Path planning method and device, storage medium and robot

Abstract

The invention discloses a path planning method and device, a storage medium and a robot, relates to the technical field of robots, is applied to robots, and comprises the following steps: updating a constructed local map by using identified perception information to obtain a current local map; determining a current working scene of itself, and determining a target point in the current local map based on the current working scene; and performing path planning based on the current local map, the current position of the robot and the target point so as to travel from the current position to the target point according to a planned target path. Thus, the robot does not need to set a global map and a corresponding advancing path, the local map is directly updated through the point cloud information, recognized in real time, of the surrounding environment, and the driving path can be flexibly planned in real time according to the change of the surrounding environment and the current working scene of the robot in the driving process; the failure rate of path planning can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of robotics technology, and in particular to a path planning method, device, storage medium and robot. Background Art

[0002] Existing path planning methods work well in specific structured scenarios (such as highways and urban roads with guide lines), but are relatively ineffective in unstructured scenarios such as courtyard lawns, which may lead to path planning failures, lawn mowers getting stuck, and operations being suspended.

[0003] It can be seen that how to flexibly plan paths and reduce the failure rate of path planning is a problem to be solved in this field. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a path planning method, device, storage medium and robot, which can flexibly plan the driving path according to the changes in the surrounding environment and the current working scene in real time during driving, thereby reducing the failure rate of path planning. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a path planning method, applied to a robot, comprising:

[0006] Using the recognized perception information, the constructed local map is updated to obtain the current local map;

[0007] Determine a current working scene of the system, and determine a target point in the current local map based on the current working scene;

[0008] Path planning is performed based on the current local map, the current position of the vehicle and the target point, so as to travel from the current position to the target point according to the planned target path.

[0009] Optionally, the updating of the constructed local map by using the recognized perception information to obtain the current local map includes:

[0010] Identify semantic information and depth information of work area boundaries and / or obstacles through visual sensors;

[0011] The semantic information and depth information of the working area boundary and / or the obstacle are marked in the constructed local map, so as to update the local map in real time to obtain the current local map.

[0012] Optionally, determining a current working scene of the system, and determining a target point in the current local map based on the current working scene, includes:

[0013] If the current working scene indicates that the robot is moving along a channel and the distance to the obstacle is not greater than a preset distance, then a plurality of intersection points of the channel and the boundary of the current local map are determined as first candidate points;

[0014] If the distance between the first candidate point that matches the current forward direction of the robot and the obstacle position is not less than the preset distance, the corresponding first candidate point is determined as the target point;

[0015] If the distance between the first candidate point that matches the robot's current forward direction and the position of the obstacle is less than the preset distance, then several points on the channel that are between the first candidate point and the robot's current position and whose distance from the obstacle position is not less than the preset distance are determined as second candidate points, so as to determine the target point with the largest distance from the current position from among the several second candidate points.

[0016] Optionally, determining a current working scene of the system, and determining a target point in the current local map based on the current working scene, includes:

[0017] If the current working scene indicates that the robot is moving along the boundary of the working area, and the distance between the current position of the robot and the obstacle position is not less than a preset distance, then determining a plurality of third candidate points on the boundary of the working area that intersect with the boundary of the current local map;

[0018] Determine a plurality of points among the plurality of third candidate points whose distances from the obstacle position are not less than the preset distance as fourth candidate points, and determine a target point whose distance from the current position is the largest from the plurality of fourth candidate points;

[0019] Alternatively, if the current working scene indicates that the robot is moving along the boundary of the working area, and the satellite positioning signal strength of the robot is less than a preset signal strength threshold, the candidate point on the current local map corresponding to the backward direction of the robot at the current moment is determined as the target point.

[0020] Optionally, determining a current working scene of the system, and determining a target point in the current local map based on the current working scene, includes:

[0021] If the current working scene represents that the robot is moving along the boundary of the working area so as to construct a boundary map of the working area according to the position points of the robot's movement, then the point on the boundary of the working area in the current local map whose distance from its current position is not less than a preset distance and which is closest to the current position is determined as the target point.

[0022] Optionally, determining a current working scene of the system, and determining a target point in the current local map based on the current working scene, includes:

[0023] If the current working scene indicates that the robot is mowing along the boundary of the working area, a point on the boundary of the working area in the current local map whose distance from its current position is not less than a preset distance and which is closest to the current position is determined as the target point.

