Multi-robot path planning methods, devices, equipment and media
By reusing historical motion path points in a multi-robot system, a locally stable motion path is constructed, which solves the stability and executability problems of path planning in dynamic environments and improves the stability and executability of path planning.
Patent Information
- Application Number
- CN202311500477.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-10
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-11-10
AI Technical Summary
In multi-robot systems, frequent changes in the dynamic environment lead to the replanning of motion paths for each robot, resulting in poor path stability and affecting executability.
By acquiring the robot's historical motion paths, extracting multiple consecutive available path points, constructing local motion paths, and determining a second local motion path from the last path point as a new starting point to the destination, the target motion path is generated by combining the two, thus reducing the frequency of path updates.
This improves the stability and feasibility of robot motion paths and reduces instability issues caused by frequent path updates due to environmental changes.
Smart Images

Figure CN117406740B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of path planning technology, and in particular to a multi-robot path planning method, apparatus, device, and medium. Background Technology
[0002] With the development of robotics technology, multi-robot systems, compared to single robots, offer superior autonomous mobility, flexibility, and robustness, and are widely used in various fields, such as logistics, handling, cleaning, and other service industries. When multiple robots work collaboratively, multi-robot path planning—that is, finding motion paths that allow robots to reach the target work point quickly without conflict—has become a crucial issue.
[0003] Currently, multi-robot path planning generally relies on conflict-based search algorithms to find a path for each robot that does not conflict with other robots. However, in practical applications, the environment for multi-robot systems is dynamically changing, and each time the environment changes, a new path needs to be planned for each robot. Therefore, with frequent changes in the application environment, the number of times a new path needs to be planned for each robot increases. This frequent updating of robot paths leads to poor stability of the planned paths, resulting in poor executability. Summary of the Invention
[0004] This application provides a multi-robot path planning method, apparatus, device, and medium, which can improve the stability of the motion path planned for the robot, thereby enhancing the executability of the motion path.
[0005] In a first aspect, embodiments of this application provide a multi-robot path planning method, including:
[0006] In response to a path planning request sent by any robot, the target historical motion path of the robot is obtained, wherein the path planning request includes a motion start point and a motion end point;
[0007] From the target's historical motion path, obtain a series of first available path points starting from the motion starting point, and obtain a first local motion path based on the series of first available path points;
[0008] Using the last of the multiple first available path points as the new starting point, a second local motion path is determined from the new starting point to the end point.
[0009] The target motion path of the robot is obtained based on the first local motion path and the second local motion path.
[0010] Secondly, embodiments of this application provide a multi-robot path planning device, comprising:
[0011] The acquisition module is used to acquire the target historical motion path of the robot in response to a path planning request sent by any robot, wherein the path planning request includes a motion start point and a motion end point;
[0012] The first determining module is used to obtain a plurality of consecutive first available path points starting from the starting point of the movement from the target's historical movement path, and to obtain a first local movement path based on the plurality of first available path points;
[0013] The second determining module is used to determine a second local motion path from the new motion starting point to the motion ending point, taking the last of the multiple first available path points as the new motion starting point;
[0014] The path planning module is used to obtain the target motion path of the robot based on the first local motion path and the second local motion path.
[0015] Thirdly, embodiments of this application provide an electronic device, including:
[0016] A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to perform the multi-robot path planning method as described in the first aspect embodiment or its various implementations.
[0017] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a computer program that causes a computer to perform the multi-robot path planning method as described in the first aspect embodiment or its various implementations.
[0018] Fifthly, embodiments of this application provide a computer program product containing program instructions that, when executed on an electronic device, cause the electronic device to perform the multi-robot path planning method as described in the first aspect embodiment or its various implementations.
[0019] The technical solution disclosed in this application involves obtaining a target historical motion path corresponding to the path planning request from the robot's historical motion paths based on the path planning request sent by the robot. Then, multiple consecutive first available path points starting from the starting point are obtained from the target historical motion path to form a first local motion path. Next, the last first available path point is used as the new starting point to determine a second local motion path from the new starting point to the ending point. Finally, the target motion path of the robot is obtained based on the first and second local motion paths. Therefore, by reusing multiple consecutive path points from the robot's historical motion path, the local paths in the planned motion path for the robot are stable and do not jump, thereby improving the stability and executability of the planned motion path. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 A flowchart illustrating a multi-robot path planning method provided in this application embodiment;
[0022] Figure 2 A flowchart for obtaining multiple first available path points is provided in an embodiment of this application;
[0023] Figure 3 A flowchart for determining a second local motion path is provided in an embodiment of this application;
[0024] Figure 4 A flowchart illustrating another multi-robot path planning method provided in this application embodiment;
[0025] Figure 5 A schematic block diagram of a multi-robot path planning device provided in an embodiment of this application;
[0026] Figure 6 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.
[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.
[0029] In this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or solution described as "exemplary" or "for example" in this application should not be construed as being better or more advantageous than other embodiments or solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0030] In the description of the embodiments in this application, unless otherwise stated, "multiple" means two or more, that is, at least two. "At least one" means one or more. "Any" means one or more.
[0031] Because the environment for multi-robot applications is dynamic, previously planned motion paths become unusable whenever the environment changes. Therefore, a new motion path needs to be planned for each robot when the environment changes. However, when the environment changes frequently, the number of times a new motion path needs to be planned for each robot also increases. This frequent updating of robot motion paths leads to poor stability of the planned motion paths and consequently, poor executability.
[0032] To address the aforementioned technical problems, the inventive concept of this application is as follows: based on the received path planning request, a target historical motion path corresponding to the path planning request is obtained, and multiple consecutive available path points starting from the starting point are obtained from the target historical motion path. Then, a first local motion path is generated based on the multiple available path points. Next, a second local motion path from the new starting point to the end point is determined using the last available path point among the multiple available path points as the new starting point. Finally, the target motion path is obtained based on the first and second local motion paths. By reusing multiple consecutive path points in the robot's historical motion path, a locally stable and unchanging available path is generated, thereby improving the stability of the motion path planned for the robot and enhancing the executability of the motion path.
