Automatic guided vehicle path planning method and device for intelligent warehousing

Abstract

The invention discloses an automatic guided vehicle path planning method and device for intelligent warehousing, and relates to the technical field of path planning. Obtaining an order list of intelligent storage, determining the scheduling priority of each order, and carrying out transportation task distribution to obtain a task list; generating a shortest path for any transportation task in the task list to obtain a path list, and determining an automatic guide vehicle according to the transportation path; sending the transportation tasks in the task list to the automatic guide vehicle and executing the transportation tasks; determining key routes and key nodes on the transportation path, monitoring coordinates of each automatic guided vehicle in real time, and if path conflicts exist, performing path planning; the intelligent warehousing system obtains an order list, determines scheduling priority, preferentially processes key orders, and generates a shortest path according to tasks to reduce transportation time and cost and reduce energy consumption. The system monitors path conflicts in real time, local optimization is carried out, the stability and reliability of the logistics system are ensured, and the overall logistics operation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of path planning, and particularly relates to an automatic guided vehicle path planning method and device for intelligent warehousing. Background Art

[0002] With the booming development of the logistics industry, the intelligent warehousing system, as an essential key part in building an efficient and intelligent logistics system, realizes the automation and intelligence of warehouse management and on-site operations by integrating advanced Internet of Things technologies, automated equipment, and intelligent management systems, so as to improve storage efficiency, reduce operating costs, and provide high-quality customer services in a modern warehousing mode.

[0003] In the prior art, goods are transported in the warehouse by automatic guided vehicles. However, there are still some problems when using automatic guided vehicles. For example, there is no real-time monitoring during the operation of automatic guided vehicles. If there are multiple automatic guided vehicles operating at the same time in the aisle or intersection of the shelves, conflicts are likely to occur, resulting in a decrease in the local transportation efficiency of the warehouse and a reduction in the overall stability of the logistics. Summary of the Invention

[0004] The object of the present invention is to solve the problems that there is no real-time monitoring during the operation of automatic guided vehicles, and if there are multiple automatic guided vehicles operating at the same time in the aisle or intersection of the shelves, conflicts are likely to occur, resulting in a decrease in the local transportation efficiency of the warehouse and a reduction in the overall stability of the logistics, and to propose an automatic guided vehicle path planning method and device for intelligent warehousing.

[0005] In the first aspect of the implementation of the present invention, an automatic guided vehicle path planning method for intelligent warehousing is first proposed. The method includes:

[0006] Obtain the order list of the intelligent warehousing and determine the scheduling priority of each order, and perform transportation task allocation according to the scheduling priority to obtain a task list;

[0007] Generate the shortest path for any one transportation task in the task list to obtain a path list, and sequentially determine an automatic guided vehicle for the transportation paths in the path list;

[0008] Send the transportation tasks in the task list to the automatic guided vehicle so that the automatic guided vehicle executes the transportation task according to the transportation path;

[0009] Determine the critical route and critical nodes on the transportation path, and real-time monitor the coordinates of each automatic guided vehicle. If there is a path conflict in the critical route or critical nodes, perform path planning again.

[0010] Optionally, obtaining the order list of the intelligent warehousing and determining the scheduling priority of each order includes:

[0011] Acquire historical order data, extract commodity attributes in the historical order data as a feature matrix, and preprocess the data in the feature matrix to obtain a target feature matrix;

[0012] Initializing the data set in the target feature matrix as a cluster set, calculating the similarity between any group of clusters in the cluster set, and merging the group of clusters if the similarity is greater than a similarity threshold; a group of clusters includes multiple clusters;

[0013] Iteratively merging the cluster set until the clusters in the cluster set are merged into one cluster or a preset number of merging times is reached to obtain a hierarchical clustering model;

[0014] The position of each order in the order list in the hierarchical clustering model is determined, and the scheduling priority is determined according to the position of the order.

[0015] Optionally, generating the shortest path for any task in the task list to obtain a path list includes:

[0016] According to the target task in the task list, determine the storage location, the starting place and the destination of each order in the target task, and generate a target array according to the storage location and the coordinates of the starting place and the destination of each order;

[0017] The target array is used as the initial population, and the initial population is updated by the whale algorithm, and the spiral update is performed by the golden sine spiral motion; the update operation includes: surrounding the prey, spiral update and random search, and any whale individual represents a driving path;

[0018] The fitness of the whales is calculated and the whale with the highest fitness is taken as the update target for iterative update until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined according to the optimal whale individual; the optimal path is the shortest path.

[0019] Optionally, path conflict judgment for key routes or key nodes includes:

[0020] If the repetition degree of a route or node on the transportation path is greater than the repetition threshold, the route or node is determined to be a key route or key node;

[0021] Determine the real-time coordinates of each automated guided vehicle during the operation, and if the next route or node of the target automated guided vehicle on the transport path is a critical route or critical node, perform path conflict judgment;

[0022] If there are multiple automated guided vehicles at the target time, and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles, it is determined that there is a path conflict.

