Intelligent agent path planning method and device, equipment and medium

Abstract

The invention relates to the technical field of agents, and provides an agent path planning method and device, equipment and a medium, and the method comprises the steps: obtaining an initial position, a target position and an environment map of an agent; and according to the initial position, the target position and the environment map of the intelligent agent, performing path search by using a reserved redistribution-based adaptive window type hierarchical cooperation A algorithm to obtain a planned path of the intelligent agent. According to the acquired initial position, the target position and the environment map of the intelligent agent, the algorithm can fully understand the operation environment of the intelligent agent, accurate basic data is provided for subsequent path planning, the requirements of different initial positions and target positions are met, support is provided for various scenes, and the method is suitable for large-scale popularization and application. And furthermore, the flexibility of path planning and the adaptability of the algorithm to a dynamic environment are enhanced by utilizing an adaptive window type hierarchical cooperation A algorithm based on reservation redistribution, so that a multi-agent system can more effectively cooperatively work in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent agent technology, and in particular to an intelligent agent path planning method, device, equipment and medium. Background Art

[0002] Multi-machine path planning in a multi-business automated warehousing scenario involves coordinating multiple agents to perform tasks in a warehousing environment to ensure efficient and conflict-free material transportation and management. This involves planning the optimal path for each agent from its starting location to its destination while avoiding conflicts with other agents. Mathematically, this problem can be classified as a Multi-Agent Path Finding Problem (MAPF), the core of which is to plan paths for multiple agents (such as mobile agents) in a shared environment so that they can reach their destination from their respective starting points while avoiding conflicts and collisions.

[0003] In the field of multi-agent path planning, a global path planning method is often used to find an optimal path. This method obtains a known environment, builds an environmental model, and then plans an optimal path for the agent based on the environmental model.

[0004] However, although the global path planning method can find the optimal path, it requires accurate information about the environment in advance. In a complex and dynamically changing environment, this may lead to deficiencies in global path planning, especially in resolving path conflicts and obtaining the global optimal solution. Summary of the Invention

[0005] The present invention provides an intelligent agent path planning method, device, equipment and medium to address the defects of the global path planning method in the prior art, which is unable to cope with environmental changes and has poor robustness. It adapts to the needs of different starting and target positions, enhances the flexibility of path planning and the adaptability of the algorithm to dynamic environments, and enables multi-agent systems to work together more effectively in complex environments.

[0006] The present invention provides an intelligent agent path planning method, comprising: obtaining a starting position, a target position and an environment map of the intelligent agent; performing a path search based on the starting position, the target position and the environment map of the intelligent agent using an adaptive window-type hierarchical cooperative A algorithm based on reserved redistribution to obtain a planned path for the intelligent agent.

[0007] According to an agent path planning method provided by the present invention, a path search is performed based on the starting position, target position and environment map of the agent using an adaptive window-type hierarchical cooperative A algorithm based on reservation and redistribution to obtain a planned path for the agent, including: SA, based on a preset time window, for each agent, extracting the node with the minimum cost from the preset open set of the corresponding agent, and adding it to a preset closed set created in advance; wherein, during initialization, the node in the preset open set is the initial node determined based on the starting position of the corresponding agent and the preset cost of the initial node; SB, based on the node with the minimum cost and the environment map, determining the corresponding neighbor node, and eliminating the neighbor node in the preset closed set; SC, for each neighbor node, using a search-based time sequence A algorithm, Determine the first cost from the initial node to the neighbor node via the node with the minimum cost, and use the real-time repair A algorithm to perform a reverse search from the target node to the neighbor node to obtain the second cost; wherein the target node is determined based on the target position of the corresponding agent; SD, based on the first cost and the second cost, determine the total cost of the corresponding neighbor node; SE, based on the total cost of each neighbor node, select the neighbor node corresponding to the minimum total cost as the next path node in the planned path of the corresponding agent, and update the next path node and its corresponding total cost to the preset open set of the corresponding agent; SF, based on the preset time step, adjust the preset time window, and use the adjusted preset time window to iterate steps SA-SE until the preset maximum number of iterations is reached to obtain the corresponding planned path.