[0033] The technical solutions of this application will be described in detail below through some embodiments. The embodiments described below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.
[0034] Figure 1 This is a flowchart illustrating a multi-robot path planning method provided in an embodiment of this application. The multi-robot path planning method provided in this application can be executed by a multi-robot path planning device. This device can consist of hardware and / or software and can be integrated into an electronic device. In this application, the electronic device can be any type of server, such as a cloud server or a traditional server; this application does not impose any limitations on the type of electronic device.
[0035] like Figure 1 As shown, the method includes the following steps:
[0036] S101, in response to a path planning request sent by any robot, obtain the robot's target historical motion path. The path planning request includes the starting point and the ending point of the motion.
[0037] It should be understood that the path planning request sent by any robot mentioned above can be a request to the electronic device to replan the motion path when a change in the application environment causes the robot to be unable to continue moving according to the previously planned motion path. For example, when a robot is performing a corresponding task according to the planned motion path, it detects an obstacle on the motion path, and the obstacle prevents the robot from continuing to move forward. At this time, the robot can send a path planning request to the electronic device to replan the motion path.
[0038] The format of the above path planning request can be: robot identification information + path planning request, etc., and this application does not impose any restrictions on it.
[0039] The identification information of the robot mentioned above can be information that can uniquely identify the robot, such as robot number or robot serial number, and this application does not impose any restrictions on this.
[0040] In some alternative embodiments, upon receiving a request to replan a motion path from any robot, each path planning request can be parsed to obtain the robot's starting and ending points. Then, using a path search algorithm, a new, feasible motion path is replanned for each robot based on the starting and ending points.
[0041] In this application, the path search algorithm can be selected as the shortest path search algorithm, such as breadth-first search algorithm, A* algorithm and Dijkstra's algorithm.
[0042] In some alternative embodiments, considering that multiple robots can work collaboratively, they can send real-time path planning requests to the electronic device asynchronously or synchronously. For example, robot A might initiate a new path planning request immediately after completing its first action based on a motion path. Therefore, to accommodate both asynchronous and synchronous path planning requests from multiple robots and to achieve real-time path planning, this application sets up a path request cache pool on the electronic device side to cache real-time path planning requests sent by any robot. Thus, when the electronic device performs path planning, it can employ a centralized path planning algorithm to continuously process the cached path planning requests in the path request cache pool at a high frequency (e.g., every 500 milliseconds or every second) to achieve real-time path planning.
[0043] In this application, the path planning request cache pool can also update the stored path planning requests at a high frequency (e.g., every 500 milliseconds or every 1 second) to meet the real-time requirements of path planning.
[0044] Optionally, when performing path planning, the electronic device first caches all path planning requests from the end time of the previous path planning to the start time of the current path planning in a path request cache pool. Next, it parses all path planning requests in the cache pool to obtain the motion start point, motion end point, and robot identification information sent by each robot from each request, thus laying the foundation for real-time path planning for each robot.
[0045] Considering that multiple robots may have performed tasks multiple times in the application environment, each robot will have multiple historical motion paths. Therefore, to reduce or even avoid the problem of poor stability in the planned motion paths caused by frequent changes in the application environment and frequent updates to the robot's motion paths, this application obtains the motion start point, motion end point, and robot identification information from the path planning request. Based on the robot's identification information, it can determine all historical motion paths corresponding to that identification information. Next, based on the motion start point and motion end point, it determines the target historical motion path from all historical motion paths. Furthermore, it obtains multiple reusable path points from the target historical motion path. By reusing multiple path points from the historical motion paths to replan the target motion path for the robot, the stability of the robot's motion path can be improved.
[0046] The starting point of the target historical motion path is the robot's starting point, and the ending point of the target historical motion path is the robot's ending point.
[0047] S102, obtain multiple consecutive first available path points starting from the starting point of the movement from the target's historical movement path, and obtain a first local movement path based on the multiple first available path points.
[0048] Considering that the time information of each path point in the target's historical motion path is not the same as the trigger time of the current path planning, when this application obtains multiple reusable path points (i.e., the first available path points) from the target's historical motion path, it can perform time shifting on the time information of each path point in the target's historical motion path according to the current path planning time, so that the time information of each path point in the target's historical motion path corresponds to the current path planning time.
[0049] It should be understood that the above path points include: location information and a timestamp when the robot moves to that location. For example, if a path point is ((4,6), 5), then (4,6) represents the location information of that path point, and 5 represents the timestamp when the robot moves to the location information (4,6) at the 5th second.
[0050] The aforementioned time shifting of the time information of each path point in the target's historical movement path can be achieved by determining the time difference between the planning end time of the target's historical movement path and the trigger time of the current path planning. Then, this time difference is added to the time information of each path point in the target's historical movement path, thereby realizing the time shifting operation of the time information of each path point in the target's historical movement path.
[0051] Further, in the time-shifted target historical motion path, available path points are searched starting from the motion start point. When a plurality of consecutive available path points starting from the motion start point are found, the plurality of available path points are taken as a plurality of first available path points, and a first local motion path of the robot is constructed based on the plurality of first available path points.
[0052] It should be understood that the first available path points may be understood as path points that are not used by other robots.
[0053] In this application, constructing the first local motion path of the robot based on the plurality of first available path points is specifically to sort the plurality of first available path points in chronological order from the earliest to the latest based on the time information of the plurality of first available path points, so as to obtain the first local motion path.
[0054] For example, the plurality of first available path points include path point a ((x1, y1), t1), path point ((x2, y2), t2), path point b ((x2, y2), t2), path point c ((x3, y3), t3), and path point d ((x4, y4), t4). Then the above path points a, b, c and d are sorted according to the time information in the path points. If t1<t2<t3<t4, the sorting result of the above four path points is a→b→c→d. At this time, the obtained first local motion path starts from path point a, moves to path point b, then moves from path point b to path point c, and then moves from path point c to path point d.
[0055] In S103, the last first available path point among the plurality of first available path points is taken as a new motion start point, and a second local motion path from the new motion start point to the motion end point is determined.
