A robot path planning method, device, equipment and computer storage medium

Abstract

The application discloses a robot path planning method and device, equipment and a computer storage medium. The method comprises the following steps: obtaining a target area control map based on original map code point data; initializing a plurality of robot paths in the target area control map to obtain a first path reservation table; filtering a first target robot meeting a preset condition from the first path reservation table through a multi-level planning algorithm to obtain an initial path of the first target robot; if there is a second target robot not meeting the preset condition, re-planning an initial path of the second target robot to obtain an optimized path of the second target robot; obtaining a second path reservation table according to the initial path of the first target robot and the optimized path of the second target robot, and updating the first path reservation table to the second path reservation table; and planning paths for the plurality of robots through the second path reservation table. According to the embodiment of the application, the efficiency of centralized planning of driving paths of the plurality of robots is improved.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and in particular relates to a robot path planning method, apparatus, device and computer storage medium. Background Technology

[0002] Intelligent warehousing is an important part of the development of modern logistics. Intelligent warehousing uses a large number of Automated Guided Vehicles (AGVs) robots to transport goods in the warehouse.

[0003] Currently, multiple AGV robots are used in warehouses to handle large volumes of goods transport. To reduce conflicts between AGV robots during transport, proper path planning is necessary. Existing methods for multi-robot path planning employ a single path planning algorithm. However, this algorithm cannot tailor the target path based on the urgency of each AGV robot's task, resulting in low efficiency. Summary of the Invention

[0004] This application provides a robot path planning method, apparatus, device, and computer storage medium, which can improve the efficiency of centralized planning of the travel paths of multiple robots.

[0005] In a first aspect, embodiments of this application provide a robot path planning method, the method comprising:

[0006] Based on the original map marker data, obtain the target area control map;

[0007] Initialize multiple robot paths in the target area control map to obtain the first path reservation table;

[0008] The first target robot that meets the preset conditions is selected from the first path reservation table by a multi-level planning algorithm, and the initial path of the first target robot is obtained.

[0009] If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot;

[0010] The second path reservation table is obtained based on the initial path of the first target robot and the optimized path of the second target robot. The first path reservation table is then updated to the second path reservation table.

[0011] Path planning is performed for multiple robots using a second path reservation form.

[0012] Secondly, embodiments of this application provide a robot path planning device, comprising:

[0013] The first acquisition module is used to acquire the target area control map based on the original map code point data;

[0014] The initialization module is used to initialize multiple robot paths in the target area control map and obtain the first path reservation table.

[0015] The second acquisition module is used to select the first target robot that meets the preset conditions from the first path reservation table through a multi-level planning algorithm, and to obtain the initial path of the first target robot.

[0016] The optimization module is used to replan the initial path of the second target robot if there is a second target robot that does not meet the preset conditions, so as to obtain the optimized path of the second target robot.

[0017] The update module is used to obtain the second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table.

[0018] The planning module is used to plan paths for multiple robots using a second path reservation form.

[0019] Thirdly, embodiments of this application provide an electronic device, the device including: a processor and a memory storing computer program instructions;

[0020] When the processor executes computer program instructions, it implements a robot path planning method as described in any of the first aspects.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the robot path planning method as described in any of the first aspects.

[0022] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform a robot path planning method as described in any of the first aspects.

[0023] The robot path planning method, apparatus, device, and computer storage medium of this application employ a multi-level planning model including multi-level sub-algorithms. The robot plans the path of the target journey level by level until the planned journey of all robots is obtained, thereby improving the success rate of centralized path planning. In addition, the higher priority sub-algorithms are used to plan the path level by level, which improves the efficiency of centralized path planning. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating a robot path planning method provided in one embodiment of this application;

[0026] Figure 2 This is a flowchart illustrating a robot path planning method provided in another embodiment of this application;

[0027] Figure 3 This is a schematic diagram of a robot path planning process proposed in an embodiment of this application;

[0028] Figure 4 This is a flowchart illustrating a robot path planning method provided in yet another embodiment of this application;

[0029] Figure 5 This is a schematic diagram of the structure of a robot path planning device provided in another embodiment of this application;

[0030] Figure 6 This is a schematic diagram of the structure of a robot path planning device provided in another embodiment of this application. Detailed Implementation

[0031] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0032] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0033] Before introducing the specific implementation methods of this application, the technical terms used in describing the implementation methods of this application will be introduced first.

[0034] Multi-Agent Path Finding (MAPF) is a problem of finding a set of optimal paths from a starting position to a target position for multiple agents without conflict.

[0035] QR code: A physical QR code representing a warehouse map. Robots can navigate and locate themselves by scanning the QR code. The QR code stores the relative coordinates of the QR code on the warehouse map.

[0036] Intelligent warehousing is a crucial component of modern logistics, utilizing a large number of Automated Guided Vehicle (AGV) robots to transport goods within the warehouse. Currently, multiple AGV robots are used in warehouses to handle large volumes of goods transport. To minimize conflicts during transport, efficient path planning is essential for these AGV robots. Existing methods for multi-robot path planning employ a single path planning algorithm. However, this algorithm cannot tailor the target path based on the urgency of each AGV robot's task, resulting in low efficiency.

[0037] The robot path planning method, apparatus, device, and computer storage medium of this application improve the success rate of centralized path planning by employing a multi-level planning model including multi-level sub-algorithms to perform path planning for robots with target journeys step by step until the planned journeys of all robots are obtained. In addition, the higher priority sub-algorithms are used to plan paths step by step, which improves the efficiency of centralized path planning.

