Path construction method, electronic equipment and computer readable storage medium

Abstract

The invention discloses a path construction method, electronic equipment and a computer readable storage medium, and the method comprises the steps: carrying out the path reconstruction processing according to the historical planning path of each target object, obtaining the target execution path of each target object, and enabling the target execution path to comprise a motion state determined by adjacent passing points; traversing a target execution path of each target object, and obtaining initial resource priority information in each motion state; updating the initial resource priority information in each motion state and the obtained historical lock grid state list of each target object to obtain current resource priority information in the corresponding motion state and a lock grid state list meeting requirements; and sending the grid locking state list meeting the requirement and the current resource priority information corresponding to each motion state in the target execution path to the corresponding target object for path execution processing. According to the scheme, the efficiency and quality of path re-planning can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of path planning and processing, and in particular to a path construction method, an electronic device and a computer-readable storage medium. Background Art

[0002] In applications such as smart warehousing, the multi-vehicle path planning method aims to plan a path for each robot that can avoid static obstacles, ensure that there are no collisions or deadlocks between robots, and minimize the overall operating costs. It has become the main method for solving warehouse robot scheduling and planning problems.

[0003] The current path planning method only considers multi-vehicle planning within the planning cycle, and each round of planning does not refer to historical planning results, resulting in insufficient re-planning efficiency and quality.

[0004] Therefore, a path construction method is urgently needed. Summary of the invention

[0005] The present application at least provides a path construction method, an electronic device and a computer-readable storage medium, which can improve the efficiency and quality of re-planning the path.

[0006] In a first aspect, the present application provides a path construction method, the method comprising: performing path reconstruction processing according to the historical planned path of each target object to obtain a target execution path of each target object, the target execution path comprising a motion state determined by adjacent waypoints; traversing the target execution path of each target object to obtain initial resource priority information under each motion state; updating the initial resource priority information under each motion state and the acquired historical lock grid state list of each target object to obtain current resource priority information under the corresponding motion state and a lock grid state list that meets the requirements; sending the lock grid state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing.

[0007] In one embodiment, the step of updating the initial resource priority information under each motion state and the acquired historical lock state list of each target object to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements includes: obtaining the current motion state of each target object in the corresponding target execution path and the historical lock state list of each target object; updating the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list; updating the initial resource priority information under the corresponding motion state according to the updated lock state list to obtain the current resource priority information under the corresponding motion state; performing lock state application processing according to the updated lock state list to obtain the lock state list that meets the requirements.

[0008] In one embodiment, the step of performing lock state application processing according to the updated lock state list to obtain the lock state list that meets the requirements includes: determining the motion state to be applied in the corresponding target execution path according to the target lock state in the updated lock state list; judging whether the motion state to be applied meets the requirements according to the number of lock states in the updated lock state list, the motion state to be applied, and the current resource priority information corresponding to the motion state to be applied; if so, adding the motion state to be applied to the updated lock state list to obtain the lock state list that meets the requirements.

[0009] In one embodiment, the step of updating the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list includes: determining the motion state to be released from the historical lock state list according to the current motion state; releasing the motion state to be released in the historical lock state list to obtain the updated lock state list.

[0010] In one embodiment, the step of updating the initial resource priority information under the corresponding motion state according to the updated lock state list to obtain the current resource priority information under the corresponding motion state includes: obtaining the motion state to be released when determining the updated lock state list; updating the initial resource priority information corresponding to the motion state to be released to obtain the current resource priority information corresponding to the motion state to be released.

[0011] In one embodiment, the step of performing path reconstruction processing based on the historical planning path of each target object to obtain the target execution path of each target object includes: reconstructing the initial planning path of each target object based on the historical planning path of each target object to obtain the target planning path of each target object; performing parallel solution processing on the initial planning path of each target object to obtain the target planning path of each target object; and initializing the target planning path of each target object to obtain the target execution path of each target object.

[0012] In one embodiment, the target planning path includes way points arranged in chronological order, and the step of initializing the target planning path of each target object to obtain the target execution path of each target object includes: performing path conversion processing on the way points in the target planning path of each target object to obtain the motion state path corresponding to each target object, the motion state path including a waiting state; and eliminating the waiting state in the motion state path to obtain the target execution path.

