, and an outdoor map is constructed in real time based on the outdoor environment data.
In this embodiment, the outdoor environment data refers to data of an environment when actually performing patrol outdoors. The outdoor map is a real-time map constructed for the inspection environment.
In particular, the application is applied to a smart robot with a shape similar to a quadruped animal, such as a smart dog robot, a smart cat robot, or other shaped smart devices. Through the top installation at this four-footed robot can carry out the equipment of laser radar scanning, through this equipment, when four-footed robot patrols and examines in the open air, the scanning and acquire outdoor environmental data.
Further, the outdoor map is constructed by using SLAM (simultaneous localization and mapping) technology to the outdoor environment data obtained by scanning.
S20: and acquiring the current position information and the destination information of the quadruped robot, and generating a routing inspection path in an outdoor map.
In this embodiment, the current position information refers to a position where the quadruped robot is located when the quadruped robot is patrolled outdoors. The destination information is information of the position of the quadruped robot when the quadruped robot finishes the next inspection task when the quadruped robot inspects outdoors. The inspection path refers to a path which the quadruped robot needs to walk in the inspection task.
Specifically, with the SLAM technique, the current position information of the quadruped robot is acquired when the outdoor map is constructed. Meanwhile, according to the actual inspection requirement, destination information is set in the constructed outdoor map or the actual map system. Further, a corresponding patrol route is generated in the outdoor map.
S30: and acquiring an outdoor environment type from the outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type.
In this embodiment, the outdoor environment type refers to a type of dividing the outdoor environment when the inspection is actually performed. The obstacle avoidance model is a model for detecting whether an obstacle exists in an actual inspection environment.
Specifically, according to the actual inspection requirement, the outdoor environment types, such as unattended mountains, plains or other environment types, are divided in advance for the scene requiring inspection, and the characteristics obtained through laser scanning in each outdoor environment are extracted respectively. Furthermore, the outdoor environment data obtained by scanning through the laser radar technology is compared with the characteristics in the preset outdoor environment type, and the comparison result is used as the obtained outdoor environment type.
Further, matching an obstacle avoidance model corresponding to the outdoor environment type through the obtained outdoor environment type. Understandably, when the obstacle avoidance model is trained in advance, the obstacle avoidance model is respectively corresponding to the different types of outdoor environments obtained through division, and the obstacle avoidance model obtained through training is uniquely associated with the corresponding type of the outdoor environment.
S40: and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
In the present embodiment, the obstacle information refers to information on an obstacle present in the patrol path of the quadruped robot. The inspection obstacle avoidance scheme is a scheme for avoiding obstacles in an inspection path. The obstacle detour scheme refers to a scheme of detouring an obstacle in the patrol route. The obstacle crossing scheme refers to a scheme of crossing from above an obstacle to avoid the obstacle.
Specifically, when the obstacle is scanned or otherwise acquired in the inspection path of the quadruped robot in the application through the obstacle avoidance model, the obstacle information of the obstacle is acquired, and the obstacle information includes information such as the distance from the quadruped robot, the size of the obstacle, and whether the obstacle is static or dynamic.
Further, the actual width of the obstacle, the length and the height of the relative routing inspection path are calculated according to the distance between the obstacle and the robot and the size of the obstacle when the obstacle is acquired, and the actual width, the length and the height of the relative routing inspection path are used as the size of the obstacle.
When the obstacle crossing plan is generated, if the quadruped robot has the jumping function, the maximum jumping height of the quadruped robot, the length and the height of the relative routing inspection path are obtained according to the actual jumping capability of the quadruped robot, whether the quadruped robot can jump the obstacle through the jumping function is judged, and if the quadruped robot can jump the obstacle, the corresponding obstacle crossing plan is generated according to the length and the actual height of the relative routing inspection path of the obstacle. The length of the relative routing inspection path refers to the length of the part of the obstacle overlapping with the routing inspection path.
