AGV robot path planning method and system

Abstract

The invention provides an AGV robot path planning method and system. The method comprises the steps that a map node graph, robot parameters, a starting node and a target node are acquired; introducing a robot constraint condition, and calculating an evaluation cost value of the robot from a current node to a target node based on a heuristic function; according to the evaluation cost value of the robot from the current node to the target node, based on an A * search algorithm, searching an optimal path of the robot from the starting node to the target node in map nodes; and generating a path instruction from the optimal path, and sending the path instruction to the robot for execution. Based on an advanced path planning algorithm, the path of the AGV robot is automatically planned, the optimal planning path is searched, and high efficiency of task execution of the AGV robot is achieved.

Description

Technical Field

[0001] The present invention relates to the field of path planning and coordination, and more specifically, to a AGV robot path planning method and system. Background Art

[0002] AGV robots are used in many application scenarios. For example, express delivery, takeout delivery and some other tasks can all be performed by AGV robots, which frees up manpower and saves manpower.

[0003] When the AGV robot is performing a task, the path of the AGV robot will affect the efficiency of task execution. Therefore, it is very important to plan the path of the AGV robot to perform the task. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides an AGV robot path planning method and system, which solves the problems that the existing path planning methods mostly rely on fixed paths, cannot be dynamically adjusted, and are difficult to adapt to changing environments and needs.

[0005] According to a first aspect of the present invention, a method for AGV robot path planning is provided, comprising:

[0006] Get the map node graph, robot parameters, start node and target node;

[0007] Introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function;

[0008] According to the evaluation cost of the robot from the current node to the target node, based on the A* search algorithm, search the map nodes for the optimal path from the start node to the target node;

[0009] The optimal path generates a path instruction and sends it to the robot for execution.

[0010] Based on the above technical solution, the present invention can also make the following improvements.

[0011] Optionally, the robot parameters include robot size, and the robot constraints include robot size constraints and node path width constraints; the introducing robot constraints and calculating the evaluation cost value of the robot from the current node to the target node based on the heuristic function includes:

[0012] f(n)=g(n)+h(n)+λ size ×C size +λ path ×C path ;

[0013] Among them, f(n) is the evaluation cost of the robot from the current node n to the target node, g(n) is the path cost from the current node n to the starting node, h(n) is the estimated cost from the current node n to the target node, and λ size and λ path are the weight factors of the robot size constraint and the node path width constraint, C size and C path are the robot size constraint cost and the node path width constraint cost.

[0014] Optionally, according to the evaluation cost value of the robot from the current node to the target node, based on the A* search algorithm, the optimal path of the robot from the start node to the target node is searched in the map nodes:

[0015] Starting from the start node of the robot, searching for at least one neighbor node that satisfies the first constraint and the second constraint;

[0016] The neighbor node with the smallest evaluation cost value among multiple neighbor nodes is taken as the current node, and the neighbor node with the smallest evaluation cost value is continued to be searched based on the current node until the target node is searched, and the optimal path of the robot from the starting node to the target node is obtained. The first restriction condition is that the robot type is the type allowed by the node to pass, and the second restriction condition is that the robot can pass through the node.

[0017] Optionally, the method further includes:

[0018] Classifying the types of AGV robots and setting the types of AGV robots that are allowed to pass through each node as the first restriction condition of the AGV robots; and,

[0019] According to the size of the AGV robot, the width of the road section where the node is located, and the driving mode of the AGV robot, it is judged whether the AGV robot can pass through the node, which serves as the second restriction condition of the AGV robot.

[0020] Optionally, judging whether the AGV robot can pass through the node according to the size of the AGV robot, the width of the road section where the node is located, and the driving mode of the AGV robot includes:

[0021] Calculate the angle difference β based on the angle between the front angle of the section where the AGV robot is traveling and the positive direction of the X-axis, and the angle between the section where the node is located and the positive direction of the X-axis;

[0022] According to trigonometric functions, calculate the minimum width of the section where the AGV robot passes through the node:

[0023] Minimum width W' = trolley length L*sinβ + trolley width W*cosβ;

[0024] If the minimum width of the section where the AGV robot passes through the node is smaller than the actual width of the section where the node is located, the AGV robot can pass through the node; otherwise, the AGV robot cannot pass through the node.

[0025] According to a second aspect of the present invention, a path planning and coordination method for multiple AGV robots is provided, comprising:

[0026] The path of each AGV robot is planned based on the AGV robot path planning method to obtain the planned path of each AGV robot;

[0027] According to the parameter information, path information of each AGV robot and the road section information of each node, the conflict detection of multiple AGV robots is performed;

[0028] If the driving of multiple AGV robots conflicts, the planned path of the AGV robot with a lower task priority is adjusted according to the task priority of each AGV robot to obtain a backup path for the AGV robot with a lower task priority.