[0013] In one embodiment, the step of reconstructing the initial planned path of each target object based on the historical planned path of each target object includes: determining a replanned buffer path from the historical planned path according to the motion state of each target object in the corresponding historical planned path; performing path reconstruction processing using the target waypoint in the replanning buffer path as the replanning starting point to obtain the initial planned path of each target object.

[0014] A second aspect of the present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned path construction method.

[0015] A third aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, which implement the above-mentioned path construction method when the program instructions are executed by a processor.

[0016] The above scheme reconstructs the path according to the historical planning path of each target object to obtain the target execution path of each target object, and the target execution path includes the motion state determined by the adjacent waypoints; traverses the target execution path of each target object to obtain the initial resource priority information under each motion state and the historical lock state list of each target object; updates the initial resource priority information under each motion state and the historical lock state list of each target object to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; sends the lock state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing. On the one hand, considering the impact of the historical planning path on the reconstructed path, the efficiency and quality of the reconstructed path can be improved, and the operation stability of the target object within multiple planning cycle life-long can be maintained; on the other hand, by updating the current resource priority information corresponding to each motion state and the lock state list that meets the requirements, the timing of the target object when executing the reconstructed path can be guaranteed, and execution conflicts between target objects can be avoided.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0019] Figure 1 is a flowchart of an exemplary embodiment of a path construction method shown in the present application;

[0020] Figure 2 It is a schematic diagram of the effect of the path map in the path construction method shown in this application;

[0021] Figure 3 is a schematic diagram of a topological structure of an exemplary embodiment of a path construction method illustrated in the present application;

[0022] Figure 4 yes Figure 1 A schematic flow chart of an exemplary embodiment of step S130 in the path construction method shown;

[0023] Figure 5 yes Figure 1 A schematic flow chart of an exemplary embodiment of step S110 in the path construction method is shown;

[0024] Figure 6 is a schematic diagram of the effect of replanning a buffer path of an exemplary embodiment of a path construction method shown in the present application;

[0025] Figure 7 is a block diagram of a path construction device shown in an exemplary embodiment of the present application;

[0026] Figure 8 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0027] Fig. 9 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0028] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0029] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0030] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0031] First of all, it should be noted that in order to improve the efficiency and quality of re-planning the path. This application proposes a path construction method, an electronic device and a computer-readable storage medium. For details, please refer to Figure 1 , Figure 1 It is a flowchart of an exemplary embodiment of the path construction method shown in the present application.

[0032] The execution subject of the path construction method may be a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a computer, a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The execution subject of the path construction method may also be a path construction device with data processing and analysis capabilities. In some possible implementations, the path construction method may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0033] Specifically, the path construction method of this embodiment includes the following steps:

[0034] Step S110, performing path reconstruction processing according to the historical planning path of each target object to obtain the target execution path of each target object, where the target execution path includes the motion state determined by adjacent waypoints.

[0035] The target object can be a storage robot in a smart storage scenario or an unmanned vehicle on a traffic road. Figure 2 , Figure 2 FIG. 4 is a schematic diagram showing the effect of the target object's behavior map in an actual application scenario.

[0036] The historical planning path refers to the path that has been planned according to the starting point and end point of the robot and the robot is currently moving along the historical planning path.

[0037] The target execution path includes multiple waypoints, for example, Figure 2 The points in represent the waypoints of the robot's path.

[0038] The motion state describes the movement of the robot staying at a waypoint or moving from one waypoint to an adjacent waypoint. For example, if the robot moves from waypoint a to waypoint b, the motion state can be represented as motion_a_b, where waypoint a and waypoint b are the starting point and end point of the motion state, respectively. For another example, if the robot waits at waypoint c, the motion state can be represented as motion_c, where waypoint c is the starting point and end point of the motion state.

[0039] For details, please refer to Figure 3 , Figure 3 , a schematic diagram of the topological structure of robot A moving from waypoint 1 to waypoint 5 and robot B moving from waypoint 5 to waypoint 6 is shown in FIG. 4 . For example, the target execution path of robot A is motion_1_2, motion_2_3, motion_3_4, motion_4_5, and the target execution path of robot B is motion_5_4, motion_4_3, motion_3_9, motion_9_8, motion_8_7, motion_7_6. motion_1_2, motion_2_3, motion_3_4, motion_4_5 are the motion states in the target execution path of robot A, and motion_5_4, motion_4_3, motion_3_9, motion_9_8, motion_8_7, motion_7_6 are the motion states in the target execution path of robot B.