[0038] The robot path planning method provided in the embodiments of this application will be introduced first below.

[0039] Figure 1 This is a flowchart illustrating a robot path planning method provided in one embodiment of this application. Figure 1 As shown, the robot path planning method provided in this application embodiment includes the following steps: S101-S106.

[0040] S101: Obtain the target area control map based on the original map code point data.

[0041] It should be noted that the original map can be a map of the target warehouse, i.e., a warehouse where multiple robots are located. The code point data can be QR codes pre-defined in the original map to represent different coordinate locations.

[0042] In one embodiment, a target area control map can be obtained based on the code point data of the original map according to preset conditions.

[0043] S102: Initialize multiple robot paths in the target area control map to obtain the first path reservation table.

[0044] In one embodiment, the path of each robot in the target area control map can be initialized to obtain a first path reservation table including the path information of each robot.

[0045] As an example, the travel path of each robot in the target area control map can be randomly generated to complete the path initialization process.

[0046] S103: Select the first target robot that meets the preset conditions from the first path reservation table through a multi-level planning algorithm, and obtain the initial path of the first target robot.

[0047] It is understandable that since different robots perform different tasks, the importance of the tasks is different, and the urgency of the tasks is different, the robots that meet the preset conditions can be selected according to preset conditions to obtain the first target robot, and the initial path of the first target robot can be retained.

[0048] In one embodiment, a first target robot that meets preset conditions can be selected from the first path reservation table using a multi-level planning algorithm to obtain the initial path of the first target robot. The preset conditions can be pre-set according to actual needs.

[0049] S104: If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot.

[0050] If there is a second target robot that does not meet the preset conditions, it means that the task to be performed by the second target robot is relatively less urgent. The initial path of the second target robot can be replanned to obtain an optimized path for the second target robot, so that the optimized path of the second target robot does not conflict with the initial path of the first target robot.

[0051] S105: Obtain the second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table.

[0052] The second path reservation table is obtained based on the initial path of the first target robot and the optimized path of the second target robot. That is, after optimizing the path of the second target robot, the first path reservation table is updated using the second path reservation table.

[0053] In one embodiment, both the first path reservation table and the second path reservation table may include the robot's driving path and the corresponding driving time period.

[0054] S106: Perform path planning for multiple robots using the second path reservation form.

[0055] In one embodiment, multiple robots can be route-planned using the driving paths and time periods corresponding to each robot stored in the second path reservation table, so that each robot can drive in the area corresponding to the target area control map according to the driving path corresponding to the second path reservation table.

[0056] The robot path planning method provided in this application improves the success rate of centralized path planning by employing a multi-level planning model that includes multi-level sub-algorithms, and performing path planning for the robots with the target journey to be planned level by level until the planned journeys of all robots are obtained. In addition, the method prioritizes the use of higher-priority sub-algorithms to plan paths level by level, thereby improving the efficiency of centralized path planning.

[0057] In some embodiments of this application, to further improve the efficiency of centralized path planning for multiple robots, another robot path planning method is proposed. Please refer to [link to relevant documentation]. Figure 2 This is a flowchart illustrating a robot path planning method provided in another embodiment of this application. Figure 2 As shown, the robot path planning method includes: S201-S209.

[0058] S201: Obtain the target area control map based on the original map code point data.

[0059] S202: Initialize multiple robot paths in the target area control map to obtain the first path reservation table.

[0060] In this embodiment, S201-S202 are the same as S101-S102 in the embodiments of this application. For the sake of brevity, they will not be described in detail here. For detailed information, please refer to the description in the embodiments of this application.

[0061] In some embodiments of this application, the multi-level planning algorithm includes a first-level algorithm, a second-level algorithm, and a third-level algorithm;

[0062] Each level of the algorithm, including the first-level, second-level, and third-level algorithms, includes its own corresponding task urgency index. The task urgency index in the later-level algorithm includes the task urgency index in the earlier-level algorithm. The threshold values ​​for the same task urgency index are different for different-level planning algorithms. The higher the level, the smaller the threshold value for the task urgency index. The level of the first-level algorithm is lower than that of the second-level algorithm, and the level of the second-level algorithm is lower than that of the third-level algorithm.

[0063] In one embodiment, the first-level algorithm includes a first task urgency index (corresponding to a first threshold); the second-level algorithm includes a first task urgency index (corresponding to a third threshold) and a second task urgency index (corresponding to a second threshold); the third-level algorithm includes a first task urgency index (corresponding to a fourth threshold) and a second task urgency index (corresponding to a fifth threshold). Furthermore, if a second target robot does not meet the preset conditions, the third-level algorithm replans the initial path of the second target robot to obtain an optimized path. The first threshold is less than the third threshold, the third threshold is less than the fourth threshold, and the second threshold is less than the fifth threshold.

[0064] S203: The first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table in sequence using the first level algorithm, the second level algorithm, and the third level algorithm, until the algorithms of each level have been executed and the first target robot that meets the preset conditions corresponding to the current level algorithm has been selected, or the number of first target robots is equal to the number of multiple robots.

[0065] It is understandable that the first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table by using the first-level algorithm, the second-level algorithm, and the third-level algorithm in sequence. The number of the first target robots may be the same as the number of the multiple robots mentioned above, that is, multiple robots meet the preset conditions; the number of the first target robots may also be less than the number of the multiple robots mentioned above, that is, after selecting multiple robots through the first-level algorithm, the second-level algorithm, and the third-level algorithm, there are still remaining robots that do not meet the preset conditions.

