AGV path re-planning method and system based on conflict relation

Abstract

The invention relates to the field of path planning, and particularly provides an AGV path re-planning method and system based on a conflict relation, and the method comprises the steps: 1, generating an initial solution path for each AGV through a rapid MAPF solver; step 2, detecting and storing a conflict relation between any two AGVs according to the starting point position and the ending point position of the AGVs; step 3, constructing a modification set according to the conflict relationship among the AGVs; 4, fixing the paths of all AGVs outside the modification set, regarding the paths as dynamic obstacles, and re-planning the paths of the AGVs in the modification set by using an optimal path planning algorithm; and 5, updating the current path by using the new path obtained in the step 4, and repeatedly executing the steps 2 to 5 until an iteration termination condition is met. According to the method, the modification set is accurately constructed based on the conflict relation and iterative re-planning is carried out, so that the average solution quality is improved while the real-time performance is kept.

Description

Technical Field

[0001] This application relates to the field of path planning, specifically to an AGV path replanning method and system based on conflict relationships. Background Technology

[0002] Automated Guided Vehicles (AGVs) are increasingly used in industrial production and logistics. In a multi-AGV transportation system, providing efficient, safe, and fast travel paths is a fundamental problem that needs to be solved. Specifically, the Multi-Agent Pathfinding (MAPF) problem involves planning travel paths for all AGVs from their respective starting points to their respective destinations, ensuring that no AGVs collide while minimizing their travel time. Currently, the MAPF problem is widely used in automated warehouses, transportation, and parking scenarios. However, with the increase in the number of AGVs and the travel distance, the path space searched by this problem grows exponentially. The MAPF problem has been proven to be NP-hard, even when restricted to a two-dimensional mesh graph.

[0003] To address the Multi-AGV Path Planning (MAPF) problem, related technologies typically begin by rapidly generating feasible initial solutions using heuristic algorithms, followed by iterative improvements using the remaining computation time. Common iterative strategies include global replanning and local replanning: the former recalculates all AGV paths, potentially leading to significant solution quality improvements, but the computational cost increases exponentially with the AGV size, making it difficult to meet real-time requirements; the latter selects only a small number of AGVs for path recalculation each time, offering high computational efficiency, but is limited by random or heuristic selection principles, failing to fully utilize potential conflict information between AGVs, resulting in limited and unstable improvements. Furthermore, existing methods do not systematically consider the inherent conflict relationships between AGVs when constructing the modification set, leading to a lack of specificity in the AGV combinations targeted in each iteration. Path entanglement and interaction conflicts remain unresolved, hindering further improvements in the overall algorithm's convergence speed and solution quality. Summary of the Invention

[0004] To address the aforementioned issues, this invention provides an AGV path replanning method and system based on conflict relationships. By accurately constructing a modification set based on conflict relationships and iteratively replanning, the average solution quality is improved while maintaining real-time performance.

[0005] In a first aspect, the technical solution of the present invention provides an AGV path replanning method based on conflict relationships, comprising the following steps: Step 1: Use the fast MAPF solver to generate initial solution paths for each AGV. ; Step 2: Detect and save the conflict relationship between any two AGVs based on their start and end positions; Step 3: Construct a modification set based on the conflict relationships between each AGV. ; Step 4, Fix the Modification Set The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV in the middle; Step 5: Update the current path using the new path obtained in Step 4. Repeat steps 2 through 5 until the iteration termination condition is met.

[0006] In an optional implementation, step 3 specifically includes: Step 3.1, Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV selected is different; Step 3.2, Traverse the modification set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

[0007] In an optional implementation, the traversal termination condition includes a modification set. The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those specified, if either of these two conditions is met, the traversal will terminate.

[0008] In an optional implementation, step 4 specifically includes: Step 4.1, modify the set The paths of all AGVs except for the one mentioned above are fixed as dynamic obstacles, generating a set of dynamic obstacles. ,in, For AGV At any moment Location, For the set of all AGVs; Step 4.2: Map dynamic obstacles to the spatiotemporal map. In the middle, the constraints include modification sets AGVs in the system cannot interact with dynamic obstacles. The AGVs in the set occupy the same position at the same time, and the set that cannot be modified. The AGV in the process encountered an edge collision with a dynamic obstacle; Step 4.3, based on the spatiotemporal map The constraint is a modification set Each AGV in the process plans a new path.

[0009] In one optional implementation, the optimal path planning algorithm is any one of the LaCAM algorithm, CBS algorithm, A* algorithm, and SIPP algorithm.

[0010] In one alternative implementation, the iteration termination condition is any one of timeout, reaching the maximum number of iterations, or being unable to continue improvement.