[0023] Optionally, performing path planning again includes:

[0024] Determine the target coordinates of the target automated guided vehicle, the storage location and the target destination of the remaining orders, use the target coordinates as the target starting point, and use the remaining orders as the target transportation tasks;

[0025] Performing path planning according to the target starting place, the storage location of the remaining orders and the target destination to obtain a target transportation path;

[0026] The target transportation task and the target transportation path are sent to an automatic guided vehicle, so that the automatic guided vehicle performs the target transportation task according to the target transportation path.

[0027] In a second aspect of the present invention, a path planning device for an automatic guided vehicle for intelligent warehousing is proposed, comprising: a task determination module, a task allocation module, a task execution module and a local optimization module:

[0028] The task determination module is used to obtain the order list of the intelligent warehousing and determine the dispatch priority of each order, and to allocate the transportation tasks according to the dispatch priority to obtain the task list;

[0029] The task allocation module is used to generate the shortest path for any transport task in the task list to obtain a path list, and determine the automatic guided vehicles for the transport paths in the path list in turn;

[0030] The task execution module is used to send the transportation tasks in the task list to the automatic guided vehicle, so that the automatic guided vehicle executes the transportation tasks according to the transportation path;

[0031] The local optimization module is used to determine the key routes and key nodes on the transportation route, monitor the coordinates of each automatic guided vehicle in real time, and perform path planning again if there is a path conflict on the key routes or key nodes.

[0032] Optionally, the task determination module includes: a feature matrix generation module, a cluster merging module, an iterative merging module and a scheduling priority determination module:

[0033] The feature matrix generation module is used to obtain historical order data, extract commodity attributes in the historical order data as a feature matrix, and pre-process the data in the feature matrix to obtain a target feature matrix;

[0034] The cluster merging module is used to initialize the data set in the target feature matrix into a cluster set, calculate the similarity between any group of clusters in the cluster set, and merge the group of clusters if the similarity is greater than a similarity threshold; a group of clusters includes multiple clusters;

[0035] The iterative merging module is used to iteratively merge the cluster set until the clusters in the cluster set are merged into one cluster or a preset number of merging times is reached to obtain a hierarchical clustering model;

[0036] The scheduling priority determination module is used to determine the position of each order in the order list in the hierarchical clustering model, and determine the scheduling priority according to the position of the order.

[0037] Optionally, the task allocation module includes: an array determination module, an update optimization module and an optimal path output module:

[0038] The array determination module is used to determine the storage location, the starting place and the destination of each order in the target task according to the target task in the task list, and generate a target array according to the storage location and the coordinates of the starting place and the destination of each order;

[0039] The update optimization module is used to use the target array as the initial population, perform an update operation on the initial population through the whale algorithm, and perform spiral update through the golden sine spiral motion; the update operation includes: surrounding the prey, spiral update and random search, and any whale individual represents a driving path;

[0040] The optimal path output module is used to calculate the fitness of the whales and iteratively update the whale with the highest fitness as the update target until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined based on the optimal whale individual; the optimal path is the shortest path.

[0041] Optionally, the local optimization module includes: a key route node judgment module, a path conflict judgment module and a path conflict determination module:

[0042] The key route node judgment module is used to judge the route or node as a key route or key node if the repetition degree of the route or node on the transportation path is greater than the repetition threshold;

[0043] The path conflict judgment module is used to determine the real-time coordinates of each automated guided vehicle during the operation, and if the next route or node of the target automated guided vehicle on the transportation path is a critical route or critical node, a path conflict judgment is performed;

[0044] The path conflict determination module is used to determine that a path conflict exists when there are multiple automated guided vehicles at a target time and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles.

[0045] Optionally, the local optimization module further includes: a remaining task determination module, a local path optimization module and a remaining task execution module:

[0046] The remaining task determination module is used to determine the target coordinates of the target automated guided vehicle, the storage location and the target destination of the remaining orders, and use the target coordinates as the target starting point and the remaining orders as the target transportation tasks;

[0047] The local path optimization module is used to perform path planning according to the target starting place, the storage location of the remaining orders and the target destination to obtain a target transportation path;

[0048] The remaining task execution module is used to send the target transportation task and the target transportation path to the automatic guided vehicle, so that the automatic guided vehicle executes the target transportation task according to the target transportation path.

