Path Planning Method and Apparatus, Robot, and Computer Readable Storage Medium

Abstract

The present application provides a path planning method, a path planning device, a robot, and a computer-readable storage medium. The method includes obtaining a preset map, where the map includes multiple path points and paths connecting any two adjacent path points; planning, according to the distances of the paths and the position information of all robots in the map, a target route for each robot to move from a starting path point to an ending path point. By obtaining the path points in the preset map and the paths connecting two adjacent path points, and determining the distance of each path, when planning the path from the starting path point to the ending path point, not only the distance of the path is considered, but also the position information of all robots in the map is considered, and the target route can be dynamically planned according to the distance of the path and the positions of other robots, thereby facilitating avoiding the impacts brought by robot avoidance and waiting caused by route overlap when multiple robots are running.

Description

Technical Field

[0001] This application relates to the technical field of path planning, and particularly relates to a path planning method and apparatus, a robot, and a computer-readable storage medium. Background Art

[0002] The existing path planning technology for unmanned forklifts mainly uses algorithms based on fixed path maps for path planning. The main technical process is as follows: 1) Set a path map containing fixed path segments and set the energy consumption value (cost value) for each path segment, usually equal to the length of the path; 2) Based on planning algorithms such as Dijkstra's algorithm and A-Star, calculate the path with the minimum energy consumption value for the vehicle to complete a task to complete path planning. The main limitation of the existing technology is that it only considers the shortest path of a single vehicle and does not take into account the impact of vehicle avoidance and waiting caused by path overlap during multi-vehicle operation. Summary of the Invention

[0003] In view of this, the embodiments of this application provide a path planning method and apparatus, a robot, and a computer-readable storage medium. By using the distance of the path and the position information of all robots in the map, the target route is comprehensively planned, which helps to avoid the impact of vehicle avoidance and waiting caused by route overlap during multi-vehicle operation.

[0004] The path planning method of the embodiments of this application includes obtaining a preset map, where the map includes multiple path points and paths connecting any two adjacent path points; determining the loss value of the path according to the distance of the path and the position information of all robots in the map, and planning the target route for each robot to move from the starting path point to the ending path point according to the loss value of the path, where the starting path point is any one of the path points, and the ending path point is any one of the path points other than the starting path point.

[0005] The path planning apparatus of the embodiments of this application includes an obtaining module and a planning module. The obtaining module is used to obtain a preset map, where the map includes multiple path points and paths connecting any two adjacent path points; the planning module is used to determine the loss value of the path according to the distance of the path and the position information of all robots in the map, and plan the target route for each robot to move from the starting path point to the ending path point according to the loss value of the path, where the starting path point is any one of the path points, and the ending path point is any one of the path points other than the starting path point.

[0006] The robot according to the embodiment of the present application includes a processor, and the processor is configured to obtain a preset map, where the map includes a plurality of path points and paths connecting any two adjacent path points; determine a loss value of a path according to the distance of the path and the position information of all robots in the map, and plan a target route for each robot to move from a starting path point to an ending path point according to the loss value of the path, where the starting path point is any one of the path points, and the ending path point is any one of the path points other than the starting path point.

[0007] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, a path planning method is implemented. The path planning method includes obtaining a preset map, where the map includes a plurality of path points and paths connecting any two adjacent path points; determining a loss value of a path according to the distance of the path and the position information of all robots in the map, and planning a target route for each robot to move from a starting path point to an ending path point according to the loss value of the path, where the starting path point is any one of the path points, and the ending path point is any one of the path points other than the starting path point.

[0008] The path planning method, device, robot, and computer-readable storage medium of the present application obtain the path points in a preset map and the paths connecting two adjacent path points, and determine the distance of each path. When planning the path from the starting path point to the ending path point, not only the distance of the path is considered, but also the position information of all robots in the map is considered. Therefore, when planning the target route of the current robot, the loss value of each path can be determined according to the distance of the path and the positions of other robots, and the target route can be dynamically planned according to the loss value of the path, which is beneficial to avoiding the influence caused by the route overlap of multiple robots during operation and the resulting robot avoidance and waiting.