[0056] Since the first local motion path constructed based on the plurality of first available path points only includes the motion start point of the robot and does not include the motion end point of the robot, in order to obtain a target motion path including the motion start point and the motion end point, this application may take the last first available path point among the plurality of first available path points as a new motion start point, and use a path planning algorithm to determine the second local motion path from the new motion start point to the motion end point according to the environment map, the new motion start point and the motion end point.
[0057] In this application, the path planning algorithm may include, but is not limited to: Dijkstra algorithm, A* algorithm, D* algorithm, LPA* algorithm, and D*Lite algorithm.
[0058] The aforementioned environmental map can be understood as an environmental map corresponding to a multi-robot application environment, which is pre-input into an electronic device. This environmental map can be a grid map or a topological map, and it can be 2D or 3D; this application does not impose any limitations on it.
[0059] S104, based on the first local motion path and the second local motion path, the target motion path of the robot is obtained.
[0060] After obtaining a first partial motion path including the starting point and a second partial motion path including the ending point, this application can obtain a complete motion path from the starting point to the ending point by splicing the first and second partial motion paths. Then, this complete motion path is determined as the robot's target motion path.
[0061] In some alternative implementations, after obtaining the robot's target motion path, this application can also establish a mapping relationship between the target motion path and the robot's identification information. Then, this mapping relationship is stored in a path result cache pool. The robot requesting path planning can then retrieve the corresponding target motion path from the path result cache pool based on its identification information. Finally, it performs the corresponding work based on the obtained target motion path.
[0062] The technical solution provided in this application involves obtaining a target historical motion path corresponding to the path planning request from the robot's historical motion paths based on the path planning request sent by the robot. Then, multiple consecutive first available path points starting from the starting point are obtained from the target historical motion path to form a first local motion path. Next, the last first available path point is used as the new starting point to determine a second local motion path from the new starting point to the ending point. Finally, the target motion path of the robot is obtained based on the first and second local motion paths. Therefore, by reusing multiple consecutive path points from the robot's historical motion path, the local paths in the planned motion path for the robot are guaranteed to be stable and non-jumping, thereby improving the stability and executability of the planned motion path.
[0063] Based on the foregoing embodiments, the following is combined with Figure 2 This application further explains how to obtain multiple consecutive first available path points starting from the starting point of the movement from the historical movement path of the target. For example... Figure 2 As shown, the above S102 includes the following steps S102-1 to S102-5:
[0064] S102-1, Starting from the starting point of the target's historical motion path, determine in sequence whether each path point in the target's historical motion path is located in the robot's conflict list or dynamic obstacle list.
[0065] In this application, each robot has a conflict list, which stores information on the path points that other robots need to traverse to move.
[0066] The aforementioned conflict list includes a temporary conflict list and a permanent conflict list. That is, determining whether each path point in the target's historical motion path is located in the robot's conflict list specifically involves determining whether each path point is located in the robot's temporary or permanent conflict list.
[0067] The temporary conflict list stores temporary conflict points, which indicate that when a robot is located at certain locations, it will temporarily conflict with other robots at certain times. The permanent conflict list stores permanent conflict points, which indicate that when a robot is located at certain locations, it will be in a permanent conflict with other robots from a certain time.
[0068] The conflict points in the aforementioned temporary conflict list and permanent conflict list can be any data structure used to describe the binding relationship (spatial location, time information), that is, a certain spatial location has a conflict at a certain time point (or time period). This application does not impose any restrictions on the data structure of the conflict points.
[0069] It should be noted that the temporary conflict list and permanent conflict list for each robot in this application are empty tables when the electronic device first performs path planning for multiple robots in a certain application scenario, i.e., they are initialized as empty tables. When performing real-time path planning based on the path planning requests sent by each of the multiple robots, the initial temporary conflict list and initial permanent conflict list for each robot are updated based on the start and end points carried by the multiple path planning requests, and then path planning is performed based on the updated temporary conflict list and permanent conflict list.
[0070] In other words, each robot's temporary conflict list and permanent conflict list are initialized and updated when path planning begins, and are only dynamically updated after the motion path is determined based on the start and end points sent by any robot.
[0071] In some alternative embodiments, updating the initial temporary conflict list for each robot based on the origin and destination carried by multiple path planning requests may include the following steps:
[0072] Step S11: Obtain the starting point from the starting and ending points sent by the i-th robot, and determine the sending time of the starting and ending points of the i-th robot, where i is an integer greater than or equal to 1.
[0073] Step S12: Add the starting point and sending time as temporary conflict points to the temporary conflict list of the j-th robot, where j is not equal to i and j is an integer greater than or equal to 1.
[0074] The sending time of the i-th robot's starting and ending points is specifically the start time when the electronic device executes this path planning.
[0075] In some alternative embodiments, updating the initial permanent conflict list for each robot based on the origin and destination carried by multiple path planning requests may include the following steps:
[0076] Step S21: Using the shortest path algorithm, based on the origin and destination sent by the i-th robot, determine the shortest time for the i-th robot to move from the origin to the destination, where i is an integer greater than or equal to 1.
[0077] Step S22: Add the endpoint and the shortest time as permanent conflict points to the permanent conflict list of the j-th robot, where j is not equal to i and j is an integer greater than or equal to 1.
[0078] In this application, the shortest time for the i-th robot to move from the starting point to the ending point can be determined by using a single-robot shortest path algorithm, such as the A* algorithm.
[0079] Furthermore, in this application, the dynamic obstacle list is maintained on the electronic device, and this list is initially empty when the electronic device first performs path planning for multiple robots in the application environment. When any robot detects a dynamic obstacle while moving along a planned path, it sends the obstacle's location information to the electronic device, allowing the device to update the dynamic obstacle list based on this information. This updated list of dynamic obstacles then allows the electronic device to consider the dynamic obstacles stored in the list when planning paths for this robot or other robots, ensuring that the planned paths for each robot can avoid the locations of the obstacles in the list.
[0080] In other words, the list of dynamic obstacles in this application is the latest list of dynamic obstacles.
[0081] The robot described above can detect dynamic obstacles by collecting information about the surrounding environment through sensors on the robot. Based on this information, it can detect the presence of dynamic obstacles. Specific details can be found in existing technologies, which are not limited here. The sensors mentioned above can be, but are not limited to, positioning sensors, location sensors, and cameras.