[0040] The path construction device performs path reconstruction processing according to the historical planned path of each target object to obtain the target execution path of each target object. It should be noted that the motion state in the target execution path in the embodiment of the present application includes other states except the waiting state. For the triggering of path reconstruction, as an exemplary embodiment, the path construction device may receive a historical planned path reconstruction instruction, and re-plan the historical planned path according to the historical planned path reconstruction instruction to obtain the target execution path of each target object. It should be noted that at this time, the end point of the re-planned path is the end point of the historical planned path. As another exemplary embodiment, the path construction device may receive a new task instruction, and re-plan the process according to the new task end point in the new task instruction to obtain the target execution path of each target object.

[0041] Step S120, traverse the target execution path of each target object to obtain initial resource priority information in each motion state.

[0042] The initial resource priority information under each motion state includes the robot priority order under each motion state, that is, the action priority order of different robots under the same motion state. Exemplarily, the initial resource priority information under each motion state can be manually set. For example, in a warehousing application, the priority of the robot that transports expedited items is manually set to be higher than the priority of the robot that transports ordinary items. As another example, the initial resource priority information can also be determined by traversing the actual driving speed of the robot, that is, the initial resource priority information is determined in sequence by traversing the arrival time of the robots under each motion state, and the priority of the robot that arrives at the target location first is set to be higher than the priority of the robot that arrives at the target location later. Please continue to refer to Figure 3 For motion state motion_1_2, since robot A starts from 1 and robot B starts from 5, for motion state motion_1_2, the initial resource priority information is that the priority of robot A is higher than the priority of robot B. For motion state motion_2_3, the priority of the robot that arrives first can be determined according to the travel distance and travel speed of robot A and robot B. For example, if robot B arrives at waypoint 3 first, the priority of motion state motion_2_3 and motion state motion_2_3motion_4_3 is that the priority of robot B is higher than the priority of robot A.

[0043] The embodiment of the present application traverses the target execution path of the target object, comprehensively considers the driving speed and driving distance of the target object during the traversal process, thereby improving the accuracy of the acquired initial resource priority information, and further executing according to the initial resource priority information can reduce the number of conflicts in the reconstructed path.

[0044] Step S130 , updating the initial resource priority information in each motion state and the acquired historical lock state list of each target object, to obtain the current resource priority information in the corresponding motion state and the lock state list that meets the requirements.

[0045] The historical lock state list of each target object includes the historical lock state, which is used to lock the path of the target object to be moved to avoid conflicts with the movement of other target objects. It should be noted that the number of locks in the historical lock state list can be set manually. For example, the number of locks in the historical lock state list can be 4. Figure 3 , if the current motion state of robot B is motion_4_3, then the historical lock state list of robot B can be {motion_5_4, motion_4_3, motion_3_9, motion_9_8}.

[0046] The current resource priority information refers to information that has been updated based on the initial resource priority information.

[0047] The lock state list that meets the requirements may be a list after releasing the lock state in the historical lock state list, or a list after applying for the lock state based on the historical lock state list, or a list after releasing the lock state in the historical lock state list and applying for the lock state.

[0048] The path construction device updates the initial resource priority information and the historical lock state list to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements. Exemplarily, the historical lock state list can be updated according to the number of lock states in the historical lock state list to obtain the lock state list that meets the requirements; the initial resource priority information is updated according to the actual path of the target object to obtain the current resource priority information under the corresponding motion state.

[0049] For updating the historical lock state list according to the number of lock states in the historical lock state list, a method for obtaining a lock state list that meets the requirements may be to release the lock state of the historical lock state list according to the number of lock states in the historical lock state list to obtain a lock state list that meets the requirements; or to apply for a lock state for the historical lock state list according to the number of lock states in the historical lock state list to obtain a lock state list that meets the requirements; or, to release the lock state of the historical lock state list according to the number of lock states in the historical lock state list, and apply for a lock state according to the current motion state and the historical lock state list to obtain a lock state list that meets the requirements. For example, it is determined whether the number of lock states in the historical lock state list is greater than a threshold value. If so, the first lock state in the historical lock state list is deleted; if not, a lock state adjacent to the last lock state is applied in the target execution path according to the last lock state in the historical lock state list. It should be noted that the applied lock state does not exist in the historical lock state list.