[0009] The additional aspects and advantages of the embodiments of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. Description of the Drawings

[0010] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0011] Figure 1 is a flowchart of a path planning method according to some embodiments of the present application;

[0012] Figure 2 is a scenario diagram of a path planning method according to some embodiments of the present application;

[0013] Figure 3 is a schematic flowchart of a path planning method according to some embodiments of the present application;

[0014] Figure 4 is a schematic diagram of modules of a path planning device according to some embodiments of the present application;

[0015] Figure 5 is a schematic plan view of a robot according to some embodiments of the present application; and

[0016] Figure 6 is a schematic diagram of the interaction between a computer-readable storage medium and a processor according to some embodiments of the present application. Specific Embodiments

[0017] The following describes in detail the embodiments of the present application. The examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application and should not be construed as a limitation to the embodiments of the present application.

[0018] First, the terms appearing in the present application are explained below:

[0019] Dijkstra algorithm: It is an algorithm for finding the shortest paths from a vertex to the remaining vertices, which solves the problem of the shortest path in a weighted graph. The main feature of the Dijkstra algorithm is that starting from the starting point, adopting the strategy of the greedy algorithm, each time it traverses the adjacent nodes of the vertex that is closest to the starting point and has not been visited until it expands to the end point.

[0020] A-Star algorithm: It is a most effective direct search method for finding the shortest path in a static road network.

[0021] Automated Guided Vehicle (AGV): It refers to a transport vehicle equipped with automatic navigation devices such as electromagnetic or optical ones, which can travel along a specified navigation path, has safety protection and various loading and unloading functions. In industrial applications, it is a forklift without a driver, and its power source is a rechargeable battery. Generally, its traveling path and behavior can be controlled by a computer, or its traveling path can be set up by using an electromagnetic track, and the electromagnetic track is pasted on the floor, and the forklift relies on the information brought by the electromagnetic track to move and act.

[0022] Please refer to Figure 1 , the path planning method of the embodiments of the present application includes:

[0023] Step 011: Obtain a preset map, where the map includes multiple path points and paths connecting any two adjacent path points;

[0024] Specifically, in order to accurately perform path planning, for the scenario of path planning, it is necessary to first obtain the map of the scenario. For a preset warehouse, the paths are fixed. Therefore, the path points in the map of the preset warehouse and the paths connecting adjacent two path points can be marked in advance. By establishing a high-precision map of the scenario, the accuracy of path planning can be improved.

[0025] Step 012: Determine the loss value of the path according to the distance of the path and the position information of all robots in the map, and plan the target route for each robot to move from the starting path point to the ending path point according to the loss value of the path. The starting path point is any path point, and the ending path point is any path point other than the starting path point.

[0026] Specifically, generally, when existing path planning methods perform path planning, they only need to consider the distance of the path, calculate the loss value of the path through the distance of the path, and the distance of the path is proportional to the loss value of the path. Thus, path planning is carried out according to the loss value of the path, and the route with the smallest total loss value is obtained as the planned route.

[0027] It can be understood that for some paths in the map, due to the width limitation of the path or the obstruction of fixed objects around the path, the path only allows one robot to pass at the same time. When there is a robot on the path, it is determined that the path is occupied. If the path allows a predetermined number (such as 2, 3, etc.) of robots to pass, then when there are a predetermined number of robots on the path, it is determined that the path is occupied. This application takes the example that the path in the map only allows one robot to pass. When there is a robot in the path, it is determined that the path is occupied. When two or more robots are moving relatively along this path, one robot needs to wait for the other robot to pass before it can pass the path; or when two or more robots are moving in the same direction, the two robots can follow in sequence to pass the path, but during following, due to the different driving speeds of multiple robots, the robot driving behind may need to wait for the robot in front, affecting the task execution efficiency of the robot behind.

[0028] Therefore, when performing path planning for the current robot, it is necessary to consider the positions of other robots in the map (that is, robots other than the current robot in the map). When the path is occupied by other robots, the loss value of the occupied path can be updated in time (such as increasing the loss value of the occupied path), so as to accurately plan the target route according to the updated loss value of each path (the target route is the route with the smallest total loss value among all routes connecting the starting path point and the ending path point), thus preventing the current robot from wasting too much time waiting for other robots to leave the occupied path and ensuring the task execution efficiency of the robot.