[0008] According to the present invention, a method for intelligent agent path planning is provided for determining corresponding neighbor nodes based on a node with the lowest cost and an environment map, including: determining the corresponding neighbor nodes based on the node with the lowest cost and the environment map; removing the corresponding neighbor nodes when it is determined, based on the status of each neighbor node in the environment map, that the corresponding neighbor nodes have obstacles or are occupied; and / or removing the corresponding neighbor nodes when it is determined, based on the status of each neighbor node in the environment map, that the intelligent agent is in a restricted traffic type corresponding to the neighbor nodes; Using the search-based timing A algorithm, the first cost from the initial node to the neighbor node via the node with the minimum cost is determined, including: determining the actual cost from the initial node to the node with the minimum cost based on the node with the minimum cost; using the search-based timing A algorithm, searching from the node with the minimum cost to the neighbor node to obtain the estimated cost; obtaining the corresponding first cost based on the actual cost and the estimated cost.

[0009] According to a method for intelligent agent path planning provided by the present invention, after selecting the neighbor node corresponding to the minimum total cost as the next path node in the corresponding intelligent agent's planned path, the method includes: adding the next path node determined by all intelligent agents within the current preset time window to a previously created reservation table; detecting whether there are at least two intelligent agents occupying the same node at the same time within the current preset time window in the reservation table; if so, combining the intelligent agent allocation priority, re-based on the starting position, target position and environment map of the intelligent agents corresponding to the same node, using the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation, to perform path search.

[0010] According to an agent path planning method provided by the present invention, the total cost of the corresponding neighbor node is determined according to the first cost and the second cost, including: determining the first position cost according to the node with the smallest cost and the previous node of the node with the smallest cost and the corresponding adjacent node; determining whether the road section belongs to a different map in combination with the environment map according to the road section composed of the previous node of the node with the smallest cost through the node with the smallest cost to the corresponding adjacent node, and obtaining the corresponding second position cost; wherein the second position cost is set in advance based on different types of agents and their maps; determining the corresponding third position cost according to the corresponding agent; wherein the third position cost is set in advance based on the agent driving in a straight line in the corresponding preset driving area; and obtaining the total cost of the corresponding neighbor node according to the first position cost, the second position cost, the third position cost, the first cost and the second cost.

[0011] According to an intelligent agent path planning method provided by the present invention, a first position cost is determined based on the node with the minimum cost and the previous node of the node with the minimum cost and the corresponding adjacent node, including: determining whether the road section composed of the previous node of the node with the minimum cost through the node with the minimum cost to the corresponding adjacent node is a turning section based on the node with the minimum cost and the previous node of the node with the minimum cost and the corresponding adjacent node; if it is a turning section, the node with the minimum cost and the previous node of the node with the minimum cost and the corresponding adjacent node determine the corresponding turning angle, and based on the turning angle, search for preset position cost information to determine the corresponding first position cost; wherein, the preset position cost information is first constructed based on different types of intelligent agents and their turning behaviors in the corresponding driving map area; otherwise, the corresponding adjacent node is determined to be an extreme point, and the preset position cost corresponding to the extreme point is obtained to obtain the corresponding first position cost; wherein, the preset position cost is first set based on different types of intelligent agents and their corresponding driving map types.

[0012] According to a method for intelligent agent path planning provided by the present invention, after obtaining the planned path of the intelligent agent, the method includes: sending the planned path of the intelligent agent to a preset middleware to convert the format of the planned path of the intelligent agent according to the type of the intelligent agent to be sent, and sending the planned path after format conversion to the corresponding intelligent agent to be sent.

[0013] The present invention also provides an intelligent agent path planning device, including: a data acquisition module, which obtains the starting position, target position and environmental map of the intelligent agent; a path planning module, which performs path search based on the starting position, target position and environmental map of the intelligent agent and uses an adaptive window-based hierarchical cooperative A algorithm based on reserved redistribution to obtain the planned path of the intelligent agent.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the intelligent agent path planning method as described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described intelligent agent path planning methods.

[0016] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described intelligent agent path planning methods.