In the embodiment, the outdoor environment data and the outdoor map are acquired in real time, so that the map to be inspected can be generated in real time according to the outdoor condition, and the inspection robot can conveniently perform inspection; the corresponding obstacle avoiding model is obtained according to the outdoor environment type, so that the obstacle can be scanned in the routing inspection path in time, and an obstacle avoiding scheme for the existing obstacle can be generated in time; meanwhile, the characteristics of the quadruped robot are utilized, when the quadruped robot encounters an obstacle, the robot can detour the obstacle, and can simulate the mode that an animal crosses the obstacle to cross the obstacle, so that the quadruped robot is beneficial to adapting to more environments for field inspection.
In an embodiment, as shown in fig. 2, in step S10, that is, acquiring outdoor environment data by using the lidar technology, the method specifically includes the following steps:
s11: and acquiring the average walking speed of the four-legged robot, setting the laser scanning radius, and setting the scanning period according to the average walking speed.
In the present embodiment, the average traveling speed refers to the speed of the quadruped robot when the patrol task is normally performed. The laser scanning radius refers to the scanning radius of each scanning by using the laser radar technology and constructing the outdoor map. The scanning period refers to an interval of time between two adjacent scans of outdoor environment data.
Specifically, the walking speed of the quadruped robot executing the inspection task at this time is acquired as the average walking speed according to the product specification of the quadruped robot.
Furthermore, according to the scanning capability of the device for scanning the laser radar of the quadruped robot executing the inspection task at this time and the requirement for the precision of obstacle avoidance in actual inspection, the laser scanning radius is set, and the precision and the efficiency of building an outdoor map each time are guaranteed. When the laser scanning radius is set, the minimum value of the laser scanning radius can be calculated according to the time required by constructing the outdoor map every time and the average traveling speed, and the laser scanning radius is ensured to be larger than the minimum value.
Furthermore, the time required for constructing the outdoor map can be used as a scanning period, meanwhile, the maximum walking distance of the four-legged robot executing the inspection task each time when the outdoor map is constructed can be set according to the requirements of an actual scene on the basis of the laser scanning radius, and the scanning period is calculated according to the maximum walking distance and the average walking speed.
S12: and acquiring outdoor environment data within the laser scanning radius according to the scanning period.
Specifically, after outdoor environment data are acquired for the first time and the corresponding quadruped robot is triggered to execute the patrol task, the outdoor environment data within the laser scanning radius are acquired at intervals of the scanning period.
In one embodiment, as shown in fig. 3, before step S30, the quadruped robot autonomous navigation method further includes:
s31: and acquiring corresponding obstacle information to be identified according to the outdoor environment type, and forming an obstacle information set to be identified by the obstacle information to be identified.
In the present embodiment, the obstacle information to be recognized refers to information that every obstacle may exist in the corresponding outdoor scene type. The obstacle information set to be identified refers to all data sets of the obstacle information to be identified under the corresponding outdoor environment type.
Specifically, according to each outdoor environment type, collecting corresponding obstacles which may appear, using information of each obstacle, such as branches, stones, soil pits and the like, as obstacle information to be identified, and forming all obstacle information to be identified of each outdoor scene type into an obstacle information set to be identified.
S32: and setting at least one image acquisition direction, and acquiring an obstacle image set corresponding to each obstacle to be recognized in the obstacle information set to be recognized according to the obstacle information set to be recognized.
In the present embodiment, the image capturing orientation refers to information of different orientations in which the same obstacle is photographed. The obstacle image set is a set of images of each obstacle captured.
Specifically, when training an obstacle avoidance model, in the same outdoor environment type, an obstacle is placed right in front of the quadruped robot, and then according to the set image acquisition direction, the quadruped robot is moved, and the camera of the quadruped robot is used for acquiring image data of the obstacle in different directions; furthermore, various obstacle combinations can be adopted for shooting to obtain corresponding image data, when a plurality of obstacles appear in the camera at the same time, the frontmost obstacle of the four-legged robot is marked, and the acquired image data set is used as the obstacle image set.
S33: and training the obstacle image set corresponding to each outdoor environment type to obtain an obstacle avoiding model corresponding to each outdoor environment type.