[0029] Of course, even if the loss value of the occupied path is increased, the re-planned target route may still include occupied paths. In this case, the current robot needs to wait for other robots in the occupied path to pass and then pass through the occupied path again, so as to always ensure that the total loss value of the target route is minimized and maximize the task execution efficiency of each robot.

[0030] Therefore, when planning the target route, considering the distance of the path and the position information of all robots in the map comprehensively, when other robots occupy the path that the current robot is about to travel, the current robot can dynamically re-plan the target route, avoid the occupied path, and continue to execute the task using a target route that takes less time.

[0031] As Figure 2 shown, the path points of the map include path point 1 to path point 7. The starting path point and the ending path point of the current robot M1 are path point 1 and path point 7 respectively. When all paths are not occupied, the loss value of all paths is the distance of the path. At this time, the planned target route is 1-2-4-5-7, and the total loss value of the planned target route at this time is 40 meters (m). However, when the current robot M1 moves to path point 4, path 4-5 is occupied by robot M2 and moving towards path point 4. At this time, if the path is planned in the existing way and continue to move according to the target route 1-2-4-5-7, it is necessary to wait for robot M2 in path 4-5 to pass and then pass through path 4-5. In the present application, when the current robot M1 moves to path point 4 and path 4-5 is occupied by robot M2, the loss value of path 4-5 will be updated, such as increasing the loss value of path 4-5 (increasing the original loss value of path 4-5 of 10m to 20m), so as to convert the time for the current robot M1 to wait due to the occupation of path 4-5 into the updated loss value of path 4-5. According to the updated loss value, the target route is re-planned. At this time, the target route is updated to 1-2-4-6-7 (the total loss value is 45m, which is the route with the smallest total loss value among all the routes connecting path point 1 and path point 7). Compared with the total loss value of the original target route 1-2-4-5-7, which becomes 50m, the total loss value is smaller, thus avoiding the current robot M1 waiting for other robots for too much time and realizing the dynamic planning of the target route of the current robot M1.

[0032] The path planning method of this application obtains the path points in the preset map and the paths connecting adjacent two path points, and determines the distance of each path. When planning the path from the starting path point to the ending path point, it not only considers the distance of the path, but also considers the position information of all robots in the map. Therefore, when planning the target route of the current robot, it can determine the loss value of each path according to the distance of the path and the positions of other robots, and dynamically plan the target route according to the loss value of the path, which is beneficial to avoiding the influence caused by the avoidance and waiting of robots due to the overlapping of routes when multiple robots are running.

[0033] Please refer to Figure 3 , optionally, step 012: Determine the loss value of the path according to the distance of the path and the position information of all robots in the map, and plan the target route for each robot to move from the starting path point to the ending path point, which may include:

[0034] Step 0121: Calculate the initial loss value of the path according to the distance of the path;

[0035] Step 0122: Plan the initial route for each robot to move from the starting path point to the ending path point according to the initial loss value of the path;

[0036] Step 0123: Calculate the updated loss value of the path according to the initial loss value of the path, the current route of each robot, and the position information of all robots in the map. The current route includes the initial route or the target route of the previous path planning;

[0037] Step 0124: Based on the preset path planning algorithm and the updated loss value of the path, plan the target route for each robot to move from the starting path point to the ending path point. Among all the routes connecting the starting path point and the ending path point, the sum of the loss values of all the paths included in the target route is the smallest.

[0038] Specifically, the loss value of the path includes the initial loss value and the updated loss value. In the initial state, the initial loss value and the updated loss value are the same. That is to say, when the path is not occupied, the updated loss value is equal to the initial loss value. Each path includes the initial loss value of the path obtained according to the distance of the path, such as the distance of the path is equal to the initial loss value of the path.

[0039] Then, when the current robot is at the starting path point, the initial route of the current robot can be planned according to the initial loss value of each path. At this time, the current route of the robot is the initial route, and the initial route is the route with the minimum total initial loss value among all the routes connecting the starting path point and the ending path point. Then, during the movement of the current robot, the position of the robot in the map is obtained in real time to determine the path occupancy information (such as whether it is occupied. In the case where there is a robot in the path, it means the path is occupied).