[0029] Optionally, the backup path of the AGV robot with a low task priority is:

[0030]

[0031] Among them, α is the path adjustment coefficient, Task priority is the task priority, Path cost is the original path cost.

[0032] Optionally, the method further includes:

[0033] Get the original planning paths of all AGV robots;

[0034] According to the planned paths of all AGV robots, based on the task priority and path cost of each AGV robot, by adjusting the driving speed and original planned path of each AGV robot, the global planned path of all AGV robots is obtained, so that all AGV robots can operate in a coordinated manner without conflict during driving.

[0035] According to a third aspect of the present invention, there is provided an AGV robot path planning system, comprising:

[0036] The acquisition module is used to obtain the map node graph, robot parameters, starting node and target node;

[0037] The calculation module is used to introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function;

[0038] A search module is used to search for the optimal path from the start node to the target node in the map nodes based on the evaluation cost value of the robot from the current node to the target node and the A* search algorithm;

[0039] The execution module is used to generate a path instruction from the optimal path and send it to the robot for execution.

[0040] According to a fourth aspect of the present invention, a path planning and coordination system for multiple AGV robots is provided, comprising:

[0041] The planning module is used to call the AGV robot path planning system to plan the path of each AGV robot and obtain the planned path of each AGV robot;

[0042] The conflict detection module is used to perform conflict detection on the driving of multiple AGV robots based on the parameter information, path information of each AGV robot and the road section information of each node;

[0043] The path adjustment module is used to adjust the planned path of the AGV robot with a low task priority according to the task priority of each AGV robot if a conflict occurs in the driving of multiple AGV robots, so as to obtain a backup path for the AGV robot with a low task priority.

[0044] The present invention provides an AGV robot path planning method and system, which automatically plans the path of the AGV robot based on an advanced path planning algorithm and a heuristic function, searches for the optimal planned path, and realizes high efficiency of the AGV robot in executing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of an AGV robot path planning method provided by the present invention;

[0046] Figure 2 A flow chart of a path planning and coordination method for multiple AGV robots provided by the present invention;

[0047] Figure 3 A schematic diagram of the structure of an AGV robot path planning system provided by the present invention;

[0048] Figure 4 A schematic diagram of the structure of a path planning coordination system for multiple AGV robots provided by the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In addition, the technical features in the various embodiments or single embodiments provided by the present invention can be arbitrarily combined with each other to form a feasible technical solution. This combination is not subject to the constraints of the sequence of steps and / or the structural composition mode, but must be based on the ability of ordinary technicians in this field to achieve. When the combination of technical solutions is contradictory or cannot be achieved, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0050] Figure 1 A flow chart of a path planning method for an AGV robot provided by the present invention is as follows: Figure 1 As shown, the method includes:

[0051] Step 1: Get the map node graph, robot parameters, start node and target node.

[0052] It is understandable that when the AGV robot is performing a task, the path taken from the location of the AGV robot to the task point (target node) is very critical and will affect the efficiency of performing the task. Therefore, the present invention provides a method for planning the path of the AGV robot to ensure efficient and safe movement in a complex environment.

[0053] Initialize the map and obtain the map node information diagram, including the location of each node, the actual width of the node, the parameter information of the AGV robot, including the size of the AGV robot, the turning radius during driving, etc., the starting node and target node of the AGV robot path planning.

[0054] Step 2: Introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function.

[0055] It is understandable that the path of the AGV robot is planned using classic algorithms such as A*, Dijkstra, and improved path optimization algorithms.

[0056] In the process of path planning for an AGV robot, the present invention introduces the constraints of the robot and calculates the evaluation cost value of the robot from the current node to the target node based on a heuristic function. The robot constraints include robot size constraints and node path width constraints; the introduction of the robot constraints and the calculation of the evaluation cost value of the robot from the current node to the target node based on a heuristic function include:

[0057] f(n)=g(n)+h(n)+λ size ×C size +λ path ×C path ;

[0058] Among them, f(n) is the evaluation cost of the robot from the current node n to the target node, g(n) is the path cost from the current node n to the starting node, h(n) is the estimated cost from the current node n to the target node, and λ size and λ path are the weight factors of the robot size constraint and the node path width constraint, C size and C path are the robot size constraint cost and the node path width constraint cost.

[0059] Step 3: According to the evaluation cost of the robot from the current node to the target node, based on the A* search algorithm, search for the optimal path of the robot from the start node to the target node in the map nodes.