[0011] In an optional implementation, step 2 detects and saves the conflict relationship between any two AGVs based on the start and end positions of the AGVs, specifically including: AGV The set of shortest paths ,in For starting point, for The end point; for All shortest paths ,and All shortest paths ,if and There will inevitably be a conflict, then and They are adversaries, if and If none of them conflict, then and The relationship between them is free; otherwise... The two are compatible. Save the conflict relationship between any two AGVs.

[0012] Secondly, the technical solution of the present invention provides an AGV path replanning system based on conflict relationships, comprising: The initial solution path generation module is used to generate initial solution paths for each AGV using the fast MAPF solver. ; The conflict detection module is used to detect and save the conflict relationship between any two AGVs based on the start and end positions of the AGVs. The modification set construction module is used to construct modification sets based on the conflict relationships between various AGVs. ; The path replanning module is used to fix the modification set. The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV in the middle; The path update module is used to update the initial solution path with the new path obtained from the path replanning module. Repeatedly execute the conflict detection module, the modification set construction module, the path replanning module, and the path update module until the iteration termination condition is met.

[0013] In an optional implementation, the modification set construction module constructs a modification set based on the conflict relationships between the various AGVs. Specifically, it includes: Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV selected is different; Traversing the Modification Set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

[0014] In an optional implementation, the traversal termination condition includes a modification set. The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those that meet either of these two conditions, the traversal will terminate. Alternatively, the traversal terminates when the entire modification set has been traversed. All AGVs except those mentioned above; after traversal terminates, check the current modification set. Does the number of AGVs in the current modification set exceed the preset limit? If it does, then start from the current modification set. Remove the corresponding number of AGVs from the modified set. The number of AGVs in the system is a preset upper limit.

[0015] As can be seen from the above technical solutions, this application has the following advantages: Step 2 captures and saves the conflict relationship between any two AGVs in real time, and Step 3 constructs a modification set based on this relationship, thereby ensuring that the AGV path with the most significant conflict and the greatest optimization potential is recalculated first in each iteration; Compared with random or heuristic selection, the construction of the modification set is more targeted, significantly reduces invalid calculations, and improves iteration efficiency; Step 4, under the premise of fixing the paths of the remaining AGVs and treating them as dynamic obstacles, only uses the optimal algorithm to recalculate the paths of the AGVs in the modification set, which can minimize the probability of path entanglement and conflict while ensuring real-time performance; Repeating steps 2-5 can continuously approach the global better solution within a finite time. Experiments show that the average solution quality improvement rate of this method is increased from 6.64% of the existing random strategy to 8.37% under the same number of iterations, and the advantage becomes more obvious with the increase of the number of AGVs. It has both high efficiency and stability and is suitable for large-scale industrial and warehousing logistics scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of an AGV path replanning method based on conflict relationships, provided as an embodiment of the present invention.

[0018] Figure 2 This diagram illustrates the average improvement rate of the solution based on the iterative improvement algorithm for AGV conflict relationships on the map random-32-32-20.

[0019] Figure 3 This is a schematic diagram illustrating the average improvement rate of the solution based on the iterative improvement algorithm for AGV conflict relationships in map room-32-32-4.

[0020] Figure 4 This is a schematic block diagram of an AGV path replanning system based on conflict relationships, provided for an embodiment of the present invention. Detailed Implementation

[0021] To make the purpose, features, and advantages of this application more apparent and understandable, specific embodiments and accompanying drawings will be used to clearly and completely describe the technical solution protected by this application. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] Unless otherwise defined, all technical and scientific terms used in this application have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this application and in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0023] Figure 1 This is a schematic flowchart of an AGV path replanning method based on conflict relationships, provided as an embodiment of the present invention. Figure 1 The executing entity can be an AGV path replanning system based on conflict relationships. The AGV path replanning method based on conflict relationships provided in this embodiment of the invention is executed by a computer device; correspondingly, the AGV path replanning system based on conflict relationships runs within the computer device. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0024] like Figure 1 As shown, the method includes the following steps.

[0025] Step 1: Use the fast MAPF solver to generate initial solution paths for each AGV. ; Step 2: Detect and save the conflict relationship between any two AGVs based on their start and end positions; Step 3: Construct a modification set based on the conflict relationships between each AGV. ; Step 4, Fix the Modification Set The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV in the middle; Step 5: Update the current path using the new path obtained in Step 4. Repeat steps 2 through 5 until the iteration termination condition is met.

[0026] As a refinement and extension of the specific implementation of the above embodiments, in order to fully explain the specific implementation process of this embodiment, the following will provide possible embodiments to describe the specific implementation of the above steps in a non-limiting manner.