[0040] After that, according to the initial route, determine the moving direction of the current robot when moving on each path of the initial path. In the case where the current path corresponding to the current path point where the current robot is located is occupied, calculate the updated loss value of the current path according to the initial loss value of the current path, the moving direction of the robot located on the current path, and the moving direction of the current robot.

[0041] Of course, the current route of the current robot may not be the initial route, but the target route obtained after the previous path planning. At this time, the moving direction of the current robot on each path of the current route can be determined according to the current route.

[0042] Please combine Figure 2

[0043]

[0044] It can be understood that when calculating the updated loss value of the path, only the current path corresponding to the current path point where the current robot M1 is located needs to be considered (for example, when the current robot M1 is located at path point 4, only need to consider whether the current paths 4-5 and 4-6 are occupied), and there is no need to consider whether the subsequent paths are occupied (such as paths 5-7, 6-7, etc.). Because, after the current robot M1 passes through path 4-5 or path 4-6, paths 5-7 and 6-7 may no longer be occupied. Therefore, the updated loss value of the path in this application is real-time. In the case where the path is no longer occupied, the updated loss value of the path will immediately return to the initial loss value of the path. For example, when the current robot M1 moves to path point 4 (i.e., the current path point is path point 4), it will determine whether the current paths 4-5 and 4-6 corresponding to path point 4 are occupied according to the positions of other robots in the map. And taking the initial route of the current robot M1 as 1-2-4-5-7 as an example, it can be determined that the moving direction of the current robot M1 on the current path 4-5 is from path point 4 to path point 5.Then, compare the moving direction of the current robot M1 with the moving direction of the robot located on the current path (hereinafter referred to as the occupied robot M2) (the moving direction of the occupied robot M2 can also be determined according to the current route of the occupied robot M2). If the moving direction of the occupied robot M2 is the same as that of the current robot M1, it means that the current robot M1 can follow the occupied robot M2. The current robot M1 may have to decelerate or wait because its speed is greater than that of the occupied robot M2, resulting in a delay in the time for the current robot M1 to reach the termination path point 7. Of course, it is also possible that the speed of the occupied robot M2 is greater than that of the current robot M1, and the time for the current robot M1 to reach the termination path point 7 is not affected. Therefore, the updated loss value of the current path can be determined according to the smaller first preset magnification and the initial loss value of the current path (e.g., the updated loss value of the current path = the first preset magnification * the initial loss value of the current path). For example, the first preset magnification is 1.1, 1.2, etc., so as to transfer the risk that the current path is occupied and the current robot M1 needs to follow and may cause a delay in the time for the current robot M1 to reach the termination path point 7 to the loss value of the current path.

[0045] If the moving direction of the occupied robot M2 is opposite to that of the current robot M1, it means that the current robot M1 must wait for the occupied robot M2 to pass before it can enter path 4-5. At this time, the waiting time can be determined to be relatively long (i.e., the time for the occupied robot M2 to pass through path 4-5). For example, if the occupied robot M2 is at path point 5, the waiting time reaches the longest, that is, the time required for the occupied robot M2 to move from path point 4 to path point 5; if the occupied robot M2 is between path 4-5, the waiting time will be reduced; it can be understood that the closer the occupied robot M2 is to path point 4 (i.e., the closer to the current path point where the current robot M1 is located), the shorter the waiting time. At this time, the risk that the current path is occupied and the current robot M1 needs to wait for the occupied robot M2 to pass, resulting in a delay in the time for the current robot M1 to reach the termination path point 7, can be transferred to the loss value of the current path. Therefore, at this time, the updated loss value can be calculated according to the larger second preset magnification and the initial loss value of the current path (e.g., the updated loss value of the current path = the second preset magnification * the initial loss value of the current path). Since the current robot M1 almost certainly needs to wait for a certain period of time at this time, the second preset magnification can be set relatively large (e.g., greater than the first preset magnification), such as 1.5, 2, etc. Of course, the second preset magnification can also be determined according to the distance between the occupied robot M2 and the current path point where the current robot M1 is located. The smaller this distance is, the smaller the second preset magnification is, so as to accurately determine the second preset magnification and ensure the accuracy of path planning. In this way, the updated loss value of each path in the map can be obtained.