[0066] In some embodiments of this application, the first-level algorithm includes a first task urgency index, and S203 may specifically include the following steps:

[0067] Obtain the start time of the initial path for each robot in the first path reservation table;

[0068] The task waiting time for each robot is determined based on the difference between each start time and the current time.

[0069] Based on the task waiting time, determine the first indicator value corresponding to the robot's first task urgency index. The task waiting time and the first task urgency index value are inversely correlated.

[0070] Obtain the first threshold of the current task urgency index corresponding to the first-level algorithm;

[0071] Select the first target robot whose first indicator value is greater than the first threshold from the first path reservation table;

[0072] Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

[0073] In one embodiment, the start time of the initial path for each robot in the first path reservation table is obtained. Based on the difference between each start time and the current time, the task waiting time for each robot is determined. Based on the task waiting time, a first indicator value corresponding to the robot's first task urgency index is determined. The task waiting time and the first task urgency index value are inversely correlated. That is, the longer the task waiting time, the higher the task urgency of the robot, and the lower the first task urgency index value.

[0074] Obtain the first threshold of the current task urgency index corresponding to the first-level algorithm, and select the first target robot from the first path reservation table whose first index value is greater than the first threshold. That is, the task reduction degree of the first target robot is relatively high.

[0075] Remove the first target robot from the first path reservation table to obtain the remaining robots. Update the remaining robots with the robots in the first path reservation table for use in the next level of screening.

[0076] In other embodiments of this application, the second-level algorithm includes a first task urgency index and a second task urgency index, and S203 may further include the following steps:

[0077] Obtain the estimated time required for each robot in the first path reservation table to complete the initial path;

[0078] The second indicator value corresponding to the robot's second task urgency index is obtained by weighted summation of the task waiting time and the estimated time.

[0079] Obtain the second threshold of the current task urgency index corresponding to the second-level algorithm;

[0080] Select the first target robot whose second indicator value is greater than the second threshold from the first path reservation table;

[0081] Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

[0082] In this embodiment of the application, the estimated time required for each robot to complete the initial path is obtained from the first path reservation table. The task waiting time and the estimated time are weighted and summed according to a preset weight value to obtain a weighted sum value, which is the second index value corresponding to the robot's second task urgency index.

[0083] The second threshold of the urgency index of the current level task corresponding to the second level algorithm can be obtained, that is, the second threshold corresponding to the urgency index of the second task can be obtained. The first target robot with the second index value greater than the second threshold can be determined from the first path reservation table. The first target robot is the robot that meets the preset conditions corresponding to the current level algorithm.

[0084] In one embodiment, the information corresponding to the first target robot can be removed from the first path reservation table to obtain the remaining robots. The remaining robots are then updated to the robots in the first path reservation table for use in the next level of algorithm selection.

[0085] It should be noted that before obtaining the estimated time required for each robot in the first path reservation table to complete its initial path, the first task urgency index and its corresponding third threshold can be used to filter out the first target robot from the first path reservation table whose index value is greater than the third threshold. The information corresponding to the first target robot is then removed from the first path reservation table to obtain the remaining robots. These remaining robots are then updated to the robots in the first path reservation table. The third threshold is greater than the first threshold. The above filtering method can adopt the filtering method proposed in any embodiment of this application.

[0086] In other embodiments of this application, the third-level algorithm includes a first task urgency index and a second task urgency index, and S203 may further include the following steps:

[0087] The first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table using the first task urgency index and the second task urgency index.

[0088] If a second target robot does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot.

[0089] In one embodiment, using a first task urgency index and its corresponding fourth threshold, a first target robot with an index value greater than the fourth threshold is selected from the first path reservation table. The information corresponding to the first target robot is then removed from the first path reservation table to obtain the remaining robots. These remaining robots are then updated to the robots in the first path reservation table. The fourth threshold is greater than the third threshold. The above selection method can be any of the selection methods proposed in any embodiment of this application.

[0090] After obtaining the updated first path reservation table, using the second task urgency index and its corresponding fifth threshold, a first target robot with an index value greater than the fifth threshold is selected from the first path reservation table. The information corresponding to the first target robot is then removed from the first path reservation table, resulting in the remaining robots. These remaining robots are then updated to the robots in the first path reservation table. The fifth threshold is greater than the second threshold. The above selection method can be any of the selection methods proposed in any embodiment of this application.

[0091] S204: If there is a second target robot that does not meet the preset conditions, randomly generate multiple alternative paths for the second target robot and the time information corresponding to each alternative path.

[0092] It is understandable that if there is a second target robot that does not meet the preset conditions, it means that the task corresponding to the second target robot is less urgent. The path of the second target robot can be replanned to avoid the first target robot.

[0093] In one embodiment, there may be one or more second target robots. Multiple alternative paths for each second target robot, along with the corresponding time information for each alternative path, can be randomly generated.

[0094] S205: Determine the shortest alternative path from multiple alternative paths to obtain the optimized path and the corresponding time information.

[0095] Understandably, when there are multiple alternative paths, the shortest alternative path can be selected as the optimized path, thereby making the second robot's driving efficiency relatively high.

[0096] S206: Obtain the second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table.

[0097] S207: Path planning for multiple robots is performed using the second path reservation form.