Specifically, the anti-collision algorithm is used to train the obstacle image set of each outdoor environment type, for example, the backsbone algorithm of 16 at vgg is used to train the obstacle image set, and an obstacle avoidance model corresponding to the outdoor environment type is obtained.
In an embodiment, as shown in fig. 4, in step S40, a corresponding inspection obstacle avoidance scheme is generated according to the obstacle information, where the inspection obstacle avoidance scheme includes an obstacle detouring scheme and an obstacle crossing scheme, and the method specifically includes the following steps:
s411: and acquiring the size of the obstacle from the obstacle information.
In the present embodiment, the obstacle size refers to information of the actual size of the obstacle.
Specifically, the distance from the obstacle to the quadruped robot which actually performs the inspection task and the size of the obstacle obtained by scanning are obtained from the obstacle information, and the actual size of the obstacle is calculated as the size of the obstacle by using a formula of a trigonometric function.
S412: and acquiring a preset obstacle size standard, and comparing the obstacle size with the obstacle size standard to obtain a corresponding comparison result.
In the present embodiment, the obstacle size criterion refers to the maximum size for determining whether the quadruped robot that actually performs the patrol task can cross the obstacle.
Specifically, the obstacle size standard is set by acquiring the height of the quadruped robot actually performing the patrol task, and the jumping ability. Further, the obstacle size is compared with the obstacle size standard in numerical value, and a corresponding comparison result is obtained.
S413: and if the small obstacle information is obtained from the comparison result, generating an obstacle crossing scheme, otherwise, generating an obstacle bypassing scheme.
Specifically, if the comparison result shows that the size of the obstacle is smaller than the obstacle size standard, the small obstacle information is generated, and the obstacle crossing scheme is generated, and if the comparison result shows that the size of the obstacle is larger than or equal to the obstacle size standard, that is, the quadruped robot cannot cross the obstacle, the obstacle bypassing scheme is generated.
In an embodiment, as shown in fig. 5, in step S40, the inspection obstacle avoidance scheme further includes an obstacle avoidance scheme, and generates a corresponding inspection obstacle avoidance scheme according to the obstacle information, further including the following steps:
s421: and setting an environment acquisition time period, and acquiring the passing environment images in real time in the environment acquisition time period to form a passing environment image set.
In the present embodiment, the environment acquisition time period refers to a time period for acquiring the situation of the environment of the path that the quadruped robot has traveled during the patrol. The passing environment image refers to an image of a four-legged robot passing in the process of inspection. The route environment image set refers to a data set of route environment images.
Specifically, the environment acquisition time period is preset, for example, 5 seconds, 10 seconds, 15 seconds, or the like, and the corresponding passing environment image is acquired in the environment acquisition time period, that is, when the quadruped robot actually executes the inspection task, an image of the environment in the environment acquisition time period before the current time is acquired by the camera and is used as the environment image and used as the passing environment image set, so that it can be understood that the passing environment image set iterates in real time along with the continuous process of the quadruped robot actually executing the inspection task.
S422: and acquiring the evasive position information in a passing environment image set in real time.
In the present embodiment, the evasive position information refers to a position at which the quadruped robot, which can be used to actually perform the inspection task, avoids a sudden obstacle.
Specifically, the images of the passing environment are concentrated, a corresponding radius is set according to the maximum jumping distance of the quadruped robot, and a position which can be used for the quadruped robot to actually execute the routing inspection task to avoid, such as an open place, is acquired within the radius.
S423: and if the dynamic obstacle information is acquired, acquiring the movement direction of the obstacle from the dynamic obstacle information.
In the present embodiment, the dynamic obstacle information refers to information of an obstacle that is bursty and that dynamically changes position. The obstacle moving direction refers to a direction in which the dynamically moving obstacle moves.
Specifically, if it is acquired that a moving obstacle, such as a falling stone or soil block, appears on the inspection path, the obstacle movement direction of the dynamic obstacle is acquired.
S424: and generating an obstacle avoidance scheme according to the movement direction of the obstacle and the avoidable position information.