[0082] In some optional embodiments, this application determines whether each path point is located in the robot's temporary conflict list or permanent conflict list by obtaining each path point in the target's historical motion path and comparing each path point with the robot's temporary conflict list and permanent conflict list. It should be noted that the robot here refers to the robot corresponding to the target's historical motion path.
[0083] In addition, this application compares each path point in the target's historical movement path with the latest dynamic obstacle list on the electronic device to determine whether each path point is in the latest dynamic obstacle list.
[0084] If a specification is required, the execution order for determining whether each path point in the target's historical motion path is located in the robot's temporary conflict list or permanent conflict list, and whether it is located in the dynamic obstacle list, can be as follows: first determine whether each path point is located in the robot's temporary conflict list, then determine whether each path point is located in the robot's permanent conflict list, and finally determine whether each path point is located in the dynamic obstacle list; or, first determine whether each path point is located in the robot's permanent conflict list, then determine whether each path point is located in the robot's temporary conflict list, and finally determine whether each path point is located in the dynamic obstacle list, then determine whether each path point is located in the robot's temporary conflict list, and finally determine whether each path point is located in the robot's permanent conflict list, etc. This application does not impose any restrictions on the order of determining each path point.
[0085] S102-2, in response to the fact that multiple consecutive path points starting from the starting point are not in the robot's conflict list or dynamic obstacle list, determine multiple consecutive path points starting from the starting point as multiple consecutive first available path points starting from the motion starting point.
[0086] In some alternative embodiments, when it is determined that multiple consecutive path points starting from the starting point in the target's historical motion path are not located in the robot's temporary conflict list, permanent conflict list, or dynamic obstacle list, it is indicated that the multiple consecutive path points starting from the starting point are reusable path points. In this case, these path points are determined as first available path points, thereby obtaining multiple first available path points for constructing the first local motion path.
[0087] S102-3, in response to the fact that multiple consecutive path points starting from the starting point are all located in the robot's conflict list or dynamic obstacle list, perform time translation on the target historical motion path, and start again from the starting point of the target historical motion path points to determine in turn whether each path point in the target historical motion path is located in the robot's conflict list or dynamic obstacle list.
[0088] In some alternative embodiments, when it is determined that multiple consecutive path points starting from the starting point in the target's historical motion path are all located in the robot's temporary conflict list, permanent conflict list, or dynamic obstacle list, it indicates that the multiple consecutive path points starting from the starting point are unreusable path points.
[0089] In order to reuse path points in the target's historical movement path, this application can perform a time shift operation on each path point in the target's historical movement path again, so as to extend the time information of each path point in the target's historical movement path by a preset time based on the current path planning time. The preset time can be flexibly set according to the time shift requirements, such as a preset time of 1 second or 2 seconds, etc. There is no requirement for the setting of the preset time here.
[0090] By extending the time information of each path point in the target's historical movement path forward by a preset time period, this application can re-acquire each path point in the target's historical movement path and compare each path point with the robot's historical conflict list and permanent conflict list to determine whether each path point is located in the robot's temporary conflict list or permanent conflict list. Furthermore, each path point in the target's historical movement path is compared with the latest dynamic obstacle list on the electronic device to determine whether each path point is located in the latest dynamic obstacle list.
[0091] S102-4, in response to the fact that multiple consecutive path points starting from the starting point are not in the robot's conflict list or dynamic obstacle list, determine the multiple consecutive path points starting from the starting point after time translation as multiple consecutive first available path points starting from the motion starting point.
[0092] S102-5, in response to the fact that multiple path points starting from the starting point are all located in the robot's conflict list or dynamic obstacle list, the new time after time translation is taken as the current time, and the current time is translated again. Starting from the starting point of the target historical motion path point, each path point in the target historical motion path is sequentially determined to be located in the robot's conflict list or dynamic obstacle list until multiple consecutive first available path points are determined or the time translation reaches the preset time threshold.
[0093] In this application, the preset time threshold can be flexibly set according to the time shifting requirements. For example, the preset time threshold can be less than or equal to 5 seconds or 10 seconds, etc. This application does not impose any restrictions on this.
[0094] In other words, time shifting is performed on each path point in the target's historical movement path, extending the current path planning time up to a preset time threshold. For example, assuming the preset time threshold is 5 seconds, if the current path planning time is 11:21:05, then the maximum time shift for each path point in the target's historical movement path is 11:21:10.
[0095] This application avoids the problem of other robots malfunctioning due to infinite time shifting of each path point in the target's historical motion path by setting a preset time threshold.
[0096] Considering that even after time-shifting each path point in the target historical motion path to a preset time threshold, it may still be impossible to obtain multiple consecutive first available path points starting from the starting point, this application addresses this issue by employing a path planning algorithm to determine a conflict-free motion path from the starting point to the ending point based on the environmental map, the starting point, and the ending point. This conflict-free motion path is then used as the robot's target motion path.
[0097] In this application, the path planning algorithm may include, but is not limited to: Dijkstra's algorithm, A* algorithm, D* algorithm, LPA* algorithm and D*Lite algorithm.
[0098] This application determines a series of first available path points starting from the starting point from the target's historical motion path, and obtains a first local motion path corresponding to the robot based on these first available path points. By reusing path points in the robot's historical motion path, the stability of the robot's path planning can be improved, thereby enhancing the executability of the motion path.
[0099] The following is combined with Figure 3 This application further explains how, in determining the second local motion path from the new motion starting point to the motion ending point, the last of a plurality of first available path points is used as the new motion starting point. For example... Figure 3 As shown, the above S103 includes the following steps S103-1 to S103-3:
[0100] S103-1, taking the new starting point of motion as the first current point, search and determine the target neighbor point of the first current point. The target neighbor point is not in the robot's conflict list or dynamic obstacle list.
[0101] The target neighbor points include: target spatial neighbor points and target temporal neighbor points.
[0102] In some alternative embodiments, searching for and determining the target neighbor points of the first current point may include the following steps:
[0103] Step 1: Using the new starting point of motion as the first current point, search for the spatial and temporal neighbors of the first current point.