[0098] In this embodiment, S206-S207 are the same as S105-S106 in the embodiments of this application. For the sake of brevity, they will not be described in detail here. For detailed information, please refer to the description in the embodiments of this application.

[0099] S208: If the optimized path does not meet the second preset condition, the path of the second target robot is replanned using a traditional path planning algorithm to obtain the replanned result.

[0100] S209: Update the optimized path of the second target robot and the corresponding time information based on the replanning results.

[0101] It is understandable that the situation where the optimized path does not meet the second preset condition may be that the shortest path length among the multiple alternative paths is greater than the preset path length. That is, the shortest path length among the multiple alternative paths corresponding to the same robot is still very long and cannot meet the requirements. In this case, the traditional path planning algorithm can be used to replan the path of the second target robot to obtain the replanning result. Based on the replanning result, the optimized path of the second target robot and the time information corresponding to the optimized path are updated.

[0102] like Figure 3 The diagram shown is a schematic of a robot path planning process proposed in an embodiment of this application.

[0103] The A* algorithm of RCS (robot control system) can be used to initialize the path, obtain the initial paths of multiple robots, and send a locking calculation request to the locking calculation unit, that is, the request proposed in some embodiments of this application to calculate the robot's travel path within a future preset time period. The locking computation unit obtains a first path reservation table corresponding to the initial paths of multiple robots and inputs it into the WHCA (wide Hierarchical Cooperative A*) operator (i.e., the first-level algorithm). The WHCA operator selects the first target robot that meets the preset conditions corresponding to the first-level algorithm from the first path reservation table, removes the first target robot from the first path reservation table, updates the robots in the first path reservation table to the remaining robots, and returns the first path reservation table to the locking computation unit. The locking computation unit inputs the updated first path reservation table into the DRL (Deep Reinforcement Learning) operator (i.e., the second-level algorithm). The DRL operator selects the first target robot that meets the preset conditions corresponding to the second-level algorithm from the first path reservation table, removes the first target robot from the first path reservation table, updates the robots in the first path reservation table to the remaining robots, and returns the first path reservation table to the locking computation unit. The locking computation unit inputs the updated first path reservation table into the CBS (Conflict-based) operator. The search (central planning) operator (i.e., the third-level algorithm) selects the first target robot from the first path reservation table that meets the preset conditions corresponding to the second-level algorithm. It then removes the first target robot from the first path reservation table, resulting in the remaining second target robots. The initial path of the second target robot is then replanned to obtain its optimized path. Based on the initial path of the first target robot and the optimized path of the second target robot, a second path reservation table is generated. The first path reservation table is then updated to the second path reservation table, i.e., the path is updated. If there are robots among the second target robots that do not meet the preset conditions, the RCS calculator can be used for path replanning, thereby updating the second path reservation table. The updated second path reservation table is then used to plan paths for multiple robots.

[0104] The robot path planning method provided in this application employs a multi-level planning model including multiple sub-algorithms to plan the paths of robots for the target journey level by level until the planned journeys of all robots are obtained. Each level of the first-level algorithm, the second-level algorithm, and the third-level algorithm includes its own corresponding task urgency index. The task urgency index in the later level algorithm includes the task urgency index in the earlier level algorithm, and the threshold value of the same task urgency index corresponding to different level planning algorithms is different. The higher the level, the smaller the threshold value of the task urgency index. The level of the first-level algorithm is lower than that of the second-level algorithm, and the level of the second-level algorithm is lower than that of the third-level algorithm, thereby improving the success rate of centralized path planning. In addition, the priority of using higher-priority sub-algorithms to plan paths level by level improves the efficiency of centralized path planning.

[0105] To further improve the efficiency of centralized path planning for multiple robots, an alternative robot path planning method is proposed. Please refer to [link to relevant documentation]. Figure 4 This is a flowchart illustrating a robot path planning method provided in another embodiment of this application. Figure 4 As shown, the robot path planning method includes: S401-S407.

[0106] S401: Determine the target code point set from multiple code points based on the target object in the original map, the direction of passage of the code points, and the spacing between the code points.

[0107] Understandably, the original map contains a large number of code points. If every code point in the original map were to participate in the planning of the robot's path, the computational load would be enormous. Therefore, the number of code points can be reduced, and the remaining code point set can be used for path planning, thereby reducing the computational load and improving efficiency. For example, code points that the robot cannot reach, code points with uncertain robot dwell times, and code points whose small spacing could easily lead to conflicts between robots can be removed.

[0108] As an example, target code points can be determined from the code points in the original map based on the drivable direction of the code points, the spacing between code points, and the target objects in the original map, thus obtaining a set of target code points.

[0109] S402: Initialize map data based on the target code point set to obtain the target area control map.

[0110] In one embodiment, the corresponding area control region can be determined based on the target code point set, and then the map data can be initialized to obtain the target area control map.

[0111] In some embodiments of this application, the original map code point data includes the coordinate values ​​of the code points; determining the target code point set from multiple code points based on the target object in the original map, the travel direction of the code points, and the spacing between the code points includes:

[0112] Remove the code points corresponding to the target object from the code points of the original map to obtain the set of remaining code points and the target sub-region corresponding to the set of remaining code points;

[0113] For the first remaining code point in the set of remaining code points, determine whether the first remaining code point is an edge code point in the target sub-region based on the coordinate value of the first remaining code point; the first remaining code point can be any code point in the set of remaining code points.