Specifically, if the dynamic obstacle continues to move along the obstacle moving direction of the dynamic obstacle, and the quadruped robot actually performing routing inspection continues to move along the predetermined routing inspection path, when the risk of collision between the quadruped robot and the dynamic obstacle is triggered, the range covered by the dynamic obstacle in the moving process is obtained according to the obstacle moving direction and the size of the dynamic obstacle, the obstacle avoiding scheme is generated according to the covered range and the avoidable position information, and the quadruped robot is controlled to jump towards the avoidable position information in the direction away from the covered range so as to avoid the dynamic obstacle.
This application carries out composition and location through laser scanning and SLAM, and the barrier laser that exists can judge, only judges whether there is proruption barrier to appear through the camera, has reduced the calculated amount when keeping away the barrier, has promoted the real-time of keeping away the barrier.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
In one embodiment, a four-footed robot autonomous navigation apparatus is provided, which corresponds one-to-one to the four-footed robot autonomous navigation method in the above embodiments. As shown in fig. 6, the autonomous navigation apparatus for a quadruped robot includes a map building and positioning module 10, a path planning module 20, an obstacle recognition module 30, and an obstacle avoidance module 40. The functional modules are explained in detail as follows:
the map building and positioning module 10 is used for obtaining outdoor environment data through a laser radar technology and building an outdoor map in real time based on the outdoor environment data;
the path planning module 20 is used for acquiring the current position information and the destination information of the quadruped robot and generating a routing inspection path in an outdoor map;
the obstacle identification module 30 is configured to acquire an outdoor environment type from the outdoor environment data, and acquire a preset obstacle avoidance model according to the outdoor environment type;
and the obstacle avoidance module 40 is configured to scan the inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generate a corresponding inspection obstacle avoidance scheme according to the obstacle information, where the inspection obstacle avoidance scheme includes an obstacle detouring scheme and an obstacle crossing scheme.
Further, the map building and positioning module 10 includes:
the parameter setting submodule is used for acquiring the average walking path speed of the four-footed robot, setting the laser scanning radius and setting the scanning period according to the average walking path speed;
and the scanning submodule is used for acquiring outdoor environment data within the laser scanning radius according to the scanning period.
Further, the autonomous navigation apparatus for a quadruped robot further includes:
the data set setting module is used for acquiring corresponding barrier information to be identified according to the outdoor environment type and forming the barrier information to be identified into a barrier information set to be identified;
the obstacle image acquisition module is used for setting at least one image acquisition direction and acquiring an obstacle image set corresponding to each obstacle to be identified in the obstacle information set to be identified according to the obstacle information set to be identified;
and the model training module is used for training the obstacle image set corresponding to each outdoor environment type to obtain an obstacle avoiding model corresponding to each outdoor environment type.
Further, the obstacle avoidance module 40 includes:
the size calculation submodule is used for acquiring the size of the obstacle from the obstacle information;
the comparison submodule is used for acquiring a preset obstacle size standard, and comparing the obstacle size with the obstacle size standard to obtain a corresponding comparison result;
and the first obstacle avoidance sub-module is used for generating an obstacle crossing scheme if the small obstacle information is acquired from the comparison result, and otherwise, generating an obstacle bypassing scheme.
Further, the obstacle avoidance module 40 further includes:
the image pre-storage sub-module is used for setting an environment acquisition time period, acquiring the passing environment images in real time in the environment acquisition time period and forming a passing environment image set;
the position acquisition submodule is used for acquiring concentratedly the evasive position information in the passing environment image in real time;
the dynamic barrier obtaining sub-module is used for obtaining the movement direction of the barrier from the dynamic barrier information if the dynamic barrier information is obtained;
and the second avoidance sub-module is used for generating an obstacle avoidance scheme according to the movement direction of the obstacle and the avoidable position information.