[0050] For updating the initial resource priority information according to the actual behavior process of the target object, the current resource priority information in the corresponding motion state can be obtained by recording the time when different target objects reach the corresponding motion state, adjusting the priority of the target object that has reached the corresponding motion state in the initial resource priority information, and obtaining the current resource priority information in the corresponding motion state. For example, the initial resource priority information of the corresponding motion state is that the priority of robot e is higher than that of robot f and higher than that of robot g. If robot f passes through the motion state first, the priority of robot f is adjusted, and the priority of robot g can be adjusted to be higher than that of robot f.

[0051] Step S140, sending the lock state list that meets the requirements and the current resource priority information corresponding to each motion state in the target execution path to the corresponding target object for path execution processing.

[0052] The path construction device sends the lock state list that meets the requirements of each target object and the current resource priority information corresponding to each motion state in the target execution path to the corresponding target object for path execution processing.

[0053] It can be seen that the path construction method of the embodiment of the present application performs path reconstruction processing according to the historical planning path of each target object, obtains the target execution path of each target object, and the target execution path includes the motion state determined by the adjacent waypoints; traverses the target execution path of each target object, obtains the initial resource priority information under each motion state and the historical lock state list of each target object; updates the initial resource priority information under each motion state and the historical lock state list of each target object, obtains the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; sends the lock state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing. On the one hand, considering the impact of the historical planning path on the reconstructed path, the efficiency and quality of the reconstructed path can be improved, and the operation stability of the target object within multiple planning cycle life-long can be maintained; on the other hand, by updating the current resource priority information corresponding to each motion state and the lock state list that meets the requirements, the timing of the target object during execution can be guaranteed, and execution conflicts between target objects can be avoided.

[0054] Based on the above embodiments, the embodiments of the present application describe in detail how to update the initial resource priority information and the historical lock state list. Figure 4 , Figure 4 yes Figure 1 A flowchart of an exemplary embodiment of step S130 in the path construction method is shown. Specifically, based on the above embodiment, step S130 updates the initial resource priority information in each motion state and the historical lock state list of each target object, and the process of obtaining the current resource priority information in the corresponding motion state and the lock state list that meets the requirements also includes the following steps:

[0055] Step S410, obtaining the current motion state of each target object in the corresponding target execution path and a list of historical lock states of each target object.

[0056] The current motion state may be directly acquired or determined based on positioning information. Specifically, the path construction device determines a similar position from the target planning path based on the positioning information, and determines the state of the similar position as the current motion state.

[0057] Step S420 , updating the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list.

[0058] In an embodiment of the present application, the path construction device updates the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list. Exemplarily, the path construction device determines the motion state to be released from the historical lock state list according to the current motion state of the target object, and releases the motion state to be released in the historical lock state list to obtain an updated lock state list.

[0059] Regarding the method of determining the motion state to be released from the historical lock state list according to the current motion state of the target object, it can be that the historical lock state matching the current motion state is determined from the historical lock state list according to the current motion state of the target object, and then the historical lock state in the historical lock state list that is separated by a preset value from the matching historical lock state is determined as the motion state to be released. It can also be that the first lock state in the historical lock state list is determined as the motion state to be released.

[0060] The method for releasing the to-be-released motion states in the historical lock state list to obtain the updated lock state list may be to delete the to-be-released motion states in the historical lock state list, and determine the historical lock state list after deleting the historical lock state as the updated lock state list.

[0061] You can continue to read Figure 3 , if the current motion state of the target object is motion_4_3, and the historical lock state list is {motion_5_4, motion_4_3, motion_3_9, motion_9_8}, then the motion state to be released is motion_5_4, and the updated lock state list is {motion_4_3, motion_3_9, motion_9_8}.

[0062] Step S430 , updating the initial resource priority information in the corresponding motion state according to the updated lock state list to obtain the current resource priority information in the corresponding motion state.