[0114] In response to the first remaining code point being an edge code point, the passage direction of the first remaining code point is determined;

[0115] Based on the direction of travel, determine whether the first remaining code point is a one-way entry / exit code point for the target sub-region;

[0116] In response to the first remaining code point not being a unidirectional in-out code point, the target non-edge code point is updated to the first remaining code point, where the target non-edge code point is any non-edge code point adjacent to the first remaining code point;

[0117] The target code point set is determined from the updated set of remaining code points based on the number of code points and the code point spacing.

[0118] In the embodiments of this application, the target object may be a workstation in the warehouse map, a storage point, or a tidal flow lane.

[0119] It is understandable that, since there are some workstations and storage points in the warehouse that robots usually cannot reach or whose dwell time is not fixed, the code points in these areas do not need to participate in path planning. In addition, since the tidal lanes in the warehouse allow different directions of travel at different times, the path planning process will seriously affect the calculation efficiency. Therefore, the code points corresponding to the tidal lanes can also be excluded from path planning.

[0120] As an example, the code points within the area to which the target object belongs are removed from the code points in the target map, and the set of remaining code points in the target map is determined as the target code points, thus obtaining the target code point set. This reduces the number of code points involved in path planning, lowers the computational complexity of path planning, and improves the efficiency of path planning.

[0121] In some embodiments of this application, determining the target code point set from the updated remaining code point set based on the number of code points and the code point spacing of the updated remaining code point set includes:

[0122] Based on the coordinate values ​​and travel direction, multiple possible route points for robots to reach the target object are determined;

[0123] Identify the necessary checkpoints for the robot to reach the target object from among the possible checkpoints;

[0124] For the second remaining code point in the updated set of remaining code points, determine the first and second code points adjacent to the second remaining code point; the first code point, the second remaining code point, and the second code point are collinear; the second remaining code point is any code point in the updated set of remaining code points.

[0125] In response to the fact that the distance between the first code point and the second code point is less than a preset threshold and the second remaining code point is not a necessary code point, the second remaining code point is removed from the updated set of remaining code points to obtain the target code point set.

[0126] As an example, based on the coordinates of each code point and the drivable direction of each code point, the driving path from any location on the target map to the target object can be determined, and then the code points along the way to the target object can be determined based on the driving path.

[0127] It's understandable that for workstations, storage points, and shelves in a warehouse, in order for robots to transport goods normally, it's essential to ensure that the path planned based on the code points in the target code point set can reach the location of the target object. Therefore, it's necessary to determine the code points that the robot must pass through to reach the target object. These essential code points cannot be removed from the code points on the target map.

[0128] As an example, based on the coordinates of the target object's region and the coordinates of the aforementioned path markers, the necessary path markers for the robot to reach the target object can be determined from the path markers. In other words, if a path marker is removed, the robot cannot reach the target object, so that path marker is a necessary path marker.

[0129] If the first and second code points adjacent to the code point are on the same straight line, and the distance between the first and second code points is too small, it is easy for the robot to cause a collision during the movement. The code point can be removed to increase the distance between the first and second code points.

[0130] As an example, if a code point is not a necessary code point, and the distance between the first code point and the second code point adjacent to the code point is less than a first preset threshold, then the code point is removed from the code points of the target map to obtain the target code point set.

[0131] S403: Initialize multiple robot paths in the target area control map to obtain the first path reservation table.

[0132] In this embodiment, S403 is the same as S102 in the embodiment of this application. For the sake of brevity, it will not be described in detail here. For details, please refer to the description in the embodiment of this application.

[0133] S404: According to the preset cycle, the first target robot that meets the preset conditions is selected from the first path reservation table through a multi-level planning algorithm, and the initial path of the first target robot in the first time period in the future is obtained.

[0134] S405: If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot in the first time period in the future.

[0135] In one embodiment, the initial path of the first target robot within a future first time period can be obtained according to a preset period. For example, every 5 seconds, a multi-level planning algorithm can be used to filter out the first target robot that meets the preset conditions from the first path reservation table, and obtain the initial path of the first target robot within the next 20 seconds. If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot within the next 20 seconds.

[0136] S406: Obtain the second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table.

[0137] S407: Perform path planning for multiple robots using the second path reservation form.

[0138] In this embodiment, S406-S407 are the same as S105-S106 in the embodiments of this application. For the sake of brevity, they will not be described in detail here. For detailed information, please refer to the description in the embodiments of this application.

[0139] In some embodiments of this application, the method may further include the following steps:

[0140] In the case where an abnormal robot exists among multiple robots, obtain the first position coordinates of the abnormal robot;

[0141] Determine whether the first position coordinates are on the target travel path of the normal robot among multiple robots; the target travel path is either the initial target path or a replanned path.

[0142] If the first position coordinates are on the target travel path of at least one normal robot, a target detour path for each of the at least one normal robot is generated based on the first position coordinates and the travel path of the at least one normal robot, and the target detour path does not pass through the first position coordinates.

[0143] It should be noted that if a robot malfunctions and cannot be controlled, it can be added to the obstacle list, thus identifying it as an obstacle so that other robots can bypass it and avoid conflict.

[0144] In one embodiment, when there is an abnormal robot among multiple robots, the first position coordinates of the abnormal robot are obtained. If the first position coordinates are on the target travel path of at least one normal robot, a target detour path for each of the at least one normal robot is generated based on the first position coordinates and the travel path of the at least one normal robot. The target detour path does not pass through the first position coordinates, so that the normal robot can bypass the abnormal robot and reduce the occurrence of conflict.