For specific limitations of the autonomous navigation device of the quadruped robot, reference may be made to the above limitations of the autonomous navigation method of the quadruped robot, which will not be described herein again. The modules in the autonomous navigation device of the quadruped robot can be completely or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing barrier avoiding models corresponding to different outdoor environment types. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a quadruped robotic autonomous navigation method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring outdoor environment data through a laser radar technology, and constructing an outdoor map in real time based on the outdoor environment data;
acquiring current position information and destination information of the quadruped robot, and generating a routing inspection path in an outdoor map;
acquiring an outdoor environment type from outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring outdoor environment data through a laser radar technology, and constructing an outdoor map in real time based on the outdoor environment data;
acquiring current position information and destination information of the quadruped robot, and generating a routing inspection path in an outdoor map;
acquiring an outdoor environment type from outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A quadruped robot autonomous navigation method, characterized by comprising:
acquiring outdoor environment data through a laser radar technology, and constructing an outdoor map in real time based on the outdoor environment data;
acquiring current position information and destination information of the quadruped robot, and generating a routing inspection path in the outdoor map;
acquiring an outdoor environment type from the outdoor environment data, and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and scanning the routing inspection path by using the obstacle avoidance model, and if the obstacle information is scanned, generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
2. The autonomous navigation method of the quadruped robot according to claim 1, wherein the acquiring outdoor environment data by the lidar technology specifically comprises:
acquiring the average walking speed of the four-legged robot, setting a laser scanning radius, and setting a scanning period according to the average walking speed;
and acquiring the outdoor environment data within the laser scanning radius according to the scanning period.
3. The autonomous navigation method of a quadruped robot according to claim 1, wherein before the step of obtaining an outdoor environment type from the outdoor environment data, and obtaining a preset obstacle avoidance model by the outdoor environment type, the autonomous navigation method of a quadruped robot further comprises:
acquiring corresponding obstacle information to be identified according to the outdoor environment type, and forming an obstacle information set to be identified by the obstacle information to be identified;
setting at least one image acquisition direction, and acquiring an obstacle image set corresponding to each obstacle to be identified in the obstacle information set to be identified according to the obstacle information set to be identified;
and training the obstacle image set corresponding to each outdoor environment type to obtain the obstacle avoidance model corresponding to each outdoor environment type.
4. The autonomous navigation method of the quadruped robot according to claim 1, wherein the corresponding patrol inspection obstacle avoidance scheme is generated according to the obstacle information, wherein the patrol inspection obstacle avoidance scheme includes an obstacle detouring scheme and an obstacle crossing scheme, and specifically includes:
obtaining the size of the obstacle from the obstacle information;
acquiring a preset obstacle size standard, and comparing the obstacle size with the obstacle size standard to obtain a corresponding comparison result;
and if the small obstacle information is obtained from the comparison result, generating the obstacle crossing scheme, otherwise, generating the obstacle bypassing scheme.
5. The autonomous navigation method of the quadruped robot according to claim 4, wherein the inspection obstacle avoidance scheme further comprises an obstacle avoidance scheme, and the generating of the corresponding inspection obstacle avoidance scheme according to the obstacle information further comprises:
setting an environment acquisition time period, and acquiring via environment images in real time in the environment acquisition time period to form a via environment image set;
acquiring concentratedly evadible position information in the passing environment image in real time;
if the dynamic obstacle information is acquired, acquiring the movement direction of the obstacle from the dynamic obstacle information;
and generating the obstacle avoidance scheme according to the obstacle movement direction and the avoidable position information.
6. A four-footed robot autonomous navigation apparatus, characterized by comprising:
the map building and positioning module (10) is used for obtaining outdoor environment data through a laser radar technology and building an outdoor map in real time based on the outdoor environment data;
the path planning module (20) is used for acquiring the current position information and the destination information of the quadruped robot and generating a routing inspection path in the outdoor map;
the obstacle identification module (30) is used for acquiring an outdoor environment type from the outdoor environment data and acquiring a preset obstacle avoidance model according to the outdoor environment type;
and the obstacle avoidance module (40) is used for scanning in the routing inspection path by using the obstacle avoidance model, and generating a corresponding routing inspection obstacle avoidance scheme according to the obstacle information if the obstacle information is scanned, wherein the routing inspection obstacle avoidance scheme comprises an obstacle bypassing scheme and an obstacle crossing scheme.
