A method, system, and equipment for multi-AGV path planning in unmanned warehouses.

Abstract

This invention discloses a multi-AGV path planning method, system, and equipment medium for unmanned warehouses. The method includes: S1, establishing a grid map model; S2, assigning tasks to designated AGVs according to their priority; and S3, applying the PCBS algorithm to the AGVs and performing global path planning based on the grid map model to find a static, conflict-free path. This significantly reduces the possibility of traffic congestion and improves the efficiency of goods transportation.

Description

Technical Field

[0001] This invention belongs to the field of autonomous driving and relates to a multi-AGV path planning method, system and equipment medium for unmanned warehouses. Background Technology

[0002] With the rapid development of the e-commerce industry, the demand for e-commerce logistics has increased dramatically. E-commerce logistics differs significantly from traditional logistics, characterized by large order volumes and numerous tasks. If traditional logistics methods rely on manual sorting and transportation, warehousing and logistics will suffer from significantly increased labor costs and low delivery efficiency, hindering economic development and service efficiency for businesses. Therefore, intelligent AGVs (Automated Guided Vehicles) have become a key solution for improving warehouse transportation efficiency and reducing warehouse operating costs.

[0003] Automated Guided Vehicle (AGVS) systems are an important branch of unmanned warehousing systems, and their design and development meet the requirements of intelligent logistics system development. Through reasonable planning and scheduling, they can improve the turnover rate and sorting accuracy of warehousing systems, and reduce logistics costs.

[0004] With the advancement of science and technology, path planning technology faces increasingly complex and variable environments, placing higher demands on the rapid response of path planning algorithms. The performance of path planning algorithms has a significant impact on AGV scheduling systems, especially when environmental complexity increases and the number of AGVs grows, leading to traffic congestion and a substantial reduction in AGV efficiency. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a multi-AGV path planning method, system and equipment medium for unmanned warehouses, which can greatly reduce the possibility of traffic congestion and improve the efficiency of goods transportation.

[0006] To achieve the above objectives, the present invention employs the following technical solution:

[0007] A multi-AGV path planning method for unmanned warehouses includes the following process:

[0008] S1, Establish a raster map model;

[0009] S2, assigns tasks to designated AGV vehicles according to their priority order;

[0010] S3. The PCBS algorithm is applied to the above AGV vehicles, and a static, conflict-free path is found by performing global path planning based on the grid map model.

[0011] Preferably, in S2, the priority order of tasks is: order tasks with larger cargo volume > order tasks with smaller cargo volume > AGV vehicle docking tasks, and the priority is set according to the importance of the actual order.

[0012] Preferably, in S2, the task allocation principle is as follows: the task is calculated by weighting the straight-line length from the AGV vehicle to the target node by 70% and the time by 30%, with the smaller the value, the higher the priority for allocation; for idle AGV vehicles and AGV vehicles that have completed their tasks and started returning, the time is 0; for AGV vehicles that are currently executing tasks, the waiting time for the current task to end is added.

[0013] Preferably, in S3, the PCBS algorithm includes a lower-level vehicle path planning system and an upper-level conflict search system; the upper-level vehicle path planning uses the DA* algorithm to calculate the shortest path.

[0014] Furthermore, after the lower-level single-vehicle path planning system calculates the shortest path, it is input into the upper-level conflict search system's EPIT. The upper-level conflict search system searches for nodes with path conflicts. If a conflict is found at a node Q, and one of the AGVs related to the conflict is currently moving, new constraints are added only to the AGVs that have not yet started moving, and these constraints are inherited from the parent node. This node is then defined as Q1, and the DA* algorithm re-plans the path for the AGVs that have not yet started moving. Afterward, the search for conflict at node Q1 continues. If all the AGVs related to the conflict are currently moving, new constraints are added to the AGVs with lower priority, and these constraints are inherited from the parent node. This node is then defined as Q1, and the DA* algorithm plans the path for these AGVs. Afterward, the search for conflict at node Q1 continues. If none of the AGVs related to the conflict are currently moving, node Q is split into the same number of child nodes as the AGVs related to the conflict. These child nodes inherit the parent node's constraints and new constraints are added. The DA* algorithm re-plans the path, and the search for conflict continues.