[0145] In some embodiments of this application, before obtaining the first position coordinates of the abnormal robot, the method may further include the following steps:

[0146] For each of the multiple robots, a robot is identified as an anomalous robot if it meets any of the following conditions:

[0147] The robot malfunctioned;

[0148] The robot is the first target robot, and it does not meet the requirement that the robot can travel according to the target's initial path and the time information corresponding to the target's initial path.

[0149] The robot path planning method provided in this application determines a target code point set in the original map based on the drivable direction of the code points, the code point spacing, and the target object in the original map. Based on the initial paths of multiple robots, the method centrally plans the driving paths of multiple robots in the area corresponding to the target code point set, thereby reducing the area range for path planning of multiple robots, reducing computational complexity, improving computational efficiency, and enhancing the practicality of centralized robot path planning in industrial scenarios.

[0150] Based on the robot path planning method provided in the above embodiments, combined with the appendix Figure 5 This application describes the specific implementation of the robot path planning device provided in its embodiments.

[0151] See Figure 5 This is a schematic diagram of the structure of a robot path planning device provided in another embodiment of this application. The robot path planning device 500 includes:

[0152] The first acquisition module 501 is used to acquire the target area control map based on the original map code point data;

[0153] Initialization module 502 is used to initialize multiple robot paths in the target area control map and obtain the first path reservation table;

[0154] The second acquisition module 503 is used to select the first target robot that meets the preset conditions from the first path reservation table through a multi-level planning algorithm, and obtain the initial path of the first target robot.

[0155] The optimization module 504 is used to replan the initial path of the second target robot if there is a second target robot that does not meet the preset conditions, so as to obtain the optimized path of the second target robot.

[0156] The first update module 505 is used to obtain a second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table.

[0157] The planning module 506 is used to plan paths for multiple robots using a second path reservation form.

[0158] The robot path planning device provided in this application improves the success rate of centralized path planning by employing a multi-level planning model that includes multi-level sub-algorithms to plan the path of the robot to be planned step by step until the planned path of all robots is obtained. In addition, the higher priority sub-algorithms are used to plan the path step by step, which improves the efficiency of centralized path planning.

[0159] As one implementation of this application, the multi-level planning algorithm includes a first-level algorithm, a second-level algorithm, and a third-level algorithm;

[0160] Each level of the algorithm, including the first-level, second-level, and third-level algorithms, includes its own corresponding task urgency index. The task urgency index in the later-level algorithm includes the task urgency index in the earlier-level algorithm. The threshold values ​​for the same task urgency index are different for different-level planning algorithms. The higher the level, the smaller the threshold value for the task urgency index. The level of the first-level algorithm is lower than that of the second-level algorithm, and the level of the second-level algorithm is lower than that of the third-level algorithm.

[0161] As one implementation of this application, in order to further improve the efficiency of centralized path planning for multiple robots, the second acquisition module 503 may further include:

[0162] The acquisition submodule is used to sequentially use the first-level algorithm, the second-level algorithm, and the third-level algorithm to filter out the first target robot that meets the preset conditions corresponding to the current level algorithm from the first path reservation table, until the algorithms of each level have been executed to filter out the first target robot that meets the preset conditions corresponding to the current level algorithm, or the number of first target robots is equal to the number of multiple robots.

[0163] As one implementation of this application, the first-level algorithm includes a first task urgency index, and the aforementioned acquisition submodule can be specifically used for:

[0164] Obtain the start time of the initial path for each robot in the first path reservation table;

[0165] The task waiting time for each robot is determined based on the difference between each start time and the current time.

[0166] Based on the task waiting time, determine the first indicator value corresponding to the robot's first task urgency index. The task waiting time and the first task urgency index value are inversely correlated.

[0167] Obtain the first threshold of the current task urgency index corresponding to the first-level algorithm;

[0168] Select the first target robot whose first indicator value is greater than the first threshold from the first path reservation table;

[0169] Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

[0170] As one implementation of this application, the second-level algorithm includes a first task urgency index and a second task urgency index, and the aforementioned acquisition submodule can be specifically used for:

[0171] The second-level algorithm includes a first task urgency index and a second task urgency index. It sequentially uses the first-level algorithm, the second-level algorithm, and the third-level algorithm to filter out the first target robot from the first path reservation table that meets the preset conditions corresponding to the current level of the algorithm. It also includes:

[0172] Obtain the estimated time required for each robot in the first path reservation table to complete the initial path;

[0173] The second indicator value corresponding to the robot's second task urgency index is obtained by weighted summation of the task waiting time and the estimated time.

[0174] Obtain the second threshold of the current task urgency index corresponding to the second-level algorithm;

[0175] Select the first target robot whose second indicator value is greater than the second threshold from the first path reservation table;

[0176] Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

[0177] As one implementation of this application, the third-level algorithm includes a first task urgency index and a second task urgency index. The aforementioned acquisition submodule can specifically be used for:

[0178] The first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table using the first task urgency index and the second task urgency index.

[0179] If a second target robot does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot.

[0180] As one implementation of this application, to further improve the efficiency of centralized path planning for multiple robots, the above-mentioned device may further include:

[0181] The replanning module is used to replan the path of the second target robot using a traditional path planning algorithm when the optimized path does not meet the second preset condition, and obtain the replanning result.

[0182] The second update module is used to update the optimized path of the second target robot and the corresponding time information based on the replanning results.