[0027] Heuristic algorithms for the MAPF problem have been able to provide feasible solutions relatively efficiently, but the quality of the solutions is often difficult to guarantee. When the solution time is much shorter than the given time limit, to make full use of the remaining time, it can be used to recalculate the (partial / full) path of the AGV to iteratively refine the initial solution. Currently, there are two main iterative refinement strategies: Global replanning: Recalculate the paths of all AGVs; Local replanning: Optimize only the paths of some AGVs, while keeping the paths of others unchanged.

[0028] In theory, global reprogramming can escape local optima and achieve significant improvements, but it is computationally expensive. Local reprogramming, on the other hand, offers relatively limited improvement in solution quality, but is significantly more computationally efficient. Given the real-time requirements in practical applications, local reprogramming is a relatively feasible solution. This application uses a heuristic algorithm, LaCAM, to generate an initial solution and iteratively improves the current solution within time constraints.

[0029] The iterative improvement algorithm iterates through the entire AGV set each time. Select a subset ,gather It is called a modification set, which is fixed. The path of the AGV, and the... The path of the AGV is recalculated, and the new path is merged with the original path to obtain an improved solution. This process of "selecting AGV-recalculating" can be performed iteratively until the iteration termination condition is met, such as exceeding the given time limit or failing to obtain an improvement in the solution.

[0030] In this embodiment, considering the MAPF problem on a two-dimensional mesh graph, the conflict relationships between AGVs are divided into three categories: hostile relationship, free relationship, and compatible relationship.

[0031] AGV The set of shortest paths ,in For starting point, for The endpoint; for All shortest paths ,and All shortest paths ,if and There will inevitably be a conflict, then and They are adversaries, if and If none of them conflict, then and The relationship between them is free; otherwise... They are compatible.

[0032] A hostile relationship means that no matter how two AGVs choose their shortest paths, they will inevitably clash (point clash or edge clash). This relationship usually stems from the highly entangled geometric positions of their start and end points. A free relationship means that the shortest paths of two AGVs will not clash regardless of their combination, usually because their activity areas do not overlap or their movement directions are completely opposite. A compatible relationship means that they are neither hostile nor free; that is, some shortest path combinations will clash, while others will not, and whether a conflict occurs depends on the specific path selection.

[0033] Based on the rules described above, detect any two AGVs for conflict based on their current paths, and save the detection results so that the relationship can be read later to adjust the modification set. For example, it can be stored in the form of a conflict relationship table, which records the conflict relationship between each AGV and any other AGV.

[0034] If two AGVs are in an adversarial relationship, there will be a conflict in any pair of their shortest paths. Therefore, the probability of conflict between them is significantly higher than that between compatible or free-relationship AGV pairs. Fast MAPF solvers, such as the LaCAM algorithm, aim to guide AGVs along the shortest paths as much as possible, which aligns perfectly with the premise of AGV conflict analysis. Of course, other algorithms can also be used as MAPF solvers. Therefore, in the initial solution generated by the LaCAM algorithm, the paths of adversarial AGVs exhibit stronger interactivity and entanglement characteristics, showing greater optimization potential. Therefore, the optimization modification set of adversarial AGVs is chosen. .

[0035] Step S3: Construct a modification set based on the conflict relationships between each AGV. Specifically, it includes the following steps.

[0036] Step 3.1, Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV is randomly selected differently.

[0037] Step 3.2, Traverse the modification set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

[0038] Traversal termination conditions include modification sets The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those specified, if either of these two conditions is met, the traversal will terminate.

[0039] For example, … 10 AGVs, selected in the current iteration Initialize the modification set for the initial AGV. At that time, Add to modification set Then iterate through … ,from Begin by checking the conflict table. and The conflict between the two parties, if they are adversaries, will... Add to modification set Otherwise, continue iterating. Modified Set The maximum number of AGVs in the system is set to 3. If all AGVs are traversed... Time Modification Set It already exists in China , , With three AGVs, the traversal is terminated, and step 4 is executed to update the current path. Then randomly divide Other AGVs besides the one mentioned above are used as the initial AGVs for iterative updates until the iteration termination condition is met.

[0040] The optimal path planning algorithm used in step 4 can be any one of the following: LaCAM algorithm, CBS algorithm, A* and constraint algorithm, or SIPP algorithm.

[0041] LaCAM (Lazy Constraints Addition Search for Multi-agent Path Finding): A suboptimal multi-agent path planning algorithm based on incremental constraint addition.

[0042] CBS (Conflict-Based Search): A hierarchical optimization framework that decomposes problems using a conflict tree.