[0024] Optionally, the moving from the current position to the target point according to the planned target path includes:

[0025] In the process of traveling from the current position to the target point according to the planned target path, judging whether there is a potential collision or direction deviation in the traveling process according to the local map updated in real time;

[0026] If so, the path from the current position of the vehicle to the target point is replanned based on the local map updated in real time, so as to continue to move toward the target point according to the replanned target path.

[0027] In a second aspect, the present application provides an electronic device, including:

[0028] Memory, used to store computer programs;

[0029] A processor is used to execute the computer program to implement the path planning method as described above.

[0030] In a third aspect, the present application provides a computer-readable storage medium for storing a computer program, which implements the path planning method as described above when executed by a processor.

[0031] In a fourth aspect, the present application provides a robot for implementing the path planning method as described above.

[0032] It can be seen that the robot in this application first updates the constructed local map using the recognized perception information to obtain the current local map; then determines its own current working scene, and determines the target point in the current local map based on the current working scene; then performs path planning based on the current local map, its own current position and the target point, so as to travel from the current position to the target point according to the planned target path. In this way, the robot in this application does not need to set up a global map and a corresponding travel path, but directly updates the local map through the point cloud information of the surrounding environment recognized in real time. During the driving process, it can flexibly plan the driving path according to the changes in the surrounding environment and its own current working scene in real time, thereby reducing the failure rate of path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0034] Figure 1 A flow chart of a path planning method disclosed in this application;

[0035] Figure 2 A schematic diagram of a specific obstacle avoidance path planning disclosed in this application;

[0036] Figure 3 This is another specific obstacle avoidance path planning schematic diagram disclosed in this application;

[0037] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, an embodiment of the present invention discloses a path planning method, which is applied to a robot and includes:

[0040] Step S11: Use the recognized perception information to update the constructed local map to obtain the current local map.

[0041] In the embodiment of the present application, the robot does not need to pre-set the global map and the corresponding travel path; the robot can identify the surrounding environment during driving, and then update the constructed local map through the identified point cloud information, and obtain a real-time current local map.

[0042] In a specific embodiment, the use of the recognized perception information to update the constructed local map to obtain the current local map may include: recognizing the semantic information and depth information of the working area boundary and / or obstacles through a visual sensor; marking the semantic information and depth information of the working area boundary and / or obstacles in the constructed local map to update the local map in real time to obtain the current local map. Specifically, the robot can use the visual sensor it carries to recognize the semantic information and depth information of the working area boundary and / or obstacles within a certain range around it, and use this information to construct a local map in real time, marking the semantic information and depth information of the corresponding working area boundary and / or obstacles in the local map, that is, using the real-time recognized point cloud information to update the current local map, and obtain the current local map corresponding to the current position of the lawn mower itself.

[0043] Step S12: determine the current working scene of the system, and determine a target point in the current local map based on the current working scene.

[0044] In an embodiment of the present application, the current local map obtained through real-time updating can determine its current working scene. For example, the current local map represents a working scene in which the robot is moving along a channel, moving along the boundary of a working area, moving along the boundary of a working area to build a boundary map of the working area based on the position point of the robot's movement, and mowing along the boundary of the working area, etc.; in different working scenarios, the robot has different travel path planning, and first determines the target point to be traveled to in the current working scenario based on the current local map.