[0017] The agent path planning method, device, equipment and medium provided by the present invention ensure that the algorithm can fully understand the agent's operating environment based on the acquired agent's starting position, target position and environmental map, provide accurate basic data for subsequent path planning, and adapt to the needs of different starting positions and target positions, provide support for various scenarios, and further utilize the adaptive window-based hierarchical cooperative A algorithm (RRA) based on reserved reallocation. -WHCA Windowed Hierarchical Cooperation A Algorithm (WHCA) ) layering and windowing techniques to preliminarily plan the multi-agent path and combine it with real-time repair (RRA) ) mechanism and reverse search, which enhances the flexibility of path planning and the adaptability of the algorithm to dynamic environments, enabling multi-agent systems to work together more effectively in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 1 is a flow chart of the intelligent agent path planning method provided by the present invention; Figure 2 It is a structural diagram of the intelligent agent path planning device provided by the present invention; Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0021] Figure 1 It is a flow chart of the intelligent agent path planning method provided by the present invention, such as Figure 1 As shown, the method includes: S11, obtain the agent's starting position, target position and environment map; S12, according to the starting position, target position and environment map of the intelligent agent, the adaptive window-based hierarchical cooperation A algorithm based on reservation and redistribution is used to perform path search to obtain the planned path of the intelligent agent.

[0022] It should be noted that the step numbers “S1N” in this specification do not represent the sequence of the intelligent agent path planning method. The intelligent agent path planning method of the present invention is described in detail below.

[0023] Step S11, obtaining the agent's starting position, target position and environment map.

[0024] It should be noted that the starting and target positions of at least one agent are obtained. The specific number can be configured based on actual design requirements and is not further specified here. Furthermore, by obtaining the starting and target positions of the agents and the environment map, subsequent path planning based on the starting and target positions of each agent, combined with the environment map, ensures that all agents can find the optimal path.

[0025] It should be noted that in actual applications, especially in the context of multi-vendor heterogeneous systems, different types of agents often need to perform independent operations in specific areas. Therefore, the environment map needs to be divided based on the agent operation area to ensure that each agent can only operate within its designated area, thereby ensuring that the agent does not operate out of bounds, avoiding regional conflicts and path overlaps, and providing neighbor information of each node during path planning so that the corresponding neighbor nodes can be accessed during path search.

[0026] It should be added that before obtaining the starting position and target position of the agent, the basic parameters required for path planning are initialized, including the environment map, parameters of each agent, preset time window size and preset maximum number of iterations.

[0027] In step S12, according to the starting position, target position and environment map of the agent, a path search is performed using the adaptive window-based hierarchical cooperation A algorithm based on reservation and redistribution to obtain the planned path of the agent.

[0028] In this embodiment, according to the starting position, target position and environment map of the agent, the reservation-based reallocation adaptive window-type layered cooperation A algorithm (Reservation-based Reallocation Adaptive WHCA , referred to as RRA -WHCA ), perform path search, and obtain the planned path of the agent, including: SA, based on a preset time window, for each agent, extract the node with the minimum cost from the preset open set of the corresponding agent, and add it to the preset closed set created in advance; wherein, during initialization, the node in the preset open set is the initial node and the preset cost of the initial node determined based on the starting position of the corresponding agent; SB, based on the node with the minimum cost and the environment map, determine the corresponding neighbor node, and eliminate the neighbor nodes in the preset closed set; SC, for each neighbor node, use the Search-based Temporal A algorithm (STA) to determine the first cost from the initial node to the neighbor node via the node with the minimum cost, and use the Real-time Repair A algorithm (STA) to determine the cost of the node. , RRA ), perform a reverse search from the target node to the neighbor node to obtain the second cost; wherein the target node is determined based on the target position of the corresponding agent; SD, determine the total cost of the corresponding neighbor node based on the first cost and the second cost; SE, select the neighbor node corresponding to the minimum total cost as the next path node in the corresponding agent's planned path based on the total cost of each neighbor node, and update the next path node and its corresponding total cost to the preset open set of the corresponding agent; SF, adjust the preset time window based on the preset time step, and use the adjusted preset time window to iterate steps SA-SE until the preset maximum number of iterations is reached to obtain the corresponding planned path.