[0015] Preferably, in the process of calculating the shortest path using the DA* algorithm, during the search phase, the algorithm searches for two adjacent nodes of the AGV vehicle's current node in the direction of the target node, and adds a turning cost to the evaluation function, converting the turning cost into a distance cost.

[0016] Preferably, during the AGV's operation, it emits a laser beam with a distance equal to the length of one grid in the direction of travel. When the AGV receives a single laser beam in the next grid ahead, it indicates that no other AGV will pass through that grid in the next moment, and the AGV continues to travel normally. When the next grid receives multiple laser beams, there is a conflict between multiple AGVs, and the paths of the multiple AGVs are re-divided according to their priority.

[0017] A multi-AGV path planning system for unmanned warehouses includes:

[0018] The raster map model creation module is used to create raster map models.

[0019] The task allocation module is used to assign tasks to designated AGV vehicles according to their priority order.

[0020] The path planning module is used to apply the PCBS algorithm to the AGV vehicles and perform global path planning based on the grid map model to find a static, conflict-free path.

[0021] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the multi-AGV path planning method for an unmanned warehouse as described in any of the preceding claims.

[0022] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the multi-AGV path planning method for an unmanned warehouse as described in any of the preceding claims.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] This invention employs the aforementioned PCBS algorithm for static global path planning of multiple AGVs. The DA* algorithm used in the lower layer effectively improves the algorithm's speed and efficiency by searching only towards the target node. Meanwhile, the priority-based conflict search system algorithm used in the upper layer effectively reduces path conflicts between vehicles in the environment by promptly identifying potential vehicle path conflicts and resolving them based on priority. The aforementioned conflict judgment system performs dynamic conflict prediction and resolution for vehicles, making the prediction of dynamic path conflicts more accurate and rapid. Compared to the traditional method of predicting conflicts by monitoring real-time information of AGV vehicles through the central control system, this significantly reduces the burden on the central control system.

[0025] Furthermore, adopting the principles of task priority and allocation can more rationally allocate tasks and improve logistics and transportation efficiency. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the multi-AGV path planning method for unmanned warehouses according to the present invention;

[0027] Figure 2 This is a schematic diagram of the conflict determination system of the present invention.

[0028] Figure 3This is a schematic diagram of the unmanned warehouse communication system of the present invention. Detailed Implementation

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0030] It should be noted that the terms “front,” “back,” “left,” “right,” “up,” and “down” used in the following description refer to the directions shown in the attached diagram, while the terms “inside” and “outside” refer to the directions toward or away from the geometric center of a specific component, respectively.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein 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. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0032] like Figure 1 The diagram illustrates the multi-AGV path planning method for unmanned warehouses according to the present invention, comprising the following steps:

[0033] Step 1: Based on the actual situation of the unmanned warehouse, a map is created using the grid modeling method, including path grids, obstacle grids, and shelf grids.

[0034] Step 2: The unmanned warehouse scheduling system receives task information from the command center.

[0035] Step 3: The unmanned warehouse scheduling system sorts the received task information according to priority and allocates it to appropriate AGV vehicles according to allocation principles.

[0036] The priority principles include:

[0037] (1) Order tasks with larger order volume > Order tasks with smaller order volume > AGV vehicle parking tasks;

[0038] (2) Prioritize orders manually based on their actual importance.

[0039] The allocation principles include:

[0040] (1) The weight of the straight-line length from the AGV vehicle to the target node is 70% + the weight of the time is 30%. The smaller the value, the higher the priority of allocation.

[0041] (2) For idle AGV vehicles and AGV vehicles that have completed their tasks and started returning, the time is 0; for AGV vehicles that are currently performing tasks, the time to wait for the current task to end needs to be added.

[0042] Step 4: Use the PCBS algorithm to perform global path planning on the AGV vehicle that has received the task, and find a static, conflict-free path.

[0043] The aforementioned PCBS algorithm includes a lower-level single-vehicle path planning system and an upper-level conflict search system.