[0045] In a specific embodiment, determining the current working scene of itself and determining the target point in the current local map based on the current working scene may include: if the current working scene represents that the robot is moving along a channel and the distance between the robot and the obstacle is not greater than a preset distance, then determining several intersection points of the channel and the boundary of the current local map as first candidate points; if the distance between the first candidate point matching the robot's current forward direction and the obstacle position is not less than a preset distance, then determining the corresponding first candidate point as the target point; if the distance between the first candidate point matching the robot's current forward direction and the obstacle position is less than the preset distance, then determining several points on the channel between the first candidate point and the current position of the robot and the distance between the points and the obstacle position is not less than the preset distance as second candidate points, so as to determine the target point with the largest distance from the current position from the several second candidate points. Specifically, if the current local map represents that the robot's current working scene is moving along a channel, and an obstacle is encountered during the movement, and the distance between the robot and the obstacle is not greater than the preset distance, then it is necessary to determine a target point to avoid the obstacle; specifically, several intersection points of the channel and the boundary of the current local map can be determined as first candidate points, and the distance relationship between each first candidate point and the position of the obstacle (there may be multiple obstacles in the channel, obstacles near the robot, and obstacles near the intersection of the channel and the current local map, etc.) is determined. If there is a point among the first candidate points whose distance to the obstacle is not less than the preset distance, it means that the robot will not be affected by the obstacle when it is at this point, and the corresponding point can be determined as the target point; the preset distance here can be understood as a safe distance where the robot is not affected. Correspondingly, if there are no points in the first candidate points whose distance to the obstacle is not less than the preset distance, it means that the robot will still be affected by the obstacles when it is located at these points; even after the robot reaches the first candidate point, it still needs to plan a path to avoid the (new) obstacle; therefore, it is necessary to re-determine the points, and several points between the first candidate points that match the current position of the lawn mower and the forward direction can be determined on the channel, and the points among these points whose distance to the obstacle is not less than the preset distance are determined as the second candidate points; that is, the points whose distance to the obstacle is less than the preset distance are eliminated from several first candidate points, and the remaining points are recorded as the second candidate points; it can be understood that the second candidate points should be points located on the channel, and are located on both sides of the obstacle with the current position of the robot. At this time, when selecting the target point, in order to avoid obstacles, the second candidate point farthest from the current position of the robot can be selected as the target point. In a specific embodiment, if Figure 2As shown, the dotted box is the range of the current local map of the mowing robot, which includes the boundary of the area to be mowed (the boundary of the working area), the obstacle blocking the channel and the mowing robot in the channel. The obstacle blocks the forward position of the mowing robot, and the mowing robot needs to plan a path to avoid the obstacle. At this time, the intersection between the channel and the current local map can be determined, and then a point that matches the forward direction of the mowing robot and is located on the channel is selected as the first candidate point, and then the first candidate point is used as the target point for path planning. Further, if the distance between the first candidate point determined on the channel through the above steps and the obstacle position is less than the preset distance, the target point needs to be re-determined; a number of second candidate points can be determined between the first candidate point on the channel and the current position of the mowing robot, and a new target point is selected according to the distance between the second candidate point and the obstacle position. Specifically, a second candidate point farthest from the current position of the mowing machine is selected from a number of second candidate points whose distance from the obstacle position is not less than the preset distance as the target point, so that the path planning can be performed using the target point, and obstacles can be avoided as much as possible, and the planned path is smoother, and the mowing robot is not easily trapped.

[0046] In another specific embodiment, determining the current working scene of itself and determining the target point in the current local map based on the current working scene may include: if the current working scene represents that the robot is moving along the boundary of the working area, and the distance between the current position of the robot and the obstacle position is not less than a preset distance, then determining a number of third candidate points on the boundary of the working area that intersect with the boundary of the current local map; determining a number of points among the third candidate points whose distances to the obstacle position are not less than the preset distance as fourth candidate points, and determining the target point with the largest distance to the current position from the fourth candidate points; or, if the current working scene represents that the robot is moving along the boundary of the working area, and the satellite positioning signal strength of the robot is less than a preset signal strength threshold, then determining the candidate point on the current local map corresponding to the backward direction of itself at the current moment as the target point. Specifically, if the current local map represents that the current working scene of the robot is moving along the boundary of the working area, the distance between the robot's own position and the obstacle is less than the preset distance, that is, it is necessary to plan a path to avoid the obstacle, then several points where the current local map intersects with the boundary of the working area can be determined as several third candidate points; then, from the several third candidate points, the point whose distance from the current position of the robot is not less than the preset distance is determined as the fourth candidate point, so as to determine the target point farthest from the robot from the several fourth candidate points. It can be understood that when the distance to the obstacle is close, it is easier to plan a path to avoid the obstacle and reduce the probability of collision with the obstacle. Correspondingly, if the robot is moving along the boundary of the working area, but the satellite positioning signal strength gradually weakens with the travel time, when the satellite signal strength is less than the preset signal strength threshold, it is necessary to adjust the robot's driving path to avoid the robot from losing control or being trapped due to the loss of the positioning signal; and because the historical trajectory that the robot has traveled is accurately positioned and is not trapped by obstacles or other things, the point in the backward direction can be selected as the target point. In a specific embodiment, if Figure 3 As shown, the dotted box is the range of the current local map of the mowing robot, which includes the boundary of the area to be mowed, obstacles and the mower. The obstacle blocks the mowing forward position of the mower, and the mower needs to plan a path to avoid the obstacle. At this time, the intersection of the current local map and the boundary of the area to be mowed is determined, that is, Figure 3In order to avoid the failure of path planning, the target point that matches the backward direction of the lawn mower is usually selected for path planning. Of course, the target point that matches the forward direction of the lawn mower can also be selected for path planning. In special cases, walking rules are pre-set, such as moving in a clockwise direction or a counterclockwise direction, etc.; at this time, the corresponding target point can be selected according to the walking rules, and the intersection between the backward direction or the forward direction of the lawn mower and the boundary of the area to be mowed or the local map can be used as the target point according to the walking rules, and then path planning is performed to plan the corresponding path 1 or path 2. It can be understood that when avoiding obstacles, the farther the distance between the selected target point and the current position of the lawn mower is, the easier it is to avoid obstacles, and the planned path is smoother and not easy to get stuck in a dead end.