[0104] The spatial neighbor points can be selected as four-neighbor neighbor points, eight-neighbor neighbor points, or predefined neighbor points, etc. This application does not impose any restrictions on them.
[0105] The aforementioned four neighboring regions can be understood as the four neighboring regions of the first current point, located above, below, to the left, and to the right of the first current point, with the first current point as the center point.
[0106] The aforementioned eight neighboring regions can be understood as the eight neighboring regions of the first current point, centered on the first current point, located to the left, upper left, upper, upper right, right, lower right, lower, and lower left of the centered point.
[0107] In other words, the search for the spatial neighbors of the first current point is specifically the search for the four-neighbor neighbors, the eight-neighbor neighbors, or custom neighbors of the first current point.
[0108] In this application, a temporal neighbor can be understood as waiting for k seconds at any spatial neighbor. That is, the position of the spatial neighbor remains unchanged, and the time is automatically increased by k seconds. The result of adding k seconds to the spatial neighbor is the temporal neighbor. Here, k is an adjustable parameter, such as 1 second, 2 seconds, or 3 seconds, etc., and this application does not impose any restrictions on it.
[0109] For example, assuming k seconds is 1 second, the spatial neighbor of the first current point is ((x1,y1), tx1), where (x1,y1) is the location information of the spatial neighbor and tx1 is the timestamp information of moving from the first current point to the spatial neighbor. Then the time neighbor of the first current point is ((x1,y1), tx1+1).
[0110] Step 2: Determine whether the spatial and temporal neighbor points of the first current point are located in the robot's conflict list or dynamic obstacle list.
[0111] Specifically, the conflict list of the aforementioned robot refers to the conflict list of the robot corresponding to the new motion starting point that is adjacent to the spatial neighbor point and the temporal neighbor point. For example, assuming the first current point is the new motion starting point 1, determining whether the spatial neighbor point and the temporal neighbor point of the new motion starting point 1 are in the robot's conflict list specifically means determining whether the spatial neighbor point and the temporal neighbor point of the new motion starting point 1 are in the conflict list of the robot corresponding to the new motion starting point 1.
[0112] Since the implementation principles for determining whether spatial and temporal neighbor points of the first current point are located in the robot's temporary conflict list, permanent conflict list, or dynamic obstacle list are the same, the following will provide a detailed explanation using the example of determining whether any spatial neighbor point of a certain first current point is located in the robot's temporary conflict list, permanent conflict list, or dynamic obstacle list.
[0113] For example, assuming that any spatial neighbor point Lx of the first current point D is ((5,7),8), then when the temporary conflict list of the robot corresponding to the first current point D includes temporary conflict points ((5,7), [6,8,10]), it can be determined that the position information of the robot corresponding to the first current point D at spatial neighbor point Lx ((5,7),8) and the temporary conflict points ((5,7), [6,8,10]) in the temporary conflict list is (5,7) and there is a temporary conflict at time 8. At this time, it is determined that the spatial neighbor point Lx of the first current point D is located in the temporary conflict list of the robot corresponding to the first current point D.
[0114] Alternatively, when the permanent conflict list of the robot corresponding to the first current point D includes permanent conflict points ((5,7), [4]), it can be determined that the position information of the robot corresponding to the first current point D at the spatial neighbor point Lx ((5,7), 8) and the permanent conflict point ((5,7), [4]) in the permanent conflict list is (5,7) after time 8. That is, the position information (5,7) in the spatial neighbor point Lx ((5,7), 8) is located in the permanent conflict list of the aforementioned robot, and the time 8 when the spatial neighbor point Lx is located at the position information (5,7) is greater than the time 4 in the permanent conflict point ((5,7), [4]). At this time, it is determined that the spatial neighbor point Lx of the first current point D is located in the permanent conflict list of the robot corresponding to the first current point D.
[0115] For example, suppose the spatial neighbor of the first current point D is any spatial neighbor LY, which is ((6,8),8). Then, the position information (6,8) in ((6,8),8) is compared with the position information of dynamic obstacles stored in the dynamic obstacle list. If (6,8) is the same as any dynamic obstacle position information stored in the dynamic obstacle list, and the time for which the dynamic obstacle position information was added is within the valid time period, then the spatial neighbor LY is determined to be the location of the dynamic obstacle.
[0116] The aforementioned effective duration refers to the effective duration set by the electronic device for the location information of dynamic obstacles detected by any robot while updating the dynamic obstacle list. In this application, the effective duration can be set based on the average dwell time of dynamic obstacles at environmental locations, or it can be set to a fixed value, etc., and this application does not impose any restrictions on this. For example, this application can set the effective duration to a fixed value such as 30 seconds.
[0117] Step 3: In response to any spatial neighbor point and / or any temporal neighbor point being in the robot's conflict list, remove the spatial neighbor point and / or temporal neighbor point, and determine the remaining spatial neighbor point and / or remaining temporal neighbor point as the target neighbor point of the first current point.
[0118] If one or more spatial and / or temporal neighbor points of the first current point are located in the corresponding robot's temporary or permanent conflict list, it indicates that the robot will encounter temporary or permanent conflicts with other robots when passing through the aforementioned spatial and / or temporal neighbor points. Therefore, this application can avoid conflicts with the movement of other robots by removing these spatial and / or temporal neighbor points.
[0119] For spatial and / or temporal neighbor points that are not in the corresponding robot's temporary or permanent conflict list, it means that no other robot will pass through that neighbor point. Therefore, these spatial and / or temporal neighbor points can be retained and used as the target neighbor points of the first current point.
[0120] Step 4: In response to any spatial neighbor point and / or any temporal neighbor point being in the list of dynamic obstacles, skip the spatial neighbor point and / or temporal neighbor point and stop the search operation.
[0121] Given that one or more spatial and / or temporal neighbor points of the first current point are in the list of dynamic obstacles, it means that the robot will collide with any dynamic obstacle when passing through the aforementioned spatial and / or temporal neighbor points. Therefore, this application can effectively avoid collisions with dynamic obstacles by skipping these spatial and / or temporal neighbor points and stopping the search operation, thereby achieving the purpose of avoiding dynamic obstacles.