[0044] The aforementioned lower-level bicycle path planning uses the DA* algorithm, which searches only in the direction of the target node during the search phase to reduce the search range, and considers the turning cost in the evaluation function.

[0045] The above method for determining the target direction:

[0046] Dx>=0, Dy>=0; the target node is in the first direction;

[0047] Dx <= 0, Dy >= 0; the target node is in the second direction;

[0048] Dx <= 0, Dy <= 0; the target node is in the third direction;

[0049] Dx>=0, Dy<=0; the target node is in the fourth direction.

[0050] In the above, Dx = x2 - x1, Dy = y2 - y1, (x1, y1) are the coordinates of the current node of the AGV vehicle, (x2, y2) are the coordinates of the target node, Dx is the difference between the x-coordinate of the target node and the x-coordinate of the current node of the vehicle, and Dy is the difference between the y-coordinate of the target node and the y-coordinate of the current node of the vehicle.

[0051] In an unmanned warehouse, the traditional A* algorithm needs to search the four neighboring nodes of the AGV vehicle's current node. In this embodiment, the DA* algorithm only needs to search the two neighboring nodes of the AGV vehicle's current node according to the direction of the target node.

[0052] The evaluation function of the DA* algorithm described above is given by the formula f(n) = g(n) + h. ’ g(n) is the actual cost from the starting point to the current node, and h is the actual cost from the starting point to the current node. ’ (n)=h m (n)+h s (n), where h m (n) represents the Manhattan distance from the searched node to the target node, h s (n) represents the turning cost from the searched node to the target node.

[0053] The above h s (n) = v*t / l, where v is the average speed of the AGV vehicle, t is the time required for the AGV vehicle wheels to turn, and l is the unit grid length, that is, converting the turning cost into a distance cost.

[0054] After the lower-level single-vehicle path planning system calculates the preliminary shortest path, it is input into the upper-level EPIT (Existing Path Information Table). The priority-based upper-level conflict search system searches for nodes with path conflicts. If a conflict is found at node Q, and if one of the AGVs related to the conflict is currently moving, new constraints are added only to the AGVs that have not yet started moving, and these constraints are inherited from the parent node. This node is then defined as Q1, and the DA* algorithm performs path planning for that AGV. The search continues at node Q1 to check for further conflicts. If all the AGVs related to the conflict are currently moving, new constraints are added to all AGVs except those with the highest priority. Furthermore, the constraints of the parent node are inherited and the node is defined as Q1. If there are multiple AGVs with the highest priority, one of the highest priority AGVs is randomly selected as the constraint-free one, and the DA* algorithm is used to plan the path for this AGV. Then, the search for whether there are still conflicts continues in node Q1. If none of the AGVs related to the conflict are currently in motion, node Q is split into the same number of child nodes as the AGVs related to the conflict. Taking two AGVs as an example, node Q is split into two child nodes, namely Q1 and Q2. The constraints of the parent node are inherited and new constraints are added. The path is replanned by the DA* algorithm, and then the search for whether there are still conflicts continues in node Q1.

[0055] The above node search is presented chronologically.

[0056] Step 5: The AGV vehicle cloud system receives the optimal path signal, drives automatically according to the path, and transmits the real-time vehicle information to the central control system.

[0057] The real-time vehicle information mentioned above includes AGV vehicle positioning information, the task being performed, and the AGV vehicle speed.

[0058] Step 6: During the AGV vehicle's operation, the conflict judgment system predicts potential conflicts caused by network latency or AGV vehicle malfunctions and promptly feeds this information back to the central control system to adjust the path and avoid conflicts.

[0059] The aforementioned conflict resolution system includes an AGV vehicle laser emitter, a laser sensor, and a small signal tower.

[0060] The AGV vehicle laser emitter is installed at the front of the vehicle and can emit a laser beam with a distance of one grid length in front of the vehicle. The laser sensor is installed on each path grid and can detect the number and direction of the laser beam. The small signal tower is installed on each path grid and can transmit a warning signal to the main control system.