[0047] In a specific embodiment, the determining of the current working scene of the robot and determining the target point in the current local map based on the current working scene may include: if the current working scene represents that the robot is moving along the boundary of the working area so as to construct the boundary map of the working area according to the position point of the robot, then determining the point on the boundary of the working area in the current local map whose distance from the current position of the robot is not less than the preset distance and whose distance is closest to the current position as the target point. Specifically, if the current local map represents that the current working scene of the robot is moving along the boundary of the working area so as to construct the boundary map of the working area according to the position point of the robot, in order to construct the map, the robot should move slowly little by little to ensure the integrity of the constructed map. Therefore, in this case, the robot can select the target point on the boundary of the working area in the current local map to construct the corresponding boundary map; specifically, select the point on the boundary of the working area whose distance from the current position of the robot is not less than the preset distance and whose distance is closest to the current position of the robot as the target point, so as to construct the map in the process of moving to the target point.

[0048] In another specific embodiment, the determining of the current working scene of the robot and determining the target point in the current local map based on the current working scene may include: if the current working scene indicates that the robot is mowing along the boundary of the working area, a point on the boundary of the working area in the current local map whose distance from the robot's current position is not less than a preset distance and whose distance to the current position is the closest point is determined as the target point. Specifically, if the current local map indicates that the robot's current working scene is mowing along the boundary of the working area, in order to avoid missing grass, the mowing area should be covered to the greatest extent. A point whose distance from the current position of the mowing robot is not less than a preset distance and whose distance to the mowing robot is the closest point can be selected from the current local map and the working area where mowing can be performed on the working area as the target point, so that the mowing area can be covered to the greatest extent and grass can be avoided. It is understandable that when selecting a point during the mowing operation, the pre-set mowing operation conditions can be referred to, such as mowing in a clockwise or counterclockwise direction, selecting a forward direction or a backward direction for patrol mowing, etc.

[0049] Step S13: perform path planning based on the current local map, the current position of the vehicle and the target point, so as to travel from the current position to the target point according to the planned target path.

[0050] Furthermore, after determining the target point that the robot currently needs to travel to through the above steps, path planning can be performed based on the target point, and then the robot travels from the current position to the target point according to the planned target path. It is understandable that path planning can be performed based on a path exploration method based on graph search, or a local path exploration method based on a control space, or a local path exploration method based on a state space, etc.

[0051] Further, in a specific embodiment, the traveling from the current position to the target point according to the planned target path may include: in the process of traveling from the current position to the target point according to the planned target path, judging whether there is a potential collision or direction deviation in the traveling process according to the local map updated in real time; if so, re-planning the path from the current position of the robot to the target point based on the local map updated in real time, so as to continue to travel to the target point according to the re-planned target path. Specifically, in the process of traveling according to the planned target path, the robot may also identify the surrounding environment in real time, update the local map, and judge whether there is a potential collision or direction deviation in the traveling process according to the local map updated in real time. If not, the target point can be reached directly according to the target path, and the path planning is re-performed according to the real-time local map at the target point. Correspondingly, if there is a collision or deviation in the direction during the traveling according to the target path, the robot may stop traveling immediately, and re-plan the path according to the local map updated in real time to correct the current traveling route.