[0029] It should be noted that through WHCA The layering is used to calculate the corresponding and window technology for each agent, preliminarily plan the path of multiple agents, and combine it with real-time repair (RRA ) mechanism and reverse search, which enhances the flexibility and adaptability of path planning. Through a hierarchical approach, the scale of multi-agent path planning problems is simplified, the calculation speed is improved, and the window technology is used to focus on local path optimization, reducing the computational burden of global search. It is further combined with a real-time repair mechanism to dynamically detect and repair path conflicts, enhance the algorithm's adaptability to dynamic environments, and ensure the feasibility of the path.

[0030] If the open set is empty and no path is found, a preset character representing the corresponding meaning is returned. The preset character can be set according to actual design requirements, such as None, etc., and is not further defined here. In addition, in the initial iteration, the nodes in the preset open set are the initial nodes and the preset costs corresponding to the initial nodes. In subsequent iterations, the nodes in the preset open set can be determined based on the updates during the previous iteration. For details, please refer to the above process, which will not be further described here. In addition, by using STA, priority queues (preset open sets) and preset closed sets are used to manage pending and processed nodes, and RRA is considered during the planning process. The object provides reverse cost estimation to optimize the path, RRA Used to support STA in accurate cost evaluation during path planning.

[0031] Specifically, the corresponding neighbor nodes are determined based on the node with the minimum cost and the environment map, including: determining the corresponding neighbor nodes based on the node with the minimum cost and the environment map; eliminating the corresponding neighbor nodes when it is determined that the corresponding neighbor nodes have obstacles or are occupied based on the status of each neighbor node in the environment map; and / or eliminating the corresponding neighbor nodes when it is determined that the intelligent agent is the restricted type of the corresponding neighbor nodes based on the status of each neighbor node in the environment map.

[0032] It should be noted that by determining whether the neighbor nodes in the environment map have obstacles or are occupied by vehicles, or whether the left and right channels restrict the passage of only some types of intelligent agents, the obtained neighbor nodes are ensured to be valid nodes, thereby improving the accuracy of subsequent path planning.

[0033] In addition, the search-based timing A algorithm is used to determine the first cost from the initial node to the neighbor node via the node with the lowest cost, including: determining the actual cost from the initial node to the node with the lowest cost based on the node with the lowest cost; using the search-based timing A algorithm, searching from the node with the lowest cost to the neighbor node to obtain the estimated cost; and obtaining the corresponding first cost based on the actual cost and the estimated cost.

[0034] It should be added that the actual cost can be obtained based on the previous actual search or the total cost of the node with the minimum cost stored in the preset open set. That is, when the neighbor node determined as the next path node in the last iteration is the node with the minimum cost currently taken out from the preset open set, the actual cost is the first cost of the neighbor node determined as the next path node in the last iteration.

[0035] In addition, the search-based timing A algorithm is used to search from the node with the lowest cost to the neighboring node to obtain the estimated cost, including: using the search-based timing A algorithm to search from the node with the lowest cost to the neighboring node to obtain the path length; and obtaining the estimated cost based on the path length and the preset proportional coefficient.

[0036] In addition, the second cost may be obtained through functions such as the Manhattan distance, and may be specifically determined based on a function of the path planning (RRA) of the real-time repair A algorithm actually used, which is not further limited here.

[0037] In an optional embodiment, the total cost of the corresponding neighbor node is determined based on the first cost and the second cost, including: determining the first position cost based on the node with the smallest cost and the previous node of the node with the smallest cost and the corresponding adjacent node; determining whether the road section belongs to a different map based on the road section composed of the previous node of the node with the smallest cost through the node with the smallest cost to the corresponding adjacent node, combined with the environmental map, to obtain the corresponding second position cost; wherein, the second position cost is set in advance based on different types of intelligent agents and their maps; determining the corresponding third position cost based on the corresponding intelligent agent; wherein, the third position cost is set in advance based on the intelligent agent driving in a straight line within the corresponding preset driving area; and obtaining the total cost of the corresponding neighbor node based on the first position cost, the second position cost, the third position cost, the first cost and the second cost.