[0122] For spatial and / or temporal neighbor points that are not in the list of dynamic obstacles, it means that there are no dynamic obstacles in the neighbor point. Therefore, these spatial and / or temporal neighbor points can be retained and used as the target neighbor points of the first current point.
[0123] S103-2, using the target neighbor point as the new first current point, continue searching and determining the target neighbor point of the new first current point until the end point of the movement is found, and obtain multiple second available path points.
[0124] In this application, the process of searching for and determining the target neighbor points of the new first current point is the same as the process of the aforementioned step S103-1. For details, please refer to the aforementioned step S103-1 section, which will not be elaborated on here.
[0125] S103-3, based on multiple second available path points, obtain the second local motion path from the new motion starting point to the motion ending point.
[0126] In some alternative embodiments, a path planning algorithm can be used to calculate a second local motion path from the new starting point to the ending point of the motion, based on multiple second available path points.
[0127] In some optional embodiments, after obtaining the robot's target motion path based on the first local motion path and the second local motion path, this application may optionally extract endpoint path points and non-endpoint path points from the target motion path. Then, the endpoint path points are added as permanent conflict points to the permanent conflict list of other robots besides the robot corresponding to the target motion path, and the non-endpoint path points are added as temporary conflict points to the temporary conflict list of other robots besides the robot corresponding to the target motion path. This completes the dynamic update operation of the temporary and permanent conflict lists of other robots besides the robot corresponding to the target motion path based on the target motion path. Thus, when the electronic device performs path planning based on the motion start point and motion end point sent by other robots, it can take into account the path points traversed by the previous robot's motion path to avoid temporary or permanent conflicts with these path points, thereby planning a motion path for each robot that does not conflict with other robots.
[0128] In another implementation scenario, considering that when determining the second local motion path from the new starting point to the ending point based on multiple second available path points, it may be impossible to determine the second local motion path, i.e., the second local motion path result is empty. To solve the problem that the second local motion path cannot be determined based on multiple second available path points, this application determines any available path point in the environment map that is not used by other robots, and determines the second local motion path based on this available path point, so as to ensure that the robot has a traversable motion path at all times. The following is combined with Figure 4 This paper further explains the multi-robot path planning method provided in this application.
[0129] like Figure 4 As shown, the method may include the following steps:
[0130] S201, in response to determining that the second local motion path is empty based on a plurality of second available path points, a first waiting point not used by other robots is determined from the plurality of second available path points, and the first waiting point is stored in the robot's waiting point list.
[0131] In this application, each robot is provided with a waiting point list, and each waiting point list is empty when the electronic device first performs path planning for multiple robots. Furthermore, this waiting point list is dynamically updated based on the waiting points involved in the movement paths of other robots. That is, when any robot's movement path contains a waiting point, the electronic device will send the waiting points traversed by that robot to the waiting point lists of other robots.
[0132] The waiting point list mentioned above mainly stores the waiting point usage of each robot. For example, Ci = (x3, y3) means that the i-th robot occupies the waiting point (x3, y3).
[0133] In this application, the waiting points stored in the waiting list are all sourced from the pre-defined location information of the environment map in multi-robot application scenarios. These waiting points can be flexibly set according to the needs of multi-robot collaboration; some locations can be designated as waiting points, or all locations can be designated as waiting points, without any restrictions.
[0134] In some alternative embodiments, considering that when traditional path planning algorithms calculate the motion paths of any two or more robots, if all the robots are going to the same destination (i.e., the same endpoint), and the traditional path planning algorithm first determines the motion path for the first robot to reach that destination, then because the same destination is occupied, the remaining robots cannot find a corresponding motion path based on the traditional path planning algorithm. That is, the path planning results for the other robots are empty.
[0135] Therefore, to address the problem that traditional path planning algorithms result in empty path results for the remaining robots when multiple robots are heading to the same destination, after determining the path for the first robot, this application sets at least one waiting point in the environmental map corresponding to multiple robots. When a path is found based on the first robot's origin and destination, since this path already occupies the destinations of other robots, this application first plans for the other robots to move from their origin to any waiting point near the destination. At this waiting point, they wait for the first robot to leave the destination before planning for the other robots to move from the waiting point to the destination. The advantage of this setup is that when multiple robots need to go to the same destination, in addition to controlling one robot to proceed normally, it also controls the other robots to queue at the waiting point near the destination, thus solving the problem of empty path results for other robots and ensuring that each robot can reach the same destination.
[0136] S202, taking the new starting point of motion as the second current point, search and determine the target neighbor point of the second current point. The target neighbor point is not in the robot's conflict list or dynamic obstacle list.
[0137] S203, using the target neighbor point as the new second current point, continue searching and determining the target neighbor point of the new second current point until a first waiting point is found, thus obtaining multiple third available path points.
[0138] S204. Based on multiple third available path points, obtain the motion path from the new motion starting point to the first waiting point.
[0139] After obtaining the motion path from the new starting point to the first waiting point, this motion path can be used as the second local motion path.
[0140] Furthermore, the robot operates based on the target motion path obtained from the first local motion path and the second local motion path, and can also send new motion path planning requests to electronic devices in real time to obtain the target motion path that can reach the motion endpoint.
[0141] The implementation principle of steps S202 to S204 is the same as or similar to steps S103-1 to S103-3 in the previous embodiment. For the specific implementation process, please refer to steps S103-1 to S103-3 above. It will not be elaborated on here.
[0142] In some alternative embodiments, considering that a second local motion path may not be determined even based on multiple third available path points, i.e., the motion path from the new motion starting point to the first waiting point may be empty. Therefore, this application continuously changes the waiting point and determines the motion path from the new motion starting point to the new first waiting point based on the new first waiting point, until the motion path from the new motion starting point to the new first waiting point is obtained. Furthermore, the finally determined motion path from the new motion starting point to the new first waiting point is taken as the second local motion path.
[0143] In other words, this application also includes: in response to determining that the motion path from the new motion starting point to the first waiting point is empty based on multiple third available path points, replacing the first waiting point with a second waiting point that has not been used by other robots; using the second waiting point as the new first waiting point, continuing to determine the motion path from the new motion starting point to the new first waiting point, until the determined motion path is not empty.