[0061] like Figure 2 As shown, the working method of the above-mentioned conflict judgment system is as follows: During the AGV vehicle's movement, the laser emitter emits a laser beam with a distance of one grid length in the direction of travel; when the laser sensor of the next grid receives a single laser beam, it indicates that no other AGV vehicle will pass through that grid in the next moment, and the AGV vehicle will continue to move normally; when the laser sensor of the next grid receives multiple laser beams, the direction of the laser beams is used to preliminarily determine the possible conflict type, and a warning signal is transmitted to the main control system by a small signal tower, which then determines the conflict type and adjusts the path.

[0062] The above-mentioned methods for preliminary determination of conflict type include:

[0063] (1) When the laser sensor receives two opposing laser beams, it is a conflict between opposing beams;

[0064] (2) When the laser sensor receives two non-parallel laser beams, it indicates a conflict at the intersection node.

[0065] (3) When the laser sensor receives two laser beams in the same direction, it is a blocking conflict.

[0066] The above-mentioned methods for adjusting the path include methods for resolving conflicts between opposing sides, methods for resolving conflicts at intersection nodes, and methods for resolving conflicts caused by obstruction.

[0067] The above-mentioned reversing conflict resolution method is as follows: the AGV vehicle with lower priority takes the current node as the starting point and the target point as the ending point, and re-plans a conflict-free route using the above-mentioned PCBS algorithm; the AGV vehicle with higher priority drives normally.

[0068] The above-mentioned intersection node conflict resolution method is as follows: AGVs with higher priority can drive normally, while AGVs with lower priority can only drive when the next grid laser sensor receives only a single laser beam. If there are AGVs with the same priority, the AGVs with that priority will drive in a random order.

[0069] The above-mentioned obstacle collision resolution method is as follows: the main control system judges the vehicle status by the real-time information sent by the AGV vehicle in front. If the AGV vehicle in front is in the loading waiting state, the AGV vehicle behind adopts the waiting strategy and waits until the next grid laser sensor receives only a single laser beam before it can move. If the AGV vehicle in front is in a fault state, the AGV vehicle behind adopts the above-mentioned PCBS algorithm to replan the path.

[0070] The multi-AGV path planning method for unmanned warehouses described in this embodiment is implemented through a warehouse communication system, using 5G mobile communication.

[0071] like Figure 3 As shown, the warehouse communication system is arranged in different zones based on shelf density. Two or three small signal towers are set up in high-density areas to specifically receive and transmit signals from these zones. One small signal tower is set up in low-density areas to specifically receive and transmit signals from these zones, ensuring rapid and smooth communication. The small signal towers are interconnected with the AGV vehicle cloud and the overall control system, with their input connected to the output of a grid laser sensor. This method of establishing dedicated small signal towers for each zone ensures fast and smooth information transmission, significantly reducing the possibility of path conflicts caused by signal delays.

[0072] The above shelf density is determined by dividing the total number of shelves in the current zone by the total number of nodes in the current zone.

[0073] The actual process of using the above-mentioned multi-AGV path planning method for unmanned warehouses is as follows:

[0074] Step 1: Based on the actual situation of the unmanned warehouse, create a grid map, including path grids and shelf grids.

[0075] Step 2: The main control system receives the three handling tasks mentioned above.

[0076] Step 3: The overall control system prioritizes the tasks and then distributes them to the AGV vehicles sequentially according to the allocation principle. The allocation results are as follows:

[0077] AGV vehicle 1 – Task A – Starting point (4, 5) – Target point (9, 9)

[0078] AGV vehicle 2 – Task B – Starting point (2, 8) – Target point (6, 4)

[0079] AGV vehicle 3 – Task C – Starting point (6, 2) – Target point (11, 7)

[0080] Step 4: Perform global path planning for the three AGV vehicles using the PCBS algorithm to plan a conflict-free path, as follows:

[0081] Vehicle 1, Route: (4,5)-(5,5)-(6,5)-(6,6)-(6,7)-(6,8)-(6,9)-(7,9)-(8,9)-(9,9)

[0082] Vehicle 2, route: (2,8)-(3,8)-(4,8)-(5,8)-(6,8)-(7,8)-(8,8)-(9,8)-(9,9)-(9,10)-(9,11)

[0083] Vehicle 3, route: (6,2)-(7,2)-(8,2)-(9,2)-(10,2)-(11,2)-(11,3)-(11,4)-(11,5)-(11,6)-(11,7)

[0084] Step 5: The AGV vehicle cloud system receives the above preliminary optimal path signal, drives automatically according to the path, and transmits the real-time vehicle information to the central control system.