[0060] Among them, according to the evaluation cost value of the robot from the current node to the target node, based on the A* search algorithm, the optimal path of the robot from the start node to the target node is searched in the map node:

[0061] Starting from the start node of the robot, searching for at least one neighbor node that satisfies the first constraint and the second constraint;

[0062] The neighbor node with the smallest evaluation cost value among multiple neighbor nodes is taken as the current node, and the neighbor node with the smallest evaluation cost value is continued to be searched based on the current node until the target node is searched, and the optimal path of the robot from the starting node to the target node is obtained. The first restriction condition is that the robot type is the type allowed by the node to pass, and the second restriction condition is that the robot can pass through the node.

[0063] Specifically, the implementation process of the A* algorithm: use two evaluation functions: g(n) represents the actual cost from the starting node to the current node n, h(n) represents the estimated cost from the current node n to the target node, and the heuristic function f(n)=g(n)+h(n) is used to evaluate the evaluation cost value of the current node n.

[0064] The algorithm starts with the start node, adds it to the open list, and then repeats the following steps:

[0065] (1): Select the node n with the smallest f(n) from the open list for expansion, remove it from the open list and add it to the closed list;

[0066] (2): For each neighbor node m of node n, if m is not in the closed list, calculate the values ​​of g(m) and h(m), and add m to the open list;

[0067] (3): If the target node is in the open list, the search is complete and the optimal path is returned; otherwise, repeat (1).

[0068] Among them, the types of AGV robots are classified, and the types of AGV robots allowed to pass through each node are set as the first restriction condition of the AGV robot; and,

[0069] According to the size of the AGV robot, the width of the road section where the node is located, and the driving mode of the AGV robot, it is judged whether the AGV robot can pass through the node, which serves as the second restriction condition of the AGV robot.

[0070] It is understandable that some restrictions are added when searching for each adjacent node m for node n:

[0071] Restriction 1: There will be a preliminary restriction on the types of AGV robots. According to the actual needs of the project, all AGV robots will be classified. Then, only certain types of vehicles can pass through certain sections of the road, and AGV robots that do not meet this type will not be allowed to pass;

[0072] Restriction 2: The space will be restricted again, and a comprehensive judgment will be made based on factors such as the size of the AGV robot (length and width), the width of the road section, and the driving mode of the car to determine whether the car can pass through this road section.

[0073] Specifically, it is determined whether the car type of the current AGV robot is a subset of the AGV robot types that can pass through this section. If not, the end point of this section is not considered;

[0074] Combined with the front angle of the AGV robot driving on this node section and the angle between the section and the positive direction of the X-axis, the angle difference β is calculated;

[0075] According to the trigonometric function, the minimum width of the AGV robot passing through this node section is obtained, W' (minimum width) = L (car length) * sin (β) + W (car width) * cos (β);

[0076] Determine whether the minimum width required for the AGV robot to pass through this node section is less than the width of the actual section of the node section. If not, the end point of this node section will not be considered.

[0077] Based on the A* heuristic search algorithm, the optimal path of the AGV robot is searched.

[0078] Step 4: Generate a path instruction based on the optimal path and send it to the AGV robot for execution.

[0079] It is understandable that the searched optimal path of the AGV robot generates a path instruction and sends it to the AGV robot for execution.

[0080] Among them, in the mixed scheduling scenario of multiple AGV robots, path coordination is crucial to ensure that there is no conflict between multiple AGV robots.

[0081] See also Figure 2 , provides a path planning coordination method for multiple AGV robots, the method comprising:

[0082] Step 1', planning the path of each AGV robot based on the AGV robot path planning method to obtain the planned path of each AGV robot.

[0083] It is understandable that in a mixed scheduling scenario of multiple AGV robots, first, the path of each AGV robot is planned based on the above-mentioned heuristic A* search algorithm to obtain the optimal planned path for each AGV robot.

[0084] Step 2': Detect conflicts between the driving of multiple AGV robots according to the parameter information, path information of each AGV robot and the road section information where each node is located.

[0085] It is understandable that conflicts may occur when each AGV robot is driving along the optimal planned path. For example, if multiple AGV robots need to pass through the same node section at the same time, then a conflict will occur if the node section cannot accommodate two or more AGV robots passing through at the same time. In order to resolve this conflict, the paths of some AGV robots need to be replanned, or the originally planned paths need to be adjusted.

[0086] Among them, according to the parameter information of each AGV robot (including size information, turning radius, etc.), path information and the road section information where each node is located, the driving of multiple AGV robots is detected.