[0063] In the embodiment of the present application, the path construction device obtains the motion state to be released when determining the updated lock state list, updates the initial resource priority information corresponding to the motion state to be released, and obtains the current resource priority information corresponding to the motion state to be released. Continuing with the example in step S420, the motion state to be released is motion_5_4, and the initial resource priority information of motion_5_4 is that the priority of robot B is greater than the priority of robot A. The current resource priority information after motion_5_4 is updated is the priority of only robot A. It should be noted that in actual applications, each motion state may have a collision relationship with other motion states, for example Figure 3 In the example above, since motion state motion_5_4 and motion state motion_4_5 have a collision relationship, when updating the initial resource priority information of the motion state, it is also necessary to consider updating the initial resource priority information of the motion state that has a collision relationship with the motion state to be updated. Continuing with the above example, since motion state motion_5_4 has a collision relationship with motion state motion_4_5, when updating the initial resource priority information of motion state motion_5_4, it is also necessary to update the initial resource priority information of motion state motion_4_5. If the initial resource priority information of motion state motion_4_5 is that the priority of robot B is greater than the priority of robot A, the current resource priority information of motion state motion_4_5 after update is the priority of only robot A.

[0064] Step S440, performing lock state application processing according to the updated lock state list to obtain a lock state list that meets the requirements.

[0065] Regarding the lock state application method, the path construction device in the embodiment of the present application obtains the target lock state in the updated lock state list in the corresponding target execution path and the pending motion state; determines whether the pending motion state meets the requirements according to the number of lock states in the updated lock state list, the pending motion state, and the resource priority information corresponding to the pending motion state; if it meets the requirements, the pending motion state is added to the updated lock state list to obtain a lock state list that meets the requirements. Among them, the target lock state can be the last motion state in the updated lock state list. For example, the target execution path of robot B is motion_5_4, motion_4_3, motion_3_9, motion_9_8, motion_8_7, motion_7_6, the historical lock state list is {motion_5_4, motion_4_3, motion_3_9, motion_9_8}, and the updated lock state list is {motion_4_3, motion_3_9, motion_9_8}. Then the target lock state can be motion_9_8, and the motion state to be applied is the motion state motion_8_7 in the target execution path. For the number of lock states, if the updated lock state list is {motion_4_3, motion_3_9, motion_9_8}, the number of lock states is 3.

[0066] Regarding the method of judging whether the pending motion state meets the requirements according to the number of locked grid states in the updated locked grid state list, the pending motion state and the resource priority information corresponding to the pending motion state, specifically, the path construction device judges whether the number of locked grid states in the updated locked grid state list is less than or equal to the preset number of locked grid states, judges whether the pending motion state is occupied by other robots and judges whether the resource priority information corresponding to the pending motion state indicates that the priority of the current robot is higher than the priority of other robots. If the number of locked grid states is less than or equal to the preset number of locked grid states, the pending motion state is not occupied by other robots and the resource priority information corresponding to the pending motion state indicates that the priority of the current robot is higher than the priority of other robots, it is determined that the pending motion state meets the requirements, and the pending motion state is added to the updated locked grid state list to obtain a locked grid state list that meets the requirements. Continue with Figure 3To illustrate, if the current motion state of robot A is motion_1_2, the updated lock state list is {motion_1_2}, the motion state to be applied is motion_2_3, the resource priority information corresponding to motion_1_2 indicates that the priority of robot A is higher than the priority of other robots, the number of lock states in the updated lock state list meets the requirements, and the motion state to be applied is not occupied by other robots, then the motion state to be applied motion_2_3 can be added to the updated lock state list {motion_1_2} to obtain the lock state list {motion_1_2, motion_2_3} ​​that meets the requirements. If the resource priority information corresponding to motion_1_2 indicates that the highest priority is robot B, that is, the priority of robot B is higher than the priority of other robots, then the motion state to be applied motion_2_3 fails to be applied. After robot B executes motion state motion_3_9 and releases motion state motion_3_9, the priority of motion state motion_2_3 is updated to only robot A, and robot A can apply for motion state motion_2_3. In other cases, even after the robot has executed motion state motion_1_2, it can only be in waiting state wait_2 at waypoint 2.

[0067] It can be seen that the path construction method of the embodiment of the present application obtains the current motion state of each target object in the corresponding target execution path and the historical lock grid state list of each target object; updates the historical lock grid state list of the target object according to the current motion state of the target object to obtain an updated lock grid state list; updates the initial resource priority information under the corresponding motion state according to the updated lock grid state list to obtain the current resource priority information under the corresponding motion state; performs lock grid state application processing according to the updated lock grid state list to obtain a lock grid state list that meets the requirements. By setting the release and application rules of the lock grid state in the lock grid state list and using the resource priority information, the passage timing between target objects can be guaranteed and the number of conflicts between target objects can be reduced.