[0085] Step 6: During the AGV vehicle's journey, the conflict judgment system predicts potential conflicts and promptly feeds them back to the central control system to adjust the path and avoid conflicts.

[0086] The aforementioned conflict detection system includes a laser emitter, a laser sensor, and a small signal tower for the AGV vehicle.

[0087] The laser emitter of the AGV vehicle is installed at the front of the vehicle and can emit a laser beam with a distance of one grid length in front of the vehicle. The laser sensor is installed on each path grid and can detect the number and direction of the laser beam. The small signal tower is installed on each path grid and can transmit a warning signal to the main control system.

[0088] The specific working steps of the above-mentioned conflict judgment system are as follows: During the AGV vehicle's movement, the laser emitter emits a laser beam with a distance of one grid length in the direction of travel; when the laser sensor of the next grid receives a single laser beam, it indicates that no other AGV vehicle will pass through that grid in the next moment, and the AGV vehicle will continue to move normally; when the laser sensor of the next grid receives multiple laser beams, the direction of the laser beams is used to preliminarily determine the possible conflict type, and a warning signal is transmitted to the main control system by a small signal tower, which then determines the conflict type and adjusts the path.

[0089] The above-mentioned methods for preliminary determination of conflict type include:

[0090] (1) When the laser sensor receives two opposing laser beams, it is a conflict between opposing beams;

[0091] (2) When the laser sensor receives two non-parallel laser beams, it indicates a conflict at the intersection node.

[0092] (3) When the laser sensor receives two laser beams in the same direction, it is a blocking conflict.

[0093] The above-mentioned methods for adjusting the path include methods for resolving conflicts between opposing sides, methods for resolving conflicts at intersection nodes, and methods for resolving conflicts caused by obstruction.

[0094] The above-mentioned reversing conflict resolution method is as follows: the AGV vehicle with lower priority takes the current node as the starting point and the target point as the ending point, and re-plans a conflict-free route using the above-mentioned PCBS algorithm; the AGV vehicle with higher priority drives normally.

[0095] The above-mentioned intersection node conflict resolution method is that AGVs with higher priority can drive normally; AGVs with lower priority can only drive when the next grid laser sensor receives only a single laser beam.

[0096] The above-mentioned obstacle collision resolution method is as follows: the main control system judges the vehicle status by the real-time information sent by the AGV vehicle in front. If the AGV vehicle in front is in the loading waiting state, the AGV vehicle behind adopts the waiting strategy and waits until the next grid laser sensor receives only a single laser beam before it can move. If the AGV vehicle in front is in a fault state, the AGV vehicle behind adopts the above-mentioned PCBS algorithm to replan the path.

[0097] The specific working process of the above conflict determination system is as follows:

[0098] (1) When the AGV vehicle 1 travels to node (6,7), the laser beam emitted by the laser emitter is received by the laser sensor at node (6,8), and the direction is towards the positive y-axis; when the AGV vehicle 2 travels to node (5,8), the laser beam emitted by the laser emitter is received by the laser emitter at node (6,8), and the direction is towards the positive x-axis.

[0099] (2) The laser sensor at node (6,8) receives two non-parallel laser beams and determines that a crossroads node conflict has occurred. The small signal tower at node (6,8) sends a warning signal to the main control system.

[0100] (3) The main control system sends a waiting instruction to the AGV vehicle 2 with lower priority. It can only travel along the original path when the laser sensor at node (6,8) receives a single laser beam; the AGV vehicle 1 with higher priority travels normally.