[0038] Furthermore, the first position cost is determined based on the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node, including: determining whether the road section consisting of the previous node of the node with the minimum cost, the node with the minimum cost, and the corresponding adjacent node is a turning section based on the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node; if it is a turning section, the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node determine the corresponding turning angle, and based on the turning angle, search for the preset position cost information to determine the corresponding first position cost; wherein, the preset position cost information is first constructed based on different types of intelligent agents and their turning behaviors in the corresponding driving map area; otherwise, determine the corresponding adjacent node as an extreme point, and obtain the preset position cost corresponding to the extreme point to obtain the corresponding first position cost; wherein, the preset position cost is first set based on different types of intelligent agents and their corresponding driving map types.

[0039] It should be noted that the turning angle can be determined based on the coordinates of the node with the lowest cost, its previous node, and its corresponding adjacent nodes. The corresponding position cost is determined based on different turning angles and in combination with preset position cost information previously set based on actual experiments or prior experience. Furthermore, the first position cost of the extreme point is greater than the first position cost corresponding to the turning angle. This can be specifically configured based on actual experimental results or prior experience and is not further specified here.

[0040] It is worth noting that when considering the turning interval, by assuming that each heterogeneous vehicle has two turning times and speeds under the average speed, namely, empty and fully loaded conditions, the actual average speed and average turning speed of the heterogeneous agent in these two cases are measured and substituted into the experiment to determine the corresponding first position cost.

[0041] In an optional embodiment, after obtaining the planned path of the intelligent agent, it includes: sending the planned path of the intelligent agent to a preset middleware to convert the format of the planned path of the intelligent agent according to the type of the intelligent agent to be sent, and sending the planned path after format conversion to the corresponding intelligent agent to be sent.

[0042] In an optional embodiment, after selecting the neighbor node corresponding to the minimum total cost as the next path node in the planned path of the corresponding intelligent agent, it includes: adding the next path node determined by all intelligent agents within the current preset time window to a previously created reservation table; detecting whether there are at least two intelligent agents occupying the same node at the same time within the current preset time window in the reservation table. If so, combining the priority of the intelligent agents, re-based on the starting position, target position and environment map of the intelligent agents corresponding to the same node, using the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation, the path search is re-performed.

[0043] It should be noted that by adding the next path node of the agent determined within the same preset time window to the reservation table, the reservation mechanism can be used to allocate path resources to the agent in advance to avoid conflicts. This makes it easier to re-search the path in combination with the agent allocation priority when a path conflict occurs, ensuring the feasibility of the overall path planning. When the corresponding node is re-searched, it is assigned to the agent with a high priority, and the node of the agent with a low priority is searched. The specific steps are described above and will not be repeated here. In addition, based on the above method, it is convenient to manage the reservation status of each path node of the agent during the path planning process. By looking up the status (is available) of the corresponding reservation table, it is determined whether any node is available at a specific time step. In this way, after determining the planned path, the corresponding planned path can be reserved and the occupancy information of the nodes in the path can be recorded to ensure that the same time step is not occupied by multiple agents.

[0044] In addition, after the corresponding planned path is sent to the corresponding intelligent agent, the next path node is reserved in advance based on the reservation window of preset length by looking up the reservation table, and the previous path node is released to avoid collisions caused by multiple intelligent agents arriving at the same location at the same time. Through the reserved reallocation mechanism, path resources are allocated to the intelligent agent in advance, and when a path conflict occurs, the path allocation of the intelligent agent is dynamically adjusted to ensure the feasibility of the overall path planning.

[0045] In summary, the embodiment of the present invention ensures that the algorithm can fully understand the operating environment of the intelligent agent based on the obtained starting position, target position and environment map, provides accurate basic data for subsequent path planning, adapts to the needs of different starting positions and target positions, provides support for various scenarios, and further utilizes the adaptive window-based hierarchical cooperation A algorithm (RRA) based on reservation reallocation. -WHCA Windowed Hierarchical Cooperation A Algorithm (WHCA) ) layering and windowing techniques to preliminarily plan the multi-agent path and combine it with real-time repair (RRA) ) mechanism and reverse search, which enhances the flexibility of path planning and the adaptability of the algorithm to dynamic environments, enabling multi-agent systems to work together more effectively in complex environments.

[0046] The intelligent agent path planning device provided by the present invention is described below. The intelligent agent path planning device described below and the intelligent agent path planning method described above can be referenced to each other.