[0046] Optionally, when calculating the updated loss value of an occupied path, the width of the occupied path can be considered. If the width of the occupied path is greater than a preset width (such as the width that allows two robots to pass through simultaneously), at this time, the two robots can move relatively or in the same direction without affecting each other. At this time, the updated loss value of the occupied path can be directly calculated based on the initial loss value of the occupied path, that is, the updated loss value of the occupied path is equal to the initial loss value of the occupied path. Of course, the preset width can also be calculated in real time. For example, according to the current routes and position information of the robots in the map, it can be determined that the occupied path currently needs to pass a predetermined number (such as 3, 4, etc.) of robots, then the preset width is equal to the width that the preset number of robots can pass through simultaneously.

[0047] Finally, according to the preset path planning algorithm (such as A-Star algorithm, Dijkstra algorithm, etc.) and the updated loss values of all paths in the map, the target route for the current robot M1 to move from the starting path point 1 to the ending path point 7 is planned, so that the sum of the loss values (specifically, the updated loss values) of all paths included in the target route is minimized, ensuring the task execution efficiency of the current robot M1, where the current robot M1 can be any one of all the robots.

[0048] Please refer to Figure 4 , to facilitate better implementation of the path planning method of the embodiments of the present application, the embodiments of the present application also provide a path planning device 10. The path planning device 10 may include:

[0049] An acquisition module 11, configured to acquire a preset map, where the map includes multiple path points and paths connecting any two adjacent path points;

[0050] A planning module 12, configured to determine the loss value of a path according to the distance of the path and the position information of all robots in the map, and plan the target route for each robot to move from the starting path point to the ending path point according to the loss value of the path, where the starting path point is any path point, and the ending path point is any path point other than the starting path point.

[0051] Specifically, the planning module 12 is configured to calculate the initial loss value of a path according to the distance of the path; plan the initial route for each robot to move from the starting path point to the ending path point according to the initial loss value of the path; calculate the updated loss value of the path according to the initial loss value of the path, the current route of each robot, and the position information of all robots in the map, where the target route includes the initial route or the target route of the previous path planning; and plan the target route for each robot to move from the starting path point to the ending path point based on the preset path planning algorithm and the updated loss value of the path, so that the sum of the loss values of all paths included in the target route is minimized.

[0052] The planning module 12 is further specifically configured to determine the moving direction of each path in the corresponding current route for each robot according to the initial route of each robot; determine the occupied information of all paths in the map according to the position information of all robots in the map; when the current path corresponding to the current path point where the current robot is located is occupied, calculate the updated loss value of the current path according to the initial loss value of the current path, the moving direction of the robot located on the current path, and the moving direction of the current robot.

[0053] The planning module 12 is further specifically configured to, when the moving direction of the robot located on the current path is the same as the moving direction of the current robot, determine the updated loss value of the current path according to the first preset magnification and the initial loss value of the current path; when the moving direction of the robot located on the current path is opposite to the moving direction of the current robot, determine the updated loss value of the current path according to the second preset magnification and the initial loss value of the current path, where the second preset magnification is greater than the first preset magnification.

[0054] The planning module 12 is further specifically configured to, when the current path is not occupied, determine that the updated loss value of the current path is equal to the initial loss value of the current path.

[0055] The planning module 12 is further specifically configured to, when the current path is no longer occupied, restore the updated loss value of the current path to the initial loss value of the current path.

[0056] Each module in the above path planning device 10 can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor 20 in the computer device in the form of hardware or be independent of the processor 20, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor 20 to call and execute the operations corresponding to each of the above modules.

[0057] Please refer to Figure 5 , the robot 100 in the embodiment of the present application includes a processor 20. The processor 20 is configured to execute the path planning method in any of the above embodiments. For the sake of brevity, it will not be elaborated here.

[0058] Among them, the robot 100 can be a device with moving ability such as an AGV, a clamping vehicle, a tractor, a stacking machine, a reach stacker, a warehousing robot, etc.

[0059] Please refer to Figure 6 , the embodiment of the present application further provides a computer-readable storage medium 300, on which a computer program 310 is stored. When the computer program 310 is executed by the processor 20, the steps of the path planning method in any of the above embodiments are implemented. For the sake of brevity, it will not be elaborated here.

[0060] It can be understood that the computer program 310 includes computer program code. The computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium can be a non-volatile computer-readable storage medium such as any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution medium, etc.