7. The autonomous navigation device of a quadruped robot according to claim 6, characterized in that said mapping and positioning module (10) comprises:
the parameter setting submodule is used for acquiring the average walking speed of the four-footed robot, setting the laser scanning radius and setting the scanning period according to the average walking speed;
and the scanning submodule is used for acquiring the outdoor environment data within the laser scanning radius according to the scanning period.
8. The autonomous navigation system of a quadruped robot according to claim 6, further comprising:
the data set setting module is used for acquiring corresponding barrier information to be identified according to the outdoor environment type and forming the barrier information to be identified into a barrier information set to be identified;
the obstacle image acquisition module is used for setting at least one image acquisition direction and acquiring an obstacle image set corresponding to each obstacle to be identified in the obstacle information set to be identified according to the obstacle information set to be identified;
and the model training module is used for training the obstacle image set corresponding to each outdoor environment type to obtain the obstacle avoidance model corresponding to each outdoor environment type.
9. A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor, when executing said computer program, implements the steps of the autonomous navigation method of a quadruped robot according to any one of claims 1 to 5.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of the autonomous navigation method of a quadruped robot according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010833431.1A CN111752285A (en) | 2020-08-18 | 2020-08-18 | Autonomous navigation method and device for quadruped robot, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010833431.1A CN111752285A (en) | 2020-08-18 | 2020-08-18 | Autonomous navigation method and device for quadruped robot, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111752285A true CN111752285A (en) | 2020-10-09 |
Family
ID=72712012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010833431.1A Pending CN111752285A (en) | 2020-08-18 | 2020-08-18 | Autonomous navigation method and device for quadruped robot, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111752285A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112712148A (en) * | 2020-12-30 | 2021-04-27 | 杭州越歌科技有限公司 | Underground pipe network monitoring method, system, device and storage medium |
| CN112783158A (en) * | 2020-12-28 | 2021-05-11 | 广州辰创科技发展有限公司 | Method, equipment and storage medium for fusing multiple wireless sensing identification technologies |
| CN112882480A (en) * | 2021-03-23 | 2021-06-01 | 海南师范大学 | System and method for fusing SLAM (simultaneous localization and mapping) by laser and vision aiming at crowd environment |
| CN113110176A (en) * | 2021-04-15 | 2021-07-13 | 北京云迹科技有限公司 | Robot-based running state control method and related equipment |
| CN113219969A (en) * | 2021-04-22 | 2021-08-06 | 深圳拓邦股份有限公司 | Obstacle avoidance control method and device for floor washing robot and floor washing robot |
| CN113781676A (en) * | 2021-09-15 | 2021-12-10 | 北京顺造科技有限公司 | Security protection system of patrolling and examining based on four-footed robot and unmanned aerial vehicle |
| CN113806936A (en) * | 2021-09-17 | 2021-12-17 | 南阳防爆电气研究所有限公司 | Performance evaluation method and evaluation system of autonomous fire-fighting robot |
| CN113867350A (en) * | 2021-09-28 | 2021-12-31 | 北京炎凌嘉业机电设备有限公司 | Intelligent bionic foot type robot stepping behavior autonomous adaptation method |
| CN114137963A (en) * | 2021-11-06 | 2022-03-04 | 中山嘉明电力有限公司 | Inspection system and method based on quadruped robot |
| CN114237225A (en) * | 2021-11-19 | 2022-03-25 | 武汉华中思能科技有限公司 | Quadruped robot and intelligent inspection management platform thereof |
| CN114326742A (en) * | 2021-12-31 | 2022-04-12 | 深圳市优必选科技股份有限公司 | Robot operation method, robot operation device, robot, and medium |