[0052] In this way, the robot in this application does not need to set up a global map or plan a path in advance. The robot can directly update the local map through the point cloud information of the surrounding environment recognized in real time, and then select the corresponding target point according to its own work scene; facing obstacles in the channel, the target point farthest from the current position of the robot can be determined on the channel according to the positional relationship between the current local map and the channel, and the path can be planned to avoid obstacles and avoid collisions in the channel; and when mowing, the target point closest to the current position of the robot is selected based on the preset distance to continue mowing, which can avoid missing grass. It can be seen that the robot in this application can be directly put into operation without setting up a global map and path in advance, and can adjust the corresponding travel path in real time according to changes in the surrounding environment to avoid being affected by obstacles, which can improve the success rate of path planning.

[0053] Furthermore, the present application also discloses an electronic device. Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0054] Figure 4A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the path planning method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0055] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0056] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0057] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the path planning method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0058] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed path planning method. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0059] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0060] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0061] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0062] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0063] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A path planning method, characterized in that: Applications in robots include: Using the recognized perception information, the constructed local map is updated to obtain the current local map; Determine a current working scene of the system, and determine a target point in the current local map based on the current working scene; Path planning is performed based on the current local map, the current position of the vehicle and the target point, so as to travel from the current position to the target point according to the planned target path.

2. The path planning method according to claim 1, characterized in that: The method of updating the constructed local map by using the recognized perception information to obtain the current local map includes: Identify semantic information and depth information of work area boundaries and / or obstacles through visual sensors; The semantic information and depth information of the working area boundary and / or the obstacle are marked in the constructed local map, so as to update the local map in real time to obtain the current local map.

3. The path planning method according to claim 1, characterized in that: The determining of the current working scene of the self, and determining the target point in the current local map based on the current working scene, includes: If the current working scene indicates that the robot is moving along a channel and the distance to the obstacle is not greater than a preset distance, then a plurality of intersection points of the channel and the boundary of the current local map are determined as first candidate points; If the distance between the first candidate point that matches the current forward direction of the robot and the obstacle position is not less than the preset distance, the corresponding first candidate point is determined as the target point; If the distance between the first candidate point that matches the robot's current forward direction and the position of the obstacle is less than the preset distance, then several points on the channel that are between the first candidate point and the robot's current position and whose distance from the obstacle position is not less than the preset distance are determined as second candidate points, so as to determine the target point with the largest distance from the current position from among the several second candidate points.

4. The path planning method according to claim 1, characterized in that: The determining of the current working scene of the self, and determining the target point in the current local map based on the current working scene, includes: If the current working scene indicates that the robot is moving along the boundary of the working area, and the distance between the current position of the robot and the obstacle position is not less than a preset distance, then determining a plurality of third candidate points on the boundary of the working area that intersect with the boundary of the current local map; Determine a plurality of points among the plurality of third candidate points whose distances from the obstacle position are not less than the preset distance as fourth candidate points, and determine a target point whose distance from the current position is the largest from the plurality of fourth candidate points; Alternatively, if the current working scene indicates that the robot is moving along the boundary of the working area, and the satellite positioning signal strength of the robot is less than a preset signal strength threshold, the candidate point on the current local map corresponding to the backward direction of the robot at the current moment is determined as the target point.

5. The path planning method according to claim 1, characterized in that: The determining of the current working scene of the self, and determining the target point in the current local map based on the current working scene, includes: If the current working scene represents that the robot is moving along the boundary of the working area, in order to construct a boundary map of the working area according to the position points of the robot's movement, the point on the boundary of the working area in the current local map whose distance from its current position is not less than a preset distance and which is closest to the current position is determined as the target point.

6. The path planning method according to claim 1, characterized in that: The determining of the current working scene of the self, and determining the target point in the current local map based on the current working scene, includes: If the current working scene indicates that the robot is mowing along the boundary of the working area, a point on the boundary of the working area in the current local map whose distance from its current position is not less than a preset distance and which is closest to the current position is determined as the target point.

7. The path planning method according to any one of claims 1 to 6, characterized in that: The moving from the current position to the target point according to the planned target path includes: In the process of traveling from the current position to the target point according to the planned target path, judging whether there is a potential collision or direction deviation in the traveling process according to the local map updated in real time; If so, the path from the current position of the vehicle to the target point is replanned based on the local map updated in real time, so as to continue to move toward the target point according to the replanned target path.

8. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the path planning method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the path planning method according to any one of claims 1 to 7.

10. A robot, characterized in that: Used to implement the path planning method as described in any one of claims 1 to 7.

Images