[0061] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0062] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0063] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A path planning method, characterized in that, Including: Obtain a preset map, where the map includes multiple waypoints and paths connecting any two adjacent waypoints; Determine the loss value of a path according to the distance of the path and the position information of all robots in the map, and plan a target route for each robot to move from a starting waypoint to an ending waypoint according to the loss value of the path, where the starting waypoint is any one of the waypoints, and the ending waypoint is any one of the waypoints other than the starting waypoint; The loss value of the path includes the initial loss value of the path and the updated loss value of the path. Determining the loss value of the path according to the distance of the path and the position information of all robots in the map, and planning a target route for each robot to move from a starting waypoint to an ending waypoint includes: Calculate the initial loss value of the path according to the distance of the path; Plan an initial route for each robot to move from the starting waypoint to the ending waypoint according to the initial loss value of the path; Calculate the updated loss value of the path according to the initial loss value of the path, the current route of each robot, and the position information of all robots in the map, where the current route includes the initial route or the target route of the previous path planning; Based on a preset path planning algorithm and the updated loss value of the path, plan the target route for each robot to move from the starting waypoint to the ending waypoint. Among all the routes connecting the starting waypoint and the ending waypoint, the sum of the loss values of all the paths included in the target route is the smallest.

2. The path planning method according to claim 1, wherein The path only allows a single robot to pass through. In the case where there is a robot on the path, it is determined that the path is occupied. Calculating the updated loss value of the path according to the initial loss value of the path, the current route of each robot, and the position information of all robots in the map includes: Determine the moving direction of each robot on each path in the corresponding target route according to the current route of each robot; Determine the occupied information of all paths in the map according to the position information of all robots in the map; In the case where the current path corresponding to the current waypoint where the current robot is located is occupied, calculate the updated loss value of the current path according to the initial loss value of the current path, the moving direction of the robot located on the current path, and the moving direction of the current robot.

3. The path planning method according to claim 2, wherein Calculating the updated loss value of the current path according to the initial loss value of the current path, the moving direction of the robot located on the current path, and the moving direction of the current robot includes: In the case where the moving direction of the robot located on the current path is the same as the moving direction of the current robot, determine the updated loss value of the current path according to a first preset magnification factor and the initial loss value of the current path; When the moving direction of the robot located at the current path is opposite to the moving direction of the current robot, determine the updated loss value of the current path according to a second preset magnification factor and the initial loss value of the current path, where the second preset magnification factor is greater than the first preset magnification factor.

4. The path planning method according to claim 3, wherein The first preset magnification factor is 1.1, and the second preset magnification factor is 2.

5. The path planning method according to claim 2, wherein Calculating the updated loss value of the path according to the initial loss value of the path, the current routes of each robot, and the position information of all the robots in the map further includes: When the current path is not occupied, determine that the updated loss value of the current path is equal to the initial loss value of the current path.

6. The path planning method according to claim 2, wherein Further includes: When the current path is no longer occupied, restore the updated loss value of the current path to the initial loss value of the current path.

7. A path planning device, characterized in that Includes: An acquisition module, configured to acquire a preset map, where the map includes a plurality of path points and paths connecting any two adjacent path points; A planning module, configured to plan a target route for each robot to move from a starting path point to an ending path point according to the distance of the path and the position information of all the robots in the map, where the starting path point is any one of the path points, and the ending path point is any one of the path points other than the starting path point; The loss value of the path includes the initial loss value of the path and the updated loss value of the path. The planning module is further configured to plan an initial route for each robot to move from the starting path point to the ending path point according to the initial loss value of the path; calculate the updated loss value of the path according to the initial loss value of the path, the current route of each robot, and the position information of all the robots in the map, where the current route includes the initial route or the target route of the previous path planning; Based on a preset path planning algorithm and the updated loss value of the path, plan the target route for each robot to move from the starting path point to the ending path point. Among all the routes connecting the starting path point and the ending path point, the sum of the loss values of all the paths included in the target route is the smallest.

8. A robot, characterized in that, Includes a processor, and the processor is configured to execute the path planning method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, Contains a computer program, and when the computer program is executed by one or more processors, it realizes the execution of the path planning method according to any one of claims 1-6.

Images