| CN114721404A (en) * | 2022-06-08 | 2022-07-08 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN114911223A (en) * | 2021-02-09 | 2022-08-16 | 北京盈迪曼德科技有限公司 | Robot navigation method and device, robot and storage medium |
| CN114967687A (en) * | 2022-05-23 | 2022-08-30 | 纯米科技(上海)股份有限公司 | Obstacle detection method, system, electronic device and computer-readable storage medium |
| CN113741467B (en) * | 2021-09-07 | 2023-10-13 | 深圳大方智能科技有限公司 | Vertical wall surface construction method and construction robot |
| CN116909284A (en) * | 2023-07-27 | 2023-10-20 | 苏州光格科技股份有限公司 | Foot robot obstacle avoidance control method, device, computer equipment and storage medium |
| CN117232501A (en) * | 2023-11-14 | 2023-12-15 | 双擎科技(杭州)有限公司 | Multi-sensor information fusion intelligent robot navigation device, method and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106610664A (en) * | 2015-10-22 | 2017-05-03 | 沈阳新松机器人自动化股份有限公司 | Movement obstacle avoidance device and control method |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN110316186A (en) * | 2019-07-01 | 2019-10-11 | 百度在线网络技术（北京）有限公司 | Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing |
| CN110393482A (en) * | 2019-09-03 | 2019-11-01 | 深圳飞科机器人有限公司 | Maps processing method and clean robot |
| CN110909637A (en) * | 2019-11-08 | 2020-03-24 | 清华大学 | Outdoor mobile robot terrain recognition method based on visual-touch fusion |
| CN111427363A (en) * | 2020-04-24 | 2020-07-17 | 深圳国信泰富科技有限公司 | Robot navigation control method and system |
-
2020
- 2020-08-18 CN CN202010833431.1A patent/CN111752285A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106610664A (en) * | 2015-10-22 | 2017-05-03 | 沈阳新松机器人自动化股份有限公司 | Movement obstacle avoidance device and control method |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN110316186A (en) * | 2019-07-01 | 2019-10-11 | 百度在线网络技术（北京）有限公司 | Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing |
| CN110393482A (en) * | 2019-09-03 | 2019-11-01 | 深圳飞科机器人有限公司 | Maps processing method and clean robot |
| CN110909637A (en) * | 2019-11-08 | 2020-03-24 | 清华大学 | Outdoor mobile robot terrain recognition method based on visual-touch fusion |
| CN111427363A (en) * | 2020-04-24 | 2020-07-17 | 深圳国信泰富科技有限公司 | Robot navigation control method and system |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112783158A (en) * | 2020-12-28 | 2021-05-11 | 广州辰创科技发展有限公司 | Method, equipment and storage medium for fusing multiple wireless sensing identification technologies |
| CN112712148A (en) * | 2020-12-30 | 2021-04-27 | 杭州越歌科技有限公司 | Underground pipe network monitoring method, system, device and storage medium |
| CN114911223A (en) * | 2021-02-09 | 2022-08-16 | 北京盈迪曼德科技有限公司 | Robot navigation method and device, robot and storage medium |
| CN114911223B (en) * | 2021-02-09 | 2023-05-05 | 北京盈迪曼德科技有限公司 | Robot navigation method, device, robot and storage medium |
| CN112882480A (en) * | 2021-03-23 | 2021-06-01 | 海南师范大学 | System and method for fusing SLAM (simultaneous localization and mapping) by laser and vision aiming at crowd environment |
| CN112882480B (en) * | 2021-03-23 | 2023-07-21 | 海南师范大学 | System and method for fusing laser and vision for crowd environment with SLAM |
| CN113110176A (en) * | 2021-04-15 | 2021-07-13 | 北京云迹科技有限公司 | Robot-based running state control method and related equipment |
| CN113219969A (en) * | 2021-04-22 | 2021-08-06 | 深圳拓邦股份有限公司 | Obstacle avoidance control method and device for floor washing robot and floor washing robot |
| CN113741467B (en) * | 2021-09-07 | 2023-10-13 | 深圳大方智能科技有限公司 | Vertical wall surface construction method and construction robot |
| CN113781676A (en) * | 2021-09-15 | 2021-12-10 | 北京顺造科技有限公司 | Security protection system of patrolling and examining based on four-footed robot and unmanned aerial vehicle |
| CN113806936A (en) * | 2021-09-17 | 2021-12-17 | 南阳防爆电气研究所有限公司 | Performance evaluation method and evaluation system of autonomous fire-fighting robot |