[0101] The final travel path of the AGV vehicle is as follows:

[0102] AGV vehicle 1, path: (4,5)-(5,5)-(6,5)-(6,6)-(6,7)-(6,8)-(6,9)-(7,9)-(8,9)-(9,9)

[0103] AGV vehicle 2, path: (2,8)-(3,8)-(4,8)-(5,8)-(5,8)-(5,8-(6,8)-(7,8)-(8,8)-(9,8)-(9,9)-(9,10)-(9,11)

[0104] AGV vehicle 3, path: (6,2)-(7,2)-(8,2)-(9,2)-(10,2)-(11,2)-(11,3)-(11,4)-(11,5)-(11,6)-(11,7)

[0105] The method described in this invention is used for multi-AGV path planning in unmanned warehouses, which can allocate tasks more rationally and improve logistics and transportation efficiency. At the same time, the conflict judgment system described above can predict and resolve conflicts more accurately and quickly. Compared with the traditional method of predicting conflicts by monitoring the real-time information of AGV vehicles through the control system, it greatly reduces the burden on the overall control system and improves the accuracy of prediction.

[0106] The following are embodiments of the apparatus of the present invention, which can be used to execute embodiments of the method of the present invention. For details not omitted in the apparatus embodiments, please refer to the embodiments of the method of the present invention.

[0107] In another embodiment of the present invention, a multi-AGV path planning system for unmanned warehouses is provided. This multi-AGV path planning system for unmanned warehouses can be used to implement the above-mentioned multi-AGV path planning method for unmanned warehouses. Specifically, the multi-AGV path planning system for unmanned warehouses includes a grid map model establishment module, a task allocation module, and a path planning module.

[0108] Among them, the raster map model building module is used to build the raster map model.

[0109] The task allocation module is used to assign tasks to designated AGV vehicles according to their priority order.

[0110] The path planning module is used to apply the PCBS algorithm to the AGV vehicles and perform global path planning based on the grid map model to find a static, conflict-free path.

[0111] In another embodiment of the present invention, a terminal device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to achieve a corresponding method flow or corresponding function. The processor described in this embodiment can be used for the operation of a multi-AGV path planning method in an unmanned warehouse, including: S1, establishing a grid map model; S2, assigning tasks to designated AGV vehicles according to their priority order; S3, applying the PCBS algorithm to the AGV vehicles and performing global path planning based on the grid map model to find a static, conflict-free path.

[0112] In another embodiment, the present invention also provides a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understood that the computer-readable storage medium here may include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor, which may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here may be high-speed RAM or non-volatile memory, such as at least one disk storage device.

[0113] One or more instructions stored in a computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the multi-AGV path planning method for unmanned warehouses in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: S1, establish a grid map model; S2, assign tasks to designated AGV vehicles according to the priority order; S3, apply the PCBS algorithm to the AGV vehicles and perform global path planning based on the grid map model to find a static conflict-free path.

[0114] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0115] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0116] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0118] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0119] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be construed as an indication that the applicant has not considered that subject matter as part of the disclosed inventive subject matter.

Claims

1. A multi-AGV path planning method for unmanned warehouses, characterized in that, The process includes the following: S1, Establish a raster map model; S2, assigns tasks to designated AGV vehicles according to their priority order; The priority order of tasks is: large order tasks > small order tasks > AGV vehicle docking tasks, and the priority is set according to the actual importance of the order. The task allocation principle is as follows: the weight of the straight-line length from the AGV vehicle to the target node is 70% plus the weight of time is 30%, and the smaller the value, the higher the priority of allocation; for idle AGV vehicles and AGV vehicles that have completed their tasks and started to return, the time is 0; for AGV vehicles that are currently executing tasks, the waiting time for the current task to end is added. S3. The PCBS algorithm is applied to the above AGV vehicles, and a static, conflict-free path is found by performing global path planning based on the grid map model. The PCBS algorithm consists of a lower-level vehicle path planning system and an upper-level conflict search system; the upper-level vehicle path planning uses DA (Data Encryption System). The algorithm calculates the shortest path; After the lower-level single-vehicle path planning system calculates the shortest path, it is input into the EPIT of the upper-level conflict search system. EPIT is an existing path information table. The upper-level conflict search system searches for nodes with path conflicts. If a conflict is found at a node Q, and one of the AGVs related to the conflict is currently moving, then only the AGVs that have not yet started moving are given new constraints, inheriting the constraints of their parent nodes, and the node is defined as Q1. The DA then... The algorithm re-plans the path for AGVs that haven't started moving, then continues searching for conflicts at node Q1. If all AGVs involved in the conflict are currently moving, new constraints are added to the AGVs with lower priority, inheriting the constraints of their parent nodes, and this node is defined as Q1. The algorithm then uses DA to... The algorithm performs path planning for the AGV vehicle, then continues searching node Q1 for potential conflicts. If none of the AGV vehicles involved in the conflict are currently in motion, node Q splits into the same number of child nodes as the AGV vehicles involved in the conflict, inheriting the constraints of the parent node and adding new constraints, which are then determined by DA. The algorithm replans the path and continues to search for conflicts; DA In the process of calculating the shortest path, the algorithm searches for two adjacent nodes of the current node of the AGV vehicle in the direction of the target node during the search phase, and adds the turning cost to the evaluation function to convert the turning cost into the distance cost. During operation, the AGV emits a laser beam with a distance equal to the length of one grid in the direction of travel. When the AGV receives a single laser beam in the next grid ahead, it indicates that no other AGV will pass through that grid in the next moment, and the AGV continues to travel normally. When the next grid receives multiple laser beams, there is a conflict between multiple AGVs, and the paths of the multiple AGVs are re-divided according to their priority.