[0047] Figure 2 A schematic structural diagram of an intelligent agent path planning device is shown, the device comprising: Data acquisition module 21, obtains the agent's starting position, target position and environment map; The path planning module 22 performs path search based on the starting position, target position and environment map of the intelligent agent using the adaptive window-type hierarchical cooperation A algorithm based on reservation and redistribution to obtain the planned path of the intelligent agent.

[0048] In this embodiment, the path planning module 22 is configured to: SA, based on a preset time window, extract the node with the lowest cost from the preset open set of the corresponding agent for each agent, and add it to the preset closed set created previously; wherein, during initialization, the node in the preset open set is the initial node determined based on the starting position of the corresponding agent and the preset cost of the initial node; SB, based on the node with the lowest cost and the environment map, determines the corresponding neighbor node and eliminates the neighbor nodes in the preset closed set; SC, for each neighbor node, uses the Search-based Temporal A algorithm (STA) to determine the first cost from the initial node to the neighbor node via the node with the lowest cost, and uses the Real-time Repair A algorithm (RTA) to determine the cost of the node. , RRA ), perform a reverse search from the target node to the neighbor node to obtain the second cost; wherein the target node is determined based on the target position of the corresponding agent; SD, determine the total cost of the corresponding neighbor node based on the first cost and the second cost; SE, select the neighbor node corresponding to the minimum total cost as the next path node in the corresponding agent's planned path based on the total cost of each neighbor node, and update the next path node and its corresponding total cost to the preset open set of the corresponding agent; SF, adjust the preset time window based on the preset time step, and use the adjusted preset time window to iterate steps SA-SE until the preset maximum number of iterations is reached to obtain the corresponding planned path.

[0049] Specifically, the path planning module 22 includes: a neighbor node determination unit, which determines the corresponding neighbor node based on the node with the lowest cost and the environment map; a valid node screening unit, which determines that the corresponding neighbor node has an obstacle or is occupied according to the status of each neighbor node in the environment map, and then eliminates the corresponding neighbor node; and / or, when it is determined that the intelligent agent is the restricted type of the corresponding neighbor node according to the status of each neighbor node in the environment map, the corresponding neighbor node is eliminated.

[0050] In addition, the path planning module 22 also includes: an actual cost determination unit, which determines the actual cost from the initial node to the node with the minimum cost based on the node with the minimum cost; a cost estimation unit, which uses the search-based timing A algorithm to search from the node with the minimum cost to the neighboring node to obtain the estimated cost; and a first cost determination unit, which obtains the corresponding first price based on the actual cost and the estimated cost.

[0051] Furthermore, the cost estimation unit includes: a path search subunit, which uses a search-based sequential A algorithm to search from the node with the lowest cost to the neighboring node to obtain the path length; a cost estimation subunit, which obtains an estimated cost based on the path length and a preset proportional coefficient.

[0052] In an optional embodiment, the path planning module 22 also includes: a first position cost acquisition unit, which determines the first position cost based on the node with the minimum cost and the previous node of the node with the minimum cost and the corresponding adjacent node; a second position cost acquisition unit, which determines whether the road section belongs to a different map based on the road section composed of the previous node of the node with the minimum cost through the node with the minimum cost to the corresponding adjacent node, combined with the environmental map, to obtain the corresponding second position cost; wherein, the second position cost is set in advance based on different types of intelligent agents and their maps; a third position cost acquisition unit, which determines the corresponding third position cost based on the corresponding intelligent agent; wherein, the third position cost is set in advance based on the intelligent agent driving in a straight line within the corresponding preset driving area; a total cost determination unit, which obtains the total cost of the corresponding neighbor node based on the first position cost, the second position cost, the third position cost, the first cost and the second cost.

[0053] Furthermore, the first position cost acquisition unit includes: a turning judgment subunit, which determines whether the road section composed of the previous node of the node with the minimum cost, the node with the minimum cost and the corresponding adjacent node is a turning section based on the node with the minimum cost, the previous node of the node with the minimum cost and the corresponding adjacent node; the first position cost acquisition subunit, if it is a turning section, determines the corresponding turning angle based on the node with the minimum cost, the previous node of the node with the minimum cost and the corresponding adjacent node, and searches for the preset position cost information based on the turning angle to determine the corresponding first position cost; wherein, the preset position cost information is constructed in advance based on different types of intelligent agents and their turning behaviors in the corresponding driving map area; otherwise, the corresponding adjacent node is determined to be an extreme point, and the preset position cost corresponding to the extreme point is obtained to obtain the corresponding first position cost; wherein, the preset position cost is set in advance based on different types of intelligent agents and their corresponding driving map types.