[0087] According to the planned path of each AGV robot, certain key nodes or path segments are scheduled in advance to avoid conflicts, so as to avoid multiple robots using the same section at the same time. This reservation mechanism can effectively reduce conflicts between robots, especially in narrow areas or intersections.

[0088] Step 3': if the driving of multiple AGV robots conflicts, the planned path of the AGV robot with a lower task priority is adjusted according to the task priority of each AGV robot to obtain a backup path for the AGV robot with a lower task priority.

[0089] It is understandable that through the conflict detection in step 2', it is possible to pre-determine the path segments where conflicts will occur, obtain the original path information of multiple AGV robots that will conflict, and perform the task priority. If a path conflict is detected, the path of the AGV robot with a low priority task is replanned, or it is arranged to wait until the AGV robot with a high priority task passes through the section before the AGV robot with a low task priority passes through the section. The path replanning formula for the AGV robot with a low task priority is:

[0090]

[0091] Among them, α is the path adjustment coefficient, Task priority is the task priority, Path cost is the original path cost.

[0092] The replanned path of the AGV robot with low task priority is obtained as a backup path to avoid conflict with the path of the AGV robot with high task priority.

[0093] During the mixed scheduling of all AGV robots, global path collaborative optimization of all AGV robots can be performed.

[0094] Among them, the original planning paths of all AGV robots are obtained;

[0095] According to the planned paths of all AGV robots, based on the task priority and path cost of each AGV robot, by adjusting the driving speed and original planned path of each AGV robot, the global planned path of all AGV robots is obtained, so that all AGV robots can operate in a coordinated manner without conflict during driving.

[0096] The global path of all AGV robots is optimized, and the speed and driving path of each AGV robot are adjusted to ensure the coordinated operation of multiple robots. The global path optimization takes into account the priority and path cost of each robot task, and achieves the overall optimality through coordinated adjustment.

[0097] See also Figure 3 , provides an AGV robot path planning system of the present invention, comprising:

[0098] The acquisition module 301 is used to obtain the map node diagram, robot parameters, starting node and target node;

[0099] A calculation module 302 is used to introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function;

[0100] A search module 303 is used to search for an optimal path from a start node to a target node in a map node based on an A* search algorithm according to an evaluation cost value of the robot from a current node to a target node;

[0101] The execution module 304 is used to generate a path instruction from the optimal path and send it to the robot for execution.

[0102] It can be understood that the AGV robot path planning system provided by the present invention corresponds to the AGV robot path planning method provided by the aforementioned embodiments. The relevant technical features of the AGV robot path planning system can refer to the relevant technical features of the AGV robot path planning method, which will not be repeated here.

[0103] See also Figure 4 , provides a path planning coordination system for multiple AGV robots of the present invention, the system comprising:

[0104] The planning module 401 is used to call the AGV robot path planning system to plan the path of each AGV robot to obtain the planned path of each AGV robot;

[0105] The conflict detection module 402 is used to perform conflict detection on the driving of multiple AGV robots according to the parameter information, path information of each AGV robot and the road section information where each node is located;

[0106] The path adjustment module 403 is used to adjust the planned path of the AGV robot with a low task priority according to the task priority of each AGV robot if a conflict occurs in the driving of multiple AGV robots, so as to obtain a backup path for the AGV robot with a low task priority.

[0107] It can be understood that the path planning and coordination system for multiple AGV robots provided by the present invention corresponds to the path planning and coordination method for multiple AGV robots provided in the aforementioned embodiments. The relevant technical features of the path planning and coordination system for multiple AGV robots can refer to the relevant technical features of the path planning and coordination method for multiple AGV robots, which will not be repeated here.

[0108] An AGV robot path planning method and system provided by an embodiment of the present invention has the following beneficial effects:

[0109] (1) Based on advanced path planning algorithms, the path of the AGV robot is automatically planned, and the optimal planning path is searched to achieve efficient task execution by the AGV robot;

[0110] (2) In the mixed scheduling scenario of multiple AGV robots, the global path of all AGV robots is optimized. By adjusting the robot speed and path, the coordinated operation of multiple robots is ensured. The global path optimization takes into account the priority and path cost of each robot task, and achieves the overall optimality through collaborative adjustment.

[0111] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0116] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0117] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A path planning method for an AGV robot, characterized in that: include: Get the map node graph, robot parameters, start node and target node; Introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function; According to the evaluation cost of the robot from the current node to the target node, based on the A* search algorithm, search the map nodes for the optimal path from the start node to the target node; The optimal path generates a path instruction and sends it to the robot for execution.