2. A multi-AGV path planning system for unmanned warehouses, characterized in that, include: The raster map model creation module is used to create raster map models. The task allocation module is used to assign tasks to designated AGV vehicles according to their priority order. The priority order of tasks is: large order tasks > small order tasks > AGV vehicle docking tasks, and the priority is set according to the actual importance of the order. The task allocation principle is as follows: the weight of the straight-line length from the AGV vehicle to the target node is 70% plus the weight of time is 30%, and the smaller the value, the higher the priority of allocation; for idle AGV vehicles and AGV vehicles that have completed their tasks and started to return, the time is 0; for AGV vehicles that are currently executing tasks, the waiting time for the current task to end is added. The path planning module is used to apply the PCBS algorithm to the above AGV vehicles and perform global path planning based on the grid map model to find a static, conflict-free path. The PCBS algorithm consists of a lower-level vehicle path planning system and an upper-level conflict search system; the upper-level vehicle path planning uses DA (Data Encryption System). The algorithm calculates the shortest path; After the lower-level single-vehicle path planning system calculates the shortest path, it is input into the EPIT of the upper-level conflict search system. EPIT is an existing path information table. The upper-level conflict search system searches for nodes with path conflicts. If a conflict is found at a node Q, and one of the AGVs related to the conflict is currently moving, then only the AGVs that have not yet started moving are given new constraints, inheriting the constraints of their parent nodes, and the node is defined as Q1. The DA then... The algorithm re-plans the path for AGVs that haven't started moving, then continues searching for conflicts at node Q1. If all AGVs involved in the conflict are currently moving, new constraints are added to the AGVs with lower priority, inheriting the constraints of their parent nodes, and this node is defined as Q1. The algorithm then uses DA to... The algorithm performs path planning for the AGV vehicle, then continues searching node Q1 for potential conflicts. If none of the AGV vehicles involved in the conflict are currently in motion, node Q splits into the same number of child nodes as the AGV vehicles involved in the conflict, inheriting the constraints of the parent node and adding new constraints, which are then determined by DA. The algorithm replans the path and continues to search for conflicts; DA In the process of calculating the shortest path, the algorithm searches for two adjacent nodes of the current node of the AGV vehicle in the direction of the target node during the search phase, and adds the turning cost to the evaluation function to convert the turning cost into the distance cost. During operation, the AGV emits a laser beam with a distance equal to the length of one grid in the direction of travel. When the AGV receives a single laser beam in the next grid ahead, it indicates that no other AGV will pass through that grid in the next moment, and the AGV continues to travel normally. When the next grid receives multiple laser beams, there is a conflict between multiple AGVs, and the paths of the multiple AGVs are re-divided according to their priority.

3. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the multi-AGV path planning method for unmanned warehouses as described in claim 1.

4. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the multi-AGV path planning method for unmanned warehouses as described in claim 1.

Images