[0054] In an optional embodiment, the path planning module 22 further includes: a reservation unit, which, after selecting the neighbor node corresponding to the minimum total cost as the next path node in the corresponding agent's planned path, adds the next path node determined by all agents within the current preset time window to a previously created reservation table; a detection unit, which detects whether there are at least two agents occupying the same node at the same time within the current preset time window in the reservation table. If so, the re-planning unit, in combination with the agent allocation priority, re-performs the path search based on the starting position, target position and environment map of the agents corresponding to the same node, using the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation.

[0055] In an optional embodiment, the device further includes: a path sending module, which, after obtaining the planned path of the intelligent body, sends the planned path of the intelligent body to a preset middleware, so as to convert the format of the planned path of the intelligent body according to the type of the intelligent body to be sent, and sends the planned path after format conversion to the corresponding intelligent body to be sent.

[0056] In summary, the embodiment of the present invention uses the path planning module to obtain the starting position, target position and environment map of the intelligent agent based on the data acquisition module to ensure that the algorithm can fully understand the operating environment of the intelligent agent, provide accurate basic data for subsequent path planning, and adapt to the needs of different starting positions and target positions, provide support for various scenarios, and further utilize the adaptive window-based hierarchical cooperative A algorithm (RRA) based on reservation reallocation. -WHCA Windowed Hierarchical Cooperation A Algorithm (WHCA) ) layering and windowing techniques to preliminarily plan the multi-agent path and combine it with real-time repair (RRA) ) mechanism and reverse search, which enhances the flexibility of path planning and the adaptability of the algorithm to dynamic environments, enabling multi-agent systems to work together more effectively in complex environments.

[0057] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 communicate with each other via the communications bus 340. The processor 310 may call logic instructions in the memory 330 to execute an agent path planning method, which includes: obtaining the agent's starting position, target position, and environment map; and performing a path search using an adaptive windowed hierarchical cooperative A algorithm based on reservation reallocation based on the agent's starting position, target position, and environment map to obtain a planned path for the agent.

[0058] Furthermore, the logic instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0059] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent agent path planning method provided by the above methods, which includes: obtaining the starting position, target position and environment map of the intelligent agent; according to the starting position, target position and environment map of the intelligent agent, using the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation to perform path search and obtain the planned path of the intelligent agent.

[0060] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the intelligent agent path planning method provided by the above-mentioned methods. The method includes: obtaining the starting position, target position and environment map of the intelligent agent; according to the starting position, target position and environment map of the intelligent agent, using the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation to perform path search and obtain the planned path of the intelligent agent.

[0061] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0062] Through the description of the above embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An agent path planning method, characterized in that: include: Get the agent's starting position, target position, and environment map; According to the starting position, target position and environment map of the intelligent agent, a path search is performed using an adaptive window-type hierarchical cooperation A algorithm based on reservation and reallocation to obtain a planned path for the intelligent agent.

2. The agent path planning method according to claim 1, characterized in that: According to the starting position, target position and environment map of the agent, a path search is performed using an adaptive window-based hierarchical cooperative A algorithm based on reservation and redistribution to obtain a planned path for the agent, including: SA, based on a preset time window, extracts the node with the lowest cost from the preset open set of each agent and adds it to the previously created preset closed set; wherein, during initialization, the nodes in the preset open set are the initial nodes determined based on the starting position of the corresponding agent and the preset cost of the initial nodes; SB, determining corresponding neighbor nodes according to the node with the minimum cost and the environment map, and eliminating neighbor nodes in the preset closed set; SC, for each neighbor node, uses a search-based sequential A algorithm to determine a first cost from the initial node to the neighbor node via the node with the lowest cost, and uses a real-time repair A algorithm to perform a reverse search from the target node to the neighbor node to obtain a second cost; wherein the target node is determined based on the target position of the corresponding agent; SD, determining a total cost of the corresponding neighbor node based on the first cost and the second cost; SE, based on the total cost of each of the neighboring nodes, selects the neighboring node corresponding to the minimum total cost as the next path node in the planned path of the corresponding agent, and updates the next path node and its corresponding total cost to the preset open set of the corresponding agent; SF, based on the preset time step, adjusts the preset time window, and uses the adjusted preset time window to iterate steps SA-SE until a preset maximum number of iterations is reached to obtain the corresponding planned path.