[0068] Based on the above embodiments, the present application embodiment describes in detail how to reconstruct the target execution path. Figure 5 , Figure 5 yes Figure 1 The flowchart of an exemplary embodiment of step S110 in the path construction method is shown. Specifically, based on the above embodiment, step S110 performs path reconstruction processing according to the historical planning path of each target object, and the process of obtaining the target execution path of each target object also includes the following steps:

[0069] Step S510, reconstructing the initial planned path of each target object according to the historical planned path of each target object.

[0070] The initial planned path is obtained by the path construction device through re-planning of MAPF (Multi-Agent Path Finding) based on the historical planned path.

[0071] Exemplarily, the path construction device can directly perform MAPF replanning according to the current running state of the target object in the historical planning path to obtain the initial planning path. As another example, considering the time-consuming MAPF replanning, the path construction device of the embodiment of the present application can set a replanning buffer path according to the historical planning path, and reconstruct the path according to the target waypoints in the replanning buffer path to obtain the initial planning path. Specifically, the path construction device obtains the motion state of the target object in the corresponding historical planning path. The motion state at this time represents the motion state of the target object in the historical planning path when path reconstruction is required, and determines the replanning buffer path from the historical planning path according to the motion state of each target object in the corresponding historical planning path; the path reconstruction process is performed using the target waypoints in the replanning buffer path as the replanning starting point to obtain the initial planning path of each target object. Among them, the replanning buffer path is a part of the historical planning path. The target waypoint can be a waypoint in the last motion state in the replanning buffer path. Exemplarily, please refer to Figure 6 , Figure 6 The replanning buffer path of robot 0-2 is shown in Figure 1. The replanning buffer path at this time is a path of 8 time steps starting from the current motion state of the robot. The replanning starting point is Figure 6 The MAPF enlightenment status shown in FIG.

[0072] It should be further explained that, in order to ensure that each target object can reach the end point in the reconstructed path, the embodiment of the present application replans the path according to a preset time step. Among them, the preset time step can be 200 time steps. In practical applications, a preset time step that is as large as possible can keep the initial planned path and the historical planned path as similar as possible, and can also enable the target object to reach the end point in the path constructed based on the preset time step. For target objects and newly added tasks that have not reached the end point in the initial planned path constructed based on the preset time step, tasks can be added to the corresponding target objects, and the path construction device replans the path according to the starting and ending points in the newly added tasks. It should be noted that A planning can be used for path planning.

[0073] Step S520 , performing parallel solution processing on the initial planning paths of each target object to obtain the target planning paths of each target object.

[0074] In order to improve the accuracy of obtaining the target planning path, the embodiment of the present application performs parallel solving processing on the reconstructed initial planning path to obtain the target planning path of each target object. Exemplarily, three solvers can be used to solve the initial planning path of each target object to obtain the solving speed of each solver, and the path solved by the solver with the fastest solving speed is selected as the target planning path of each target object.

[0075] Step S530, initializing the target planning path of each target object to obtain the target execution path of each target object.

[0076] The target planning path includes waypoints arranged in chronological order.

[0077] The path construction device performs path conversion processing on the waypoints in the target planning path of each target object to obtain the motion state path corresponding to each target object; and removes the waiting state in the motion state path to obtain the target execution path. Figure 3 , if the target planning path of robot A is 1223455, the motion states in the target planning path after path transformation are motion_1_2, wait_2, motion_2_3, motion_3_4, motion_4_5, wait_5. The target execution path after eliminating the waiting state is motion_1_2, motion_2_3, motion_3_4, motion_4_5.

[0078] It should be noted that, in order to ensure the rationality of the path, the embodiment of the present application can also make a rationality judgment based on the path information in the target execution path after the waiting state is removed. It should be further noted that, in order to ensure the integrity of the path, the path construction device of the embodiment of the present application can splice the target execution path after the waiting state is removed and the corresponding re-planning buffer path to obtain the target execution path of each target object.