[0183] As one implementation of this application, the original map code point data includes code point data of multiple code points, and the code point data includes the travel direction of the code points and the spacing between the code points. The first acquisition module 501 mentioned above may also include:

[0184] The first determination submodule is used to determine the target code point set from multiple code points based on the target object in the original map, the passage direction of the code points, and the spacing between the code points;

[0185] The second determination submodule is used to initialize map data based on the target code point set to obtain the target area control map.

[0186] As one implementation of this application, the second acquisition module 503 can also be used to: select a first target robot that meets the preset conditions from the first path reservation table according to a preset period using a multi-level planning algorithm, and obtain the initial path of the first target robot in the first time period in the future; the optimization module 504 can also be used to: if there is a second target robot that does not meet the preset conditions, re-plan the initial path of the second target robot to obtain the optimized path of the second target robot in the first time period in the future.

[0187] As one implementation of this application, the above-mentioned apparatus may further include:

[0188] The third acquisition module is used to acquire the first position coordinates of the abnormal robot when there is an abnormal robot among multiple robots;

[0189] The judgment module is used to determine whether the first position coordinates are on the target travel path of the normal robot among multiple robots; the target travel path is the initial target path or a replanned path.

[0190] The generation module is configured to generate a target detour path for at least one normal robot based on the first position coordinates and the target travel path of at least one normal robot, provided that the first position coordinates are on the target travel path of at least one normal robot. The target detour path does not pass through the first position coordinates.

[0191] As one implementation of this application, the above-mentioned apparatus may further include:

[0192] The determination module is used to identify a robot as an abnormal robot for each of a plurality of robots if the robot meets any of the following conditions:

[0193] The robot malfunctioned;

[0194] The robot is the first target robot, and it does not meet the requirement that the robot can travel according to the target's initial path and the time information corresponding to the target's initial path.

[0195] Figure 6 This is a schematic diagram of the structure of a robot path planning device provided in another embodiment of this application.

[0196] The robot path planning device may include a processor 601 and a memory 602 storing computer program instructions.

[0197] Specifically, the processor 601 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0198] Memory 602 may include a large-capacity memory for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 602 is non-volatile solid-state memory. Memory 602 may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, typically, memory 602 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the robot path planning methods in the above embodiments.

[0199] The processor 601 reads and executes computer program instructions stored in the memory 602 to implement any of the robot path planning methods in the above embodiments.

[0200] In one example, the robot path planning device may also include a communication interface 603 and a bus 610. Wherein, as Figure 6 As shown, the processor 601, memory 602, and communication interface 603 are connected through bus 610 and complete communication with each other.

[0201] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0202] Bus 610 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 610 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0203] Furthermore, in conjunction with the robot path planning methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the robot path planning methods in the above embodiments.

[0204] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0205] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0206] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0207] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0208] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A robot path planning method, characterized in that, include: Based on the original map marker data, obtain the target area control map; Initialize multiple robot paths in the target area control map to obtain the first path reservation table; The first target robot that meets the preset conditions is selected from the first path reservation table by a multi-level planning algorithm, and the initial path of the first target robot is obtained. If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot; A second path reservation table is obtained based on the initial path of the first target robot and the optimized path of the second target robot, and the first path reservation table is updated to the second path reservation table. The second path reservation form is used to plan paths for the multiple robots. The multi-level planning algorithm includes a first-level algorithm, a second-level algorithm, and a third-level algorithm. Each level of the algorithm, including the first-level algorithm, the second-level algorithm, and the third-level algorithm, includes its own corresponding task urgency index. The task urgency index in the later-level algorithm includes the task urgency index in the earlier-level algorithm. The threshold values ​​for the same task urgency index are different for different-level planning algorithms. The higher the level, the smaller the threshold value for the task urgency index. The level of the first-level algorithm is lower than that of the second-level algorithm, and the level of the second-level algorithm is lower than that of the third-level algorithm. The first-level algorithm includes a first task urgency index. The step of using a multi-level planning algorithm to select a first target robot that meets preset conditions from the first path reservation table and obtaining the initial path of the first target robot includes: Obtain the start time of the initial path for each robot in the first path reservation table; The task waiting time for each robot is determined based on the difference between each start time and the current time. Based on the task waiting time, a first index value corresponding to the first task urgency index of the robot is determined, and the task waiting time is inversely correlated with the first task urgency index value. Obtain the first threshold of the current task urgency index corresponding to the first-level algorithm; Select the first target robot whose first indicator value is greater than the first threshold from the first path reservation table; Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

2. The robot path planning method according to claim 1, characterized in that, The step of selecting a first target robot that meets preset conditions from the first path reservation table using a multi-level planning algorithm and obtaining the initial path of the first target robot includes: The first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table in sequence using the first level algorithm, the second level algorithm, and the third level algorithm, until the algorithms of each level have been executed to select the first target robot that meets the preset conditions corresponding to the current level algorithm, or the number of the first target robots is equal to the number of the plurality of robots.