[0043] A+OD (A with Operator Decomposition): Combining spatiotemporal A* and constraint propagation.

[0044] SIPP (Safe Interval Path Planning): Safe interval planning for handling dynamic obstacles.

[0045] An alternative implementation, considering the high computational cost of globally optimal algorithms (such as CBS), can employ restricted optimal algorithms, such as time / search depth-limited A* variants, to balance real-time performance and solution quality. Alternatively, based on the modified set... The number of AGVs determines the optimality. If the number is small, CBS can be used to ensure optimality. If the number is large or real-time requirements are high, heuristic A* or a variant of LaCAM can be used.

[0046] Step 4: Fix the Modification Set The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV includes the following steps.

[0047] Step 4.1, modify the set The paths of all AGVs except for the one mentioned above are fixed as dynamic obstacles, generating a set of dynamic obstacles. ,in, For AGV At any moment Location, For the set of all AGVs.

[0048] Step 4.2: Map dynamic obstacles to the spatiotemporal map. In the middle, the constraints include modification sets AGVs in the system cannot interact with dynamic obstacles. The AGVs in the set occupy the same position at the same time, and the set that cannot be modified. The AGV in the process encountered a side collision with a dynamic obstacle.

[0049] Step 4.3, based on the spatiotemporal map The constraint is a modification set Each AGV in the process plans a new path.

[0050] It should be noted that in step 4.2, when planning the new path, the new path from the starting point to the destination is the shortest path, and the goal is to minimize the total time. After obtaining the new path in step 4.3, it is possible to check whether there are any unresolved conflicts between the new path and the unmodified path, such as omissions due to limitations of the planning algorithm. If conflicts exist, return to step 4.2 to adjust the planning parameters or expand the modification set. If there are no conflicts, the new path is accepted as the new solution. The above process ensures the efficiency of local replanning and the improvement of solution quality.

[0051] In some alternative implementations, the termination condition for AGV path optimization is any one of timeout, reaching the maximum number of iterations, or being unable to continue improvement (e.g., the total time taken to achieve an unimproved solution after N consecutive iterations).

[0052] The experimental results of the iterative improvement algorithm based on AGV conflict relationships are presented in Table 1.

[0053] The experiment used SOC (Sum of Cost, total time) as the objective function and obtained an initial solution using the LaCAM algorithm. An iterative improvement algorithm based on randomly selected AGVs was used as a control. The experiment tested the iterative improvement algorithm based on AGV conflict relationships on map random-32-32-20. Figure 2 ) and room-32-32-4 ( Figure 3 The algorithm aims to improve the average solution by performing one iteration. Experiments show that the algorithm based on AGV conflict relationships achieves a greater improvement rate than the algorithm that randomly selects AGVs. The algorithm that randomly selects AGVs has an average improvement rate of 6.64% across all MAPF test instances, while the algorithm based on AGV conflict relationships further utilizes the start and end point information of the AGVs, increasing the improvement rate to an average of 8.37%.

[0054] Table 1: Experimental Results of Iterative Improvement Algorithm (Improvement Rate)

[0055] The foregoing has described in detail an embodiment of an AGV path replanning method based on conflict relationships. Based on the AGV path replanning method based on conflict relationships described in the above embodiment, this invention also provides an AGV path replanning system based on conflict relationships corresponding to the method.

[0056] Figure 4 This is a schematic block diagram of an AGV path replanning system based on conflict relationships, provided as an embodiment of the present invention. In this embodiment, the AGV path replanning system 400 based on conflict relationships can be divided into multiple functional modules according to the functions it performs. A module, as referred to in this invention, is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and is stored in memory.

[0057] Initial solution path generation module 410 is used to generate initial solution paths for each AGV using the fast MAPF solver. .

[0058] The conflict detection module 420 is used to detect and save the conflict relationship between any two AGVs based on the start and end positions of the AGVs.

[0059] Modification set construction module 430 is used to construct modification sets based on the conflict relationships between various AGVs. .

[0060] Path replanning module 440, used for fixing modification sets. The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV.

[0061] Path update module 450 is used to update the initial solution path with the new path obtained from the path replanning module. Repeatedly execute the conflict detection module, the modification set construction module, the path replanning module, and the path update module until the iteration termination condition is met.

[0062] In some alternative implementations, the modification set construction module 430 constructs a modification set based on the conflict relationships between the various AGVs. Specifically, it includes: Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV selected is different; Traversing the Modification Set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

[0063] The traversal termination condition includes the modification set. The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those specified, if either of these two conditions is met, the traversal will terminate.