| CN113867350A (en) * | 2021-09-28 | 2021-12-31 | 北京炎凌嘉业机电设备有限公司 | Intelligent bionic foot type robot stepping behavior autonomous adaptation method |
| CN114137963A (en) * | 2021-11-06 | 2022-03-04 | 中山嘉明电力有限公司 | Inspection system and method based on quadruped robot |
| CN114237225A (en) * | 2021-11-19 | 2022-03-25 | 武汉华中思能科技有限公司 | Quadruped robot and intelligent inspection management platform thereof |
| CN114326742A (en) * | 2021-12-31 | 2022-04-12 | 深圳市优必选科技股份有限公司 | Robot operation method, robot operation device, robot, and medium |
| CN114967687A (en) * | 2022-05-23 | 2022-08-30 | 纯米科技(上海)股份有限公司 | Obstacle detection method, system, electronic device and computer-readable storage medium |
| CN114721404A (en) * | 2022-06-08 | 2022-07-08 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN114721404B (en) * | 2022-06-08 | 2022-09-13 | 超节点创新科技(深圳)有限公司 | Obstacle avoidance method, robot and storage medium |
| CN116909284A (en) * | 2023-07-27 | 2023-10-20 | 苏州光格科技股份有限公司 | Foot robot obstacle avoidance control method, device, computer equipment and storage medium |
| CN117232501A (en) * | 2023-11-14 | 2023-12-15 | 双擎科技(杭州)有限公司 | Multi-sensor information fusion intelligent robot navigation device, method and medium |
| CN117232501B (en) * | 2023-11-14 | 2024-02-20 | 双擎科技(杭州)有限公司 | Multi-sensor information fusion intelligent robot navigation device, method and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111752285A (en) | Autonomous navigation method and device for quadruped robot, computer equipment and storage medium | |
| CN110968110B (en) | Method and device for determining operation area, unmanned aerial vehicle and storage medium | |
| US9274524B2 (en) | Method for machine coordination which maintains line-of-site contact | |
| US8478493B2 (en) | High integrity perception program | |
| US8666587B2 (en) | Multi-vehicle high integrity perception | |
| EP2169498B1 (en) | Vehicle with high integrity perception system | |
| EP2169499A2 (en) | High integrity perception for machine localization and safeguarding | |
| US20210255638A1 (en) | Area Division and Path Forming Method and Apparatus for Self-Moving Device and Automatic Working System | |
| WO2021164738A1 (en) | Area division and path forming method and apparatus for self-moving device and automatic working system | |
| CN112462756B (en) | Agriculture and forestry operation task generation method and device, computer equipment and storage medium | |
| CN109068278B (en) | Indoor obstacle avoidance method and device, computer equipment and storage medium | |
| CN115454077A (en) | Automatic lawn mower, control method thereof, and computer-readable storage medium | |
| CN111309011A (en) | Decision-making method, system, equipment and storage medium for autonomously exploring target | |
| WO2024055855A1 (en) | Autonomous mobile device and method for controlling the same, and computer readable storage medium | |
| CN111744690B (en) | Spraying operation control method, device, carrier and storage medium | |
| CN112506187A (en) | Mobile robot monitoring method and device and storage medium | |
| CN113454558A (en) | Obstacle detection method and device, unmanned aerial vehicle and storage medium | |
| CN110568846A (en) | AGV intelligent navigation method and system | |
| CN115097833A (en) | Automatic obstacle avoidance method and system for pesticide application robot and storage medium | |
| CN114942639A (en) | Self-adaptive path planning method and device for mobile robot | |
| CN114967495A (en) | Orchard virtual simulation inspection system and method based on Internet of things cloud control platform | |
| CN114610038A (en) | Weeding robot control system and control method | |
| CN115639820B (en) | Virtual wall setting method, autonomous mobile device, and computer-readable storage medium | |
| CN117311367B (en) | Control method and control unit of self-mobile device and self-mobile device | |
| CN110673604A (en) | Automatic warehousing control method and system for mobile robot and mobile robot |
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 |