[0144] The technical solution provided in this application embodiment, when the result of determining the second local motion path based on the new motion starting point is empty, selects any waiting point that is not used by other robots from the environment map, and determines the motion path from the new motion starting point to the waiting point based on the waiting point, so that the robot can obtain the second local motion path every time it requests a path, thereby ensuring the working effect of the robot and improving the working efficiency of multiple robots.
[0145] The following is a reference to the appendix. Figure 5 This application describes a multi-robot path planning device proposed in its embodiments. Figure 5 This is a schematic block diagram of a multi-robot path planning device provided in an embodiment of this application.
[0146] like Figure 5 As shown, the multi-robot path planning device 300 includes: an acquisition module 310, a first determination module 320, a second determination module 330, and a path planning module 340.
[0147] The acquisition module 310 is used to acquire the target historical motion path of the robot in response to a path planning request sent by any robot. The path planning request includes a motion start point and a motion end point.
[0148] The first determining module 320 is used to obtain a plurality of consecutive first available path points starting from the starting point of the movement from the target historical movement path, and to obtain a first local movement path based on the plurality of first available path points;
[0149] The second determining module 330 is used to determine a second local motion path from the new motion starting point to the motion ending point, taking the last of the multiple first available path points as the new motion starting point;
[0150] The path planning module 340 is used to obtain the target motion path of the robot based on the first local motion path and the second local motion path.
[0151] In one optional implementation of this application embodiment, the acquisition module 310 is specifically used for:
[0152] Based on any path planning request sent by the robot, obtain the robot's identification information, the starting point of movement, and the ending point of movement;
[0153] Based on the identification information, all historical movement paths of the robot are determined;
[0154] Based on the starting point and the ending point of the movement, the target historical movement path is determined from all historical movement paths.
[0155] In one optional implementation of this application embodiment, the first determining module 320 is specifically used for:
[0156] Starting from the starting point of the target historical motion path, determine in sequence whether each path point in the target historical motion path is located in the robot's conflict list or dynamic obstacle list;
[0157] In response to the fact that none of the consecutive path points starting from the starting point are in the robot's conflict list or the dynamic obstacle list, the consecutive path points starting from the starting point are determined to be consecutive first available path points starting from the motion starting point.
[0158] In an optional implementation of this application embodiment, the first determining module 320 is further configured to:
[0159] In response to the fact that multiple consecutive path points starting from the starting point are all located in the robot's conflict list or the dynamic obstacle list, the target historical motion path is time-shifted, and starting again from the starting point of the target historical motion path points, it is sequentially determined whether each path point in the target historical motion path is located in the robot's conflict list or the dynamic obstacle list.
[0160] In response to the fact that none of the consecutive path points starting from the starting point are in the robot's conflict list or the dynamic obstacle list, the consecutive path points starting from the starting point after time translation are determined to be consecutive first available path points starting from the starting point.
[0161] In response to multiple path points starting from the starting point being located in the robot's conflict list or dynamic obstacle list, the new time after time shift is taken as the current time, and the current time is shifted again. Starting from the starting point of the target historical motion path point, each path point in the target historical motion path is sequentially determined to be located in the robot's conflict list or dynamic obstacle list until multiple consecutive first available path points are determined or the time shift reaches a preset time threshold.
[0162] In one optional implementation of this application embodiment, the second determining module 330 includes:
[0163] The first determining unit is used to search for and determine the target neighbor points of the first current point, with the new starting point of motion as the first current point, wherein the target neighbor points are not located in the robot's conflict list or the dynamic obstacle list;
[0164] The second determining unit is used to continue searching for and determining the target neighbor point of the new first current point, using the target neighbor point as the new first current point, until the movement endpoint is found, and to obtain multiple second available path points;
[0165] The third determining unit is used to obtain a second local motion path from the new motion starting point to the motion ending point based on multiple second available path points.
[0166] In one optional implementation of this application embodiment, the target neighbor points include: target spatial neighbor points and target temporal neighbor points, and the first determining unit is specifically used for:
[0167] Using the new starting point of motion as the first current point, search for the spatial and temporal neighbor points of the new starting point of motion;
[0168] Determine whether the spatial and temporal neighbor points of the new motion starting point are located in the robot's conflict list or the dynamic obstacle list;
[0169] In response to any spatial neighbor point and / or any temporal neighbor point being in the robot's conflict list, the spatial neighbor point and / or temporal neighbor point are removed, and the remaining spatial neighbor point and / or remaining temporal neighbor point are determined as the target neighbor point of the first current point;
[0170] In response to any spatial neighbor point and / or any temporal neighbor point being in the list of dynamic obstacles, skip the spatial neighbor point and / or the temporal neighbor point and stop the search operation.
[0171] In one optional implementation of this application, the conflict list is either a temporary conflict list or a permanent conflict list.
[0172] It should be understood that the device embodiments and the foregoing method embodiments can correspond to each other, and similar descriptions can be referred to the method embodiments. To avoid repetition, further details will not be provided here. Specifically, Figure 5 The device 300 shown can perform Figure 1 The corresponding method embodiments, and the foregoing and other operations and / or functions of each module in device 300 are respectively implemented to achieve Figure 1 For the sake of brevity, the corresponding processes in each method are not described in detail here.
[0173] The apparatus 300 of this application embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the first aspect method embodiment in this application can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the first aspect method disclosed in this application embodiment can be directly embodied as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the first aspect method embodiment described above.
[0174] Figure 6 This is a schematic block diagram of an electronic device provided as an embodiment of this application. Figure 6 As shown, the electronic device 400 may include:
[0175] The system includes a memory 410 and a processor 420. The memory 410 stores computer programs and transfers the program code to the processor 420. In other words, the processor 420 can retrieve and run the computer program from the memory 410 to implement the multi-robot path planning method in the embodiments of this application.
[0176] For example, the processor 420 can be used to execute the above-described multi-robot path planning method embodiment according to instructions in the computer program.