[0079] It can be seen that the path construction method of the embodiment of the present application reconstructs the historical planning path of each target object to obtain the initial planning path of each target object; performs parallel solution processing on the initial planning path of each target object to obtain the target planning path of each target object; and performs initialization processing on the target planning path of each target object to obtain the target execution path of each target object. On the one hand, path reconstruction based on historical planning paths can improve planning efficiency and quality, and can maintain the stable operation of multi-vehicle path planning throughout the life cycle; on the other hand, the target planning path of each target object is determined by using a parallel solution method to improve the quality of the planned path.

[0080] Figure 7FIG. 1 is a block diagram of a path construction device shown in an exemplary embodiment of the present application. Figure 7 As shown, the exemplary path construction device 700 includes: a reconstruction module 710, a traversal module 720, an update module 730 and an execution module 740. Specifically:

[0081] The reconstruction module 710 is used to perform path reconstruction processing according to the historical planning path of each target object to obtain the target execution path of each target object, and the target execution path includes the motion state determined by adjacent waypoints.

[0082] The traversal module 720 is used to traverse the target execution path of each target object and obtain the initial resource priority information under each motion state.

[0083] The updating module 730 is used to update the initial resource priority information in each motion state and the acquired historical lock state list of each target object to obtain the current resource priority information in the corresponding motion state and the lock state list that meets the requirements.

[0084] The execution module 740 is used to send the lock state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing.

[0085] In this exemplary path construction device, path reconstruction is performed according to the historical planning path of each target object to obtain the target execution path of each target object, and the target execution path includes the motion state determined by the adjacent waypoints; the target execution path of each target object is traversed to obtain the initial resource priority information under each motion state and the historical lock state list of each target object; the initial resource priority information under each motion state and the historical lock state list of each target object are updated to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; the lock state list that meets the requirements and the current resource priority information corresponding to each motion state are sent to the corresponding target object for path execution processing. On the one hand, considering the impact of the historical planning path on the reconstructed path, the efficiency and quality of the reconstructed path can be improved, and the operation stability of the target object within multiple planning cycle life-long can be maintained; on the other hand, the current resource priority information corresponding to each motion state obtained by updating and the lock state list that meets the requirements can ensure the timing of the target object when executing the reconstructed path, and avoid execution conflicts between target objects.

[0086] The functions of each module can be found in the path construction method embodiment, which will not be repeated here.

[0087] See also Figure 8 , Figure 8The electronic device 80 includes a memory 81 and a processor 82, and the processor 82 is used to execute program instructions stored in the memory 81 to implement the steps in any of the above-mentioned path construction method embodiments.

[0088] In a specific implementation scenario, the electronic device 80 may include, but is not limited to: a microcomputer, a server, and in addition, the electronic device 80 may also include mobile devices such as a laptop computer and a tablet computer, which are not limited here.

[0089] Specifically, the processor 82 is used to control itself and the memory 81 to implement the steps in any of the above-mentioned path construction method embodiments. The processor 82 can also be called a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip with signal processing capabilities. The processor 82 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 82 can be implemented by an integrated circuit chip.

[0090] In the above scheme, the path construction method of the embodiment of the present application performs path reconstruction processing according to the historical planning path of each target object, obtains the target execution path of each target object, and the target execution path includes the motion state determined by the adjacent waypoints; traverses the target execution path of each target object, obtains the initial resource priority information under each motion state and the historical lock state list of each target object; updates the initial resource priority information under each motion state and the historical lock state list of each target object, obtains the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; sends the lock state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing. On the one hand, considering the impact of the historical planning path on the reconstructed path, the efficiency and quality of the reconstructed path can be improved, and the operation stability of the target object within multiple planning cycle life-long can be maintained; on the other hand, by updating the current resource priority information corresponding to each motion state and the lock state list that meets the requirements, the timing of the target object when executing the reconstructed path can be guaranteed, and execution conflicts between target objects can be avoided.

[0091] See also Fig. 9 , Fig. 9 The computer-readable storage medium 90 stores program instructions 91 that can be executed by a processor, and the program instructions 91 are used to implement the steps in any of the above-mentioned path construction method embodiments.