[0064] The conflict-based AGV path replanning system of this embodiment is used to implement the aforementioned conflict-based AGV path replanning method. Therefore, the specific implementation of this system can be found in the embodiment section of the conflict-based AGV path replanning method above. Thus, the specific implementation can be referred to the description of the corresponding embodiments, and will not be elaborated here.

[0065] Furthermore, since the AGV path replanning system based on conflict relationship in this embodiment is used to implement the aforementioned AGV path replanning method based on conflict relationship, its function corresponds to the function of the above method, and will not be repeated here.

[0066] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An AGV path replanning method based on conflict relationships, characterized in that, Includes the following steps: Step 1: Use the fast MAPF solver to generate initial solution paths for each AGV. ; Step 2: Based on the starting and ending positions of the AGVs, detect and save the conflict relationship between any two AGVs; Step 3: Construct a modification set based on the conflict relationships between each AGV. ; Step 4, Fix the Modification Set The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV in the middle; Step 5: Update the current path using the new path obtained in Step 4. Repeat steps 2 through 5 until the iteration termination condition is met.

2. The AGV path replanning method based on conflict relationships according to claim 1, characterized in that, Step 3 specifically includes: Step 3.1, Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV selected is different; Step 3.2, Traverse the modification set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

3. The AGV path replanning method based on conflict relationships according to claim 2, characterized in that, Traversal termination conditions include modification sets The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those specified, if either of these two conditions is met, the traversal will terminate.

4. The AGV path replanning method based on conflict relationships according to claim 1, characterized in that, Step 4 specifically includes: Step 4.1, modify the set The paths of all AGVs except for the one mentioned above are fixed as dynamic obstacles, generating a set of dynamic obstacles. ,in, For AGV At any moment Location, For the set of all AGVs; Step 4.2: Map dynamic obstacles to the spatiotemporal map. In the middle, the constraints include modification sets AGVs in the system cannot interact with dynamic obstacles. The AGVs in the set occupy the same position at the same time, and the set that cannot be modified. The AGV in the process encountered an edge collision with a dynamic obstacle; Step 4.3, based on the spatiotemporal map The constraint is a modification set Each AGV in the process plans a new path.

5. The AGV path replanning method based on conflict relationships according to claim 1, characterized in that, The optimal path planning algorithm can be any one of the following: LaCAM algorithm, CBS algorithm, A* algorithm, or SIPP algorithm.

6. The AGV path replanning method based on conflict relationships according to claim 1, characterized in that, The iteration termination condition is any one of the following: timeout, reaching the maximum number of iterations, or inability to continue improvement.

7. The AGV path replanning method based on conflict relationships according to claim 1, characterized in that, Step 2 involves detecting and saving the conflict relationships between any two AGVs based on their start and end positions. Specifically, this includes: AGV The set of shortest paths ,in For starting point, for The end point; for All shortest paths ,and All shortest paths ,if and There will inevitably be a conflict, then and They are adversaries, if and If there is no conflict, then and The relationship between them is free; otherwise... The two are compatible. Save the conflict relationship between any two AGVs.

8. An AGV path replanning system based on conflict relationships, characterized in that, include: The initial solution path generation module is used to generate initial solution paths for each AGV using the fast MAPF solver. ; The conflict detection module is used to detect and save the conflict relationship between any two AGVs based on the start and end positions of the AGVs. The modification set construction module is used to construct modification sets based on the conflict relationships between various AGVs. ; The path replanning module is used to fix the modification set. The paths of all AGVs other than those mentioned above are treated as dynamic obstacles, and the modified path is replanned using an optimal path planning algorithm. The path of the AGV in the middle; The path update module is used to update the initial solution path with the new path obtained from the path replanning module. Repeatedly execute the conflict detection module, the modification set construction module, the path replanning module, and the path update module until the iteration termination condition is met.

9. The AGV path replanning system based on conflict relationships according to claim 8, characterized in that, The modification set construction module constructs modification sets based on the conflict relationships between the various AGVs. Specifically, it includes: Initialize the modification set That is, randomly select one AGV from all AGVs as the initial AGV and add it to the modification set. In each iteration, the initial AGV selected is different; Traversing the Modification Set For all AGVs other than the initial AGV, check the conflict relationship between the initial AGV and the current AGV. If the conflict relationship between the two AGVs is hostile, then add the current AGV to the modification set. Continue until the traversal termination condition is met.

10. The AGV path replanning system based on conflict relationships according to claim 9, characterized in that, Traversal termination conditions include modification sets The number of AGVs in the set reaches the preset limit, and the modification set is traversed. For all AGVs other than those specified, if either of these two conditions is met, the traversal will terminate.

Images