2. The AGV robot path planning method according to claim 1, characterized in that: The robot parameters include robot size, and the robot constraints include robot size constraints and node path width constraints; the introduction of robot constraints and calculation of the evaluation cost value of the robot from the current node to the target node based on the heuristic function include: f(n)=g(n)+h(n)+λ size ×C size +λ path ×C path ; Among them, f(n) is the evaluation cost of the robot from the current node n to the target node, g(n) is the path cost from the current node n to the starting node, h(n) is the estimated cost from the current node n to the target node, and λ size and λ path are the weight factors of the robot size constraint and the node path width constraint, C size and C path are the robot size constraint cost and the node path width constraint cost.

3. The AGV robot path planning method according to claim 1 or 2, characterized in that: According to the evaluation cost value of the robot from the current node to the target node, based on the A* search algorithm, the optimal path from the start node to the target node of the robot is searched in the map node: Starting from the start node of the robot, searching for at least one neighbor node that satisfies the first constraint and the second constraint; The neighbor node with the smallest evaluation cost value among multiple neighbor nodes is taken as the current node, and the neighbor node with the smallest evaluation cost value is continued to be searched based on the current node until the target node is searched, and the optimal path of the robot from the starting node to the target node is obtained. The first restriction condition is that the robot type is the type allowed by the node to pass, and the second restriction condition is that the robot can pass through the node.

4. The AGV robot path planning method according to claim 3, characterized in that: The method further comprises: Classifying the types of AGV robots and setting the types of AGV robots that are allowed to pass through each node as the first restriction condition of the AGV robots; and, According to the size of the AGV robot, the width of the road section where the node is located, and the driving mode of the AGV robot, it is judged whether the AGV robot can pass through the node, which serves as the second restriction condition of the AGV robot.

5. The AGV robot path planning method according to claim 4, characterized in that: The determining whether the AGV robot can pass through the node according to the size of the AGV robot, the width of the road section where the node is located, and the driving mode of the AGV robot includes: Calculate the angle difference β based on the angle between the front angle of the section where the AGV robot is traveling and the positive direction of the X-axis, and the angle between the section where the node is located and the positive direction of the X-axis; According to trigonometric functions, calculate the minimum width of the section where the AGV robot passes through the node: Minimum width W' = trolley length L*sinβ + trolley width W*cosβ; If the minimum width of the section where the AGV robot passes through the node is smaller than the actual width of the section where the node is located, the AGV robot can pass through the node; otherwise, the AGV robot cannot pass through the node.

6. A path planning and coordination method for multiple AGV robots, characterized in that: include: Planning the path of each AGV robot based on the AGV robot path planning method of claim 1 to obtain a planned path for each AGV robot; According to the parameter information, path information of each AGV robot and the road section information of each node, the conflict detection of multiple AGV robots is performed; If the driving of multiple AGV robots conflicts, the planned path of the AGV robot with a lower task priority is adjusted according to the task priority of each AGV robot to obtain a backup path for the AGV robot with a lower task priority.

7. The path planning and coordination method for multiple AGV robots according to claim 6, characterized in that: The backup path of the AGV robot with low task priority is: Among them, α is the path adjustment coefficient, Task priority is the task priority, Path cost is the original path cost.

8. The path planning and coordination method for multiple AGV robots according to claim 6, characterized in that: The method further comprises: Get the original planned paths of all AGV robots; According to the planned paths of all AGV robots, based on the task priority and path cost of each AGV robot, by adjusting the driving speed and original planned path of each AGV robot, the global planned path of all AGV robots is obtained, so that all AGV robots can operate in a coordinated manner without conflict during driving.

9. An AGV robot path planning system, characterized in that: include: The acquisition module is used to obtain the map node graph, robot parameters, starting node and target node; The calculation module is used to introduce robot constraints and calculate the evaluation cost of the robot from the current node to the target node based on the heuristic function; A search module is used to search for the optimal path from the start node to the target node in the map nodes based on the evaluation cost value of the robot from the current node to the target node and the A* search algorithm; The execution module is used to generate a path instruction from the optimal path and send it to the robot for execution.

10. A path planning and coordination system for multiple AGV robots, characterized in that: include: A planning module, used to call the AGV robot path planning system described in claim 9 to plan the path of each AGV robot to obtain a planned path for each AGV robot; The conflict detection module is used to perform conflict detection on the driving of multiple AGV robots based on the parameter information, path information of each AGV robot and the road section information of each node; The path adjustment module is used to adjust the planned path of the AGV robot with a low task priority according to the task priority of each AGV robot if a conflict occurs in the driving of multiple AGV robots, so as to obtain a backup path for the AGV robot with a low task priority.

Images