[0092] In the above scheme, the path construction method of the embodiment of the present application performs path reconstruction processing according to the historical planning path of each target object, obtains the target execution path of each target object, and the target execution path includes the motion state determined by the adjacent waypoints; traverses the target execution path of each target object, obtains the initial resource priority information under each motion state and the historical lock state list of each target object; updates the initial resource priority information under each motion state and the historical lock state list of each target object, obtains the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; sends the lock state list that meets the requirements and the current resource priority information corresponding to each motion state to the corresponding target object for path execution processing. On the one hand, considering the impact of the historical planning path on the reconstructed path, the efficiency and quality of the reconstructed path can be improved, and the operation stability of the target object within multiple planning cycle life-long can be maintained; on the other hand, by updating the current resource priority information corresponding to each motion state and the lock state list that meets the requirements, the timing of the target object when executing the reconstructed path can be guaranteed, and execution conflicts between target objects can be avoided.

[0093] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0094] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0095] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0096] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0097] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A path construction method, characterized in that: The method comprises: Performing path reconstruction processing according to the historical planning path of each target object to obtain a target execution path of each target object, wherein the target execution path includes a motion state determined by adjacent waypoints; Traverse the target execution path of each target object and obtain the initial resource priority information under each motion state; The initial resource priority information under each motion state and the acquired historical lock state list of each target object are updated to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements; The lock state list that meets the requirements and the current resource priority information corresponding to each motion state are sent to the corresponding target object for path execution processing.

2. The path construction method according to claim 1, characterized in that: The step of updating the initial resource priority information under each motion state and the acquired historical lock state list of each target object to obtain the current resource priority information under the corresponding motion state and the lock state list that meets the requirements includes: Obtain the current motion state of each target object in the corresponding target execution path and the historical lock state list of each target object; updating the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list; The initial resource priority information in the corresponding motion state is updated according to the updated lock state list to obtain the current resource priority information in the corresponding motion state; The lock state application process is performed according to the updated lock state list to obtain the lock state list that meets the requirements.

3. The path construction method according to claim 2, characterized in that: The step of performing lock state application processing according to the updated lock state list to obtain the lock state list that meets the requirements includes: Determine the motion state to be applied for in the corresponding target execution path according to the target lock state in the updated lock state list; Determining whether the motion state to be applied meets the requirement according to the number of locked grid states in the updated locked grid state list, the motion state to be applied for, and the current resource priority information corresponding to the motion state to be applied for; If the requirements are met, the motion state to be applied for is added to the updated lock state list to obtain the lock state list that meets the requirements.

4. The path construction method according to claim 2, characterized in that: The step of updating the historical lock state list of the target object according to the current motion state of the target object to obtain an updated lock state list includes: Determine the motion state to be released from the historical lock state list according to the current motion state; The motion states to be released in the historical lock state list are released to obtain the updated lock state list.

5. The path construction method according to claim 2, characterized in that: The step of updating the initial resource priority information in the corresponding motion state according to the updated lock state list to obtain the current resource priority information in the corresponding motion state includes: Acquire the to-be-released motion state when determining the updated lock state list; The initial resource priority information corresponding to the motion state to be released is updated to obtain the current resource priority information corresponding to the motion state to be released.

6. The path construction method according to claim 1, characterized in that: The step of performing path reconstruction processing according to the historical planning paths of each target object to obtain the target execution path of each target object includes: Reconstruct the initial planning path of each target object according to the historical planning path of each target object; The initial planning paths of each target object are solved in parallel to obtain the target planning paths of each target object; The target planning path of each target object is initialized to obtain the target execution path of each target object.

7. The path construction method according to claim 6, characterized in that: The target planning path includes waypoints arranged in chronological order, and the step of initializing the target planning path of each target object to obtain the target execution path of each target object includes: Performing path conversion processing on the waypoints in the target planning path of each target object to obtain the motion state path corresponding to each target object, wherein the motion state path includes a waiting state; The waiting state in the motion state path is eliminated to obtain the target execution path.

8. The path construction method according to claim 6, characterized in that: The step of reconstructing the initial planning path of each target object according to the historical planning path of each target object comprises: Determining a replanned buffer path from the historical planning paths according to the motion state of each target object in the corresponding historical planning path; The target waypoint in the replanned buffer path is used as a replanning starting point to perform path reconstruction processing to obtain an initial planned path for each target object.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the path construction method according to any one of claims 1 to 8.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the path construction method according to any one of claims 1 to 8 is implemented.

Images