3. The robot path planning method according to claim 2, characterized in that, The second-level algorithm includes the first task urgency index and the second task urgency index. The step of sequentially using the first-level algorithm, the second-level algorithm, and the third-level algorithm to select the first target robot from the first path reservation table that meets the preset conditions corresponding to the current level algorithm further includes: Obtain the estimated time required for each robot in the first path reservation table to complete the initial path; The second index value corresponding to the second task urgency index of the robot is obtained by weighted summing of the task waiting time and the estimated time. Obtain the second threshold of the current task urgency index corresponding to the second-level algorithm; Select a first target robot from the first path reservation table whose second indicator value is greater than the second threshold; Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

4. The robot path planning method according to claim 3, characterized in that, The third-level algorithm includes a first task urgency index and a second task urgency index. The step of sequentially using the first-level algorithm, the second-level algorithm, and the third-level algorithm to select the first target robot from the first path reservation table that meets the preset conditions corresponding to the current level algorithm further includes: The first target robot that meets the preset conditions corresponding to the current level algorithm is selected from the first path reservation table using the first task urgency index and the second task urgency index. If a second target robot does not meet the preset conditions, the initial path of the second target robot is replanned to obtain an optimized path for the second target robot.

5. The robot path planning method according to claim 1, characterized in that, The step of replanning the initial path of the second target robot to obtain an optimized path for the second target robot includes: Multiple alternative paths for the second target robot are randomly generated, along with the time information corresponding to each alternative path. Among the multiple alternative paths, the shortest alternative path is determined to obtain the optimized path and the corresponding time information.

6. The robot path planning method according to claim 1, characterized in that, After replanning the initial path of the second target robot to obtain the optimized path of the second target robot, the method further includes: If the optimized path does not meet the second preset condition, the path of the second target robot is replanned using a traditional path planning algorithm to obtain the replanned result; The optimized path of the second target robot and the corresponding time information are updated based on the replanning results.

7. The robot path planning method according to claim 1, characterized in that, The original map code point data includes code point data for multiple code points, and the code point data includes the direction of passage of the code points and the spacing between the code points; The process of obtaining the target area control map based on the original map dot data includes: Based on the target objects in the original map, the direction of passage of the code points, and the spacing between the code points, determine the target code point set from the multiple code points; The map data is initialized based on the target code point set to obtain the target area control map.

8. The robot path planning method according to claim 1, characterized in that, The step of selecting a first target robot that meets preset conditions from the first path reservation table using a multi-level planning algorithm and obtaining the initial path of the first target robot includes: According to a preset cycle, a first target robot that meets the preset conditions is selected from the first path reservation table through a multi-level planning algorithm, and the initial path of the first target robot in the first future time period is obtained. If a second target robot does not meet the preset conditions, the initial path of the second target robot is replanned to obtain an optimized path for the second target robot, including: If there is a second target robot that does not meet the preset conditions, the initial path of the second target robot is replanned to obtain the optimized path of the second target robot in the first time period in the future.

9. The robot path planning method according to claim 1, characterized in that, Also includes: If an abnormal robot is present among the plurality of robots, the first position coordinates of the abnormal robot are obtained; Determine whether the first position coordinates are on the target travel path of the normal robot among the plurality of robots; the target travel path is the initial target path or a replanned path. If the first position coordinates are on the target travel path of at least one normal robot, a target detour path is generated for each of the at least one normal robot based on the first position coordinates and the travel path of the at least one normal robot, and the target detour path does not pass through the first position coordinates.

10. The robot path planning method according to claim 9, characterized in that, Before obtaining the first position coordinates of the abnormal robot, the method further includes: For each of the plurality of robots, a robot is determined to be an abnormal robot if it meets any of the following conditions: The robot malfunctioned; The robot is the first target robot, and it does not satisfy the requirement that the robot can travel according to the target initial path and the time information corresponding to the target initial path.

11. A robot path planning device, characterized in that, include: The first acquisition module is used to acquire the target area control map based on the original map code point data; An initialization module is used to initialize multiple robot paths in the target area control map to obtain a first path reservation table; The second acquisition module is used to select a first target robot that meets preset conditions from the first path reservation table through a multi-level planning algorithm, and to obtain the initial path of the first target robot. The optimization module is used to replan the initial path of the second target robot if there is a second target robot that does not meet the preset conditions, so as to obtain the optimized path of the second target robot. The update module is used to obtain a second path reservation table based on the initial path of the first target robot and the optimized path of the second target robot, and update the first path reservation table to the second path reservation table. The planning module is used to plan paths for the multiple robots using the second path reservation form; The multi-level planning algorithm includes a first-level algorithm, a second-level algorithm, and a third-level algorithm. Each level of the algorithm, including the first-level algorithm, the second-level algorithm, and the third-level algorithm, includes its own corresponding task urgency index. The task urgency index in the later-level algorithm includes the task urgency index in the earlier-level algorithm. The threshold values ​​for the same task urgency index are different for different-level planning algorithms. The higher the level, the smaller the threshold value for the task urgency index. The level of the first-level algorithm is lower than that of the second-level algorithm, and the level of the second-level algorithm is lower than that of the third-level algorithm. The first-level algorithm includes a first task urgency index and a second acquisition module. It is further configured to acquire the start time of the initial path for each robot in the first path reservation table; determine the task waiting time for each robot based on the difference between each start time and the current time; determine a first index value corresponding to the first task urgency index of the robot based on the task waiting time, wherein the task waiting time is inversely correlated with the first task urgency index value; and acquire a first threshold value for the current task urgency index corresponding to the first-level algorithm. Select the first target robot whose first indicator value is greater than the first threshold from the first path reservation table; Remove the first target robot from the first path reservation table to obtain the remaining robots, and update the remaining robots to the robots in the first path reservation table.

12. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the robot path planning method as described in any one of claims 1-10.

Images