[0177] In some embodiments of this application, the processor 420 may include, but is not limited to:
[0178] General-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0179] In some embodiments of this application, the memory 510 includes, but is not limited to:
[0180] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).
[0181] In some embodiments of this application, the computer program may be divided into one or more modules, which are stored in the memory 410 and executed by the processor 420 to complete the multi-robot path planning method provided in this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device.
[0182] like Figure 6 As shown, the electronic device 400 may further include:
[0183] Transceiver 430, which can be connected to processor 420 or memory 410.
[0184] The processor 420 can control the transceiver 430 to communicate with other devices; specifically, it can send information or data to other devices or receive information or data sent by other devices. The transceiver 430 may include a transmitter and a receiver. The transceiver 430 may further include antennas, and the number of antennas may be one or more.
[0185] It should be understood that the various components in the electronic device are connected through a bus system, which includes a data bus, a power bus, a control bus, and a status signal bus.
[0186] This application also provides a computer storage medium storing a computer program thereon, which, when executed by a computer, enables the computer to perform the multi-robot path planning method of the above-described method embodiments.
[0187] This application also provides a computer program product containing program instructions, which, when run on an electronic device, cause the electronic device to execute the multi-robot path planning method described in the above method embodiments.
[0188] When implemented using software, it can be implemented entirely or partially as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).
[0189] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0190] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.
[0191] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0192] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.
[0193] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A multi-robot path planning method, characterized by, include: In response to a path planning request sent by any robot, the target historical motion path of the robot is obtained, wherein the path planning request includes a motion start point and a motion end point; From the target's historical motion path, obtain a series of first available path points starting from the motion starting point, and obtain a first local motion path based on the series of first available path points; Using the last of the multiple first available path points as the new starting point, a second local motion path is determined from the new starting point to the end point. The target motion path of the robot is obtained based on the first local motion path and the second local motion path.
2. The method of claim 1, wherein, The step of obtaining the target historical motion path of the robot in response to a path planning request sent by any robot includes: Based on any path planning request sent by the robot, obtain the robot's identification information, the starting point of movement, and the ending point of movement; Based on the identification information, all historical movement paths of the robot are determined; Based on the starting point and the ending point of the movement, the target historical movement path is determined from all historical movement paths.
3. The method of claim 1, wherein, The step of obtaining a series of consecutive first available path points starting from the starting point of the movement from the target's historical movement path includes: Starting from the starting point of the target historical motion path, determine in sequence whether each path point in the target historical motion path is located in the robot's conflict list or dynamic obstacle list; In response to the fact that none of the consecutive path points starting from the starting point are in the robot's conflict list or the dynamic obstacle list, the consecutive path points starting from the starting point are determined to be consecutive first available path points starting from the motion starting point.
4. The method of claim 3, wherein, The method further includes: In response to the fact that multiple consecutive path points starting from the starting point are all located in the robot's conflict list or the dynamic obstacle list, the target historical motion path is time-shifted, and starting again from the starting point of the target historical motion path points, it is sequentially determined whether each path point in the target historical motion path is located in the robot's conflict list or the dynamic obstacle list. In response to the fact that none of the consecutive path points starting from the starting point are in the robot's conflict list or the dynamic obstacle list, the consecutive path points starting from the starting point after time translation are determined to be consecutive first available path points starting from the starting point. In response to multiple path points starting from the starting point being located in the robot's conflict list or dynamic obstacle list, the new time after time shift is taken as the current time, and the current time is shifted again. Starting from the starting point of the target historical motion path point, each path point in the target historical motion path is sequentially determined to be located in the robot's conflict list or dynamic obstacle list until multiple consecutive first available path points are determined or the time shift reaches a preset time threshold.
5. The method of claim 1, wherein, The step of determining a second local motion path from the last of a plurality of first available path points as the new motion starting point to the motion ending point includes: Using the new starting point of motion as the first current point, search and determine the target neighbor points of the first current point, wherein the target neighbor points are not located in the robot's conflict list or dynamic obstacle list; Using the target neighbor point as the new first current point, continue searching and determining the target neighbor point of the new first current point until the endpoint of the movement is found, thus obtaining multiple second available path points; Based on multiple second available path points, a second local motion path is obtained from the new motion starting point to the motion ending point.
6. The method of claim 5, wherein, The target neighbor points include: target spatial neighbor points and target temporal neighbor points. The step of searching for and determining the target neighbor points of the first current point, using the new motion starting point as the first current point, includes: Using the new starting point of motion as the first current point, search for the spatial and temporal neighbor points of the new starting point of motion; Determine whether the spatial and temporal neighbor points of the new motion starting point are located in the robot's conflict list or the dynamic obstacle list; In response to any spatial neighbor point and / or any temporal neighbor point being in the robot's conflict list, the spatial neighbor point and / or temporal neighbor point are removed, and the remaining spatial neighbor point and / or remaining temporal neighbor point are determined as the target neighbor point of the first current point; In response to any spatial neighbor point and / or any temporal neighbor point being in the list of dynamic obstacles, skip the spatial neighbor point and / or the temporal neighbor point and stop the search operation.
7. The method according to any one of claims 3-6, characterized in that, The conflict list can be a temporary conflict list or a permanent conflict list.
8. A multi-robot path planning apparatus, characterized by comprising: include: The acquisition module is used to acquire the target historical motion path of the robot in response to a path planning request sent by any robot, wherein the path planning request includes a motion start point and a motion end point; The first determining module is used to obtain a plurality of consecutive first available path points starting from the starting point of the movement from the target's historical movement path, and to obtain a first local movement path based on the plurality of first available path points; The second determining module is used to determine a second local motion path from the new motion starting point to the motion ending point, taking the last of the multiple first available path points as the new motion starting point; The path planning module is used to obtain the target motion path of the robot based on the first local motion path and the second local motion path.
9. An electronic device, comprising: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to perform the multi-robot path planning method as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the multi-robot path planning method as described in any one of claims 1 to 7.
Citation Information
Patent Citations
Multi-robot path planning method based on conflict detection
CN112835364A
Robot intelligent path planning method in unknown dynamic environment
CN115047880A
Automatic driving vehicle planning control method and related product
CN115817528A