3. The agent path planning method according to claim 2, characterized in that: Determining a corresponding neighbor node according to the node with the minimum cost and the environment map includes: Determining a corresponding neighbor node according to the node with the minimum cost and the environment map; When it is determined based on the status of each neighboring node in the environment map that an obstacle exists or the corresponding neighboring node is occupied, the corresponding neighboring node is removed; and / or, When determining, based on the state of each neighboring node in the environment map, that the agent is a restricted type of a corresponding neighboring node, removing the corresponding neighboring node; Determining a first cost for the initial node to reach the neighbor node via the node with the minimum cost by using a search-based sequential A algorithm includes: Determining, based on the node with the minimum cost, an actual cost from the initial node to the node with the minimum cost; Using a search-based sequential A algorithm, searching from the node with the minimum cost to the neighboring nodes to obtain an estimated cost; A corresponding first price is obtained according to the actual price and the estimated price.

4. The agent path planning method according to claim 2, characterized in that: After selecting the neighbor node corresponding to the minimum total cost as the next path node in the corresponding agent's planned path, it includes: Add the next path node determined by all agents within the current preset time window to the previously created reservation table; Detect whether there are at least two agents occupying the same node at the same time in the current preset time window in the reservation table. If so, combine the agent allocation priority and re-use the starting position, target position and environment map of the agents corresponding to the same node, and use the adaptive window-based hierarchical cooperation A algorithm based on reserved reallocation to perform path search.

5. The agent path planning method according to claim 2, characterized in that: Determining a total cost of a corresponding neighbor node based on the first cost and the second cost includes: Determine a first position cost according to the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node; Determining whether a road segment formed by the previous node of the node with the minimum cost, passing through the node with the minimum cost, and reaching a corresponding adjacent node in combination with the environment map, thereby determining whether the road segment belongs to a different map, and obtaining a corresponding second position cost; wherein the second position cost is previously set based on different types of agents and their corresponding maps; Determining a corresponding third position cost according to the corresponding agent; wherein the third position cost is previously set based on the agent traveling in a straight line within a corresponding preset driving area; A total cost of the corresponding neighbor node is obtained according to the first position cost, the second position cost, the third position cost, the first cost and the second cost.

6. The agent path planning method according to claim 5, characterized in that: Determining a first position cost according to the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node includes: Determine, based on the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node, whether a road section consisting of the previous node of the node with the minimum cost, the node with the minimum cost, and the corresponding adjacent node is a turning section; If it is a turning section, the node with the minimum cost, the previous node of the node with the minimum cost, and the corresponding adjacent node are used to determine the corresponding turning angle. Based on the turning angle, the preset position cost information is searched to determine the corresponding first position cost. The preset position cost information is previously constructed based on different types of intelligent agents and their turning behaviors in the corresponding driving map area. Otherwise, the corresponding adjacent node is determined to be a limit point, and the preset position cost corresponding to the limit point is obtained to obtain the corresponding first position cost; wherein, the preset position cost is set in advance based on different types of intelligent agents and their corresponding driving map types.

7. The agent path planning method according to claim 1, characterized in that: After obtaining the planned path of the agent, the method includes: The planned path of the agent is sent to a preset middleware to convert the format of the planned path of the agent according to the type of the agent to be sent, and the planned path after format conversion is sent to the corresponding agent to be sent.

8. An intelligent agent path planning device, characterized in that: include: Data acquisition module, which obtains the agent's starting position, target position and environment map; The path planning module performs path search based on the starting position, target position and environment map of the intelligent agent and obtains the planned path of the intelligent agent by using the adaptive window-type hierarchical cooperation A algorithm based on reserved redistribution.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the intelligent agent path planning method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent agent path planning method as described in any one of claims 1 to 7 is implemented.

Images