[0049] Beneficial effects of the present invention:

[0050] The present invention proposes an automatic guided vehicle path planning method for intelligent warehousing, which obtains an order list of intelligent warehousing and determines the scheduling priority of each order, allocates transportation tasks according to the scheduling priority to obtain a task list; generates the shortest path for any transportation task in the task list to obtain a path list, and determines automatic guided vehicles for the transportation paths in the path list in turn; sends the transportation tasks in the task list to the automatic guided vehicle, so that the automatic guided vehicle performs the transportation tasks according to the transportation path; determines the key routes and key nodes on the transportation path, monitors the coordinates of each automatic guided vehicle in real time, and performs path planning again if there is a path conflict in the key route or key node; obtains the order list and determines the scheduling priority through the intelligent warehousing system, gives priority to key orders and ensures the transportation efficiency of key orders, generates the shortest path according to the transportation tasks in the task list, reduces transportation time and cost, reduces energy consumption, monitors and resolves path conflicts in real time, performs local path optimization, ensures the stability and reliability of the logistics system, and improves the operation efficiency of the overall logistics system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present invention will be further described below in conjunction with the accompanying drawings.

[0052] Figure 1 A flow chart of an automatic guided vehicle path planning method for intelligent warehousing is provided for an embodiment of the present invention;

[0053] Figure 2 A structural schematic diagram of an automatic guided vehicle path planning device for intelligent warehousing is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the present invention, the description of "first", "second", etc. is only used for descriptive purposes, and cannot be understood as indicating or implying its relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, 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.

[0055] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0056] The embodiment of the present invention provides a method for automatic guided vehicle path planning for intelligent warehousing. Figure 1 , Figure 1 A flow chart of a method for automatic guided vehicle path planning for intelligent warehousing provided by an embodiment of the present invention. The method comprises the following steps:

[0057] S101, obtaining an order list of the intelligent warehousing and determining the dispatch priority of each order, and assigning the transportation task according to the dispatch priority to obtain a task list;

[0058] S102, generating a shortest path for any transport task in the task list to obtain a path list, and determining an automatic guided vehicle for each transport path in the path list in turn;

[0059] S103, sending the transport task in the task list to the automatic guided vehicle, so that the automatic guided vehicle performs the transport task according to the transport path;

[0060] S104, determining the key routes and key nodes on the transport path, monitoring the coordinates of each automatic guided vehicle in real time, and if there is a path conflict on the key routes or key nodes, performing path planning again;

[0061] An automatic guided vehicle path planning method for intelligent warehousing provided in an embodiment of the present invention obtains an order list and determines a scheduling priority through an intelligent warehousing system, gives priority to key orders and ensures the transportation efficiency of key orders, generates the shortest path according to the transportation tasks in the task list, reduces transportation time and cost, reduces energy consumption, monitors and resolves path conflicts in real time, performs local path optimization, ensures the stability and reliability of the logistics system, and improves the operating efficiency of the overall logistics system.

[0062] In one implementation, an order list of smart warehousing is obtained and a dispatch priority of the order list is determined. The order list contains multiple orders, one order corresponds to one product, and one order corresponds to a dispatch priority (value). The dispatch priorities are arranged in descending order (from large to small), and the corresponding orders are therefore ordered to obtain an order table. The orders in the order table are divided according to a preset number to obtain multiple transportation tasks, and a task list is obtained for multiple transportation tasks; one transportation task corresponds to a shortest path, and the shortest paths generated by all transportation tasks can obtain a path list, and automatic guided vehicles are assigned to the transportation paths in the path list, that is, the nearest allocation, and the automatic guided vehicle closest to the head order or the tail order (the orders in the transportation task are picked up linearly) in the transportation task is assigned. The guide vehicle (idle, task-free automated guided vehicle) serves as the vehicle for this task and sends the transport task in the task list to the automated guided vehicle, where the transport task contains multiple orders. The scheduling priorities (sum of scheduling priorities) of the multiple orders are added as feature tags to the automated guided vehicle that performs this transport task. When the automated guided vehicle performs the transport task according to the transport path, at this moment, if an automated guided vehicle has already appeared on the next critical route (aisle) or critical node (intersection), the vehicle stops and waits; at this moment, if multiple automated guided vehicles are about to pass through the next critical route or critical node at the same time, a path conflict judgment is performed, and the transport path of the party with the largest sum of scheduling priorities remains unchanged, and the remaining automated guided vehicles re-plan their transport paths.

[0063] In one implementation, by obtaining the order list of the smart warehouse and determining the dispatch priority of the order, the system can quickly identify which orders need to be processed first. The above dispatch priority-based dispatch strategy helps to optimize the order processing process and reduce waiting time, thereby significantly improving the efficiency of the overall warehouse operation; ensuring that orders with higher importance (demand) are given priority in transportation.

[0064] In one implementation, transport task allocation is performed according to scheduling priorities, which can ensure the most reasonable utilization of resources (automatic guided vehicles) and allocate transport tasks to idle automated guided vehicles nearby. The above allocation method avoids idleness and waste of resources and optimizes the allocation of transport tasks. Generating the shortest path for the transport tasks in the task list can greatly reduce transport time and cost, improve the transport efficiency and utilization efficiency of automated guided vehicles, reduce energy consumption, reduce idle driving and waiting time, and optimize the operating efficiency of the overall logistics system.

[0065] In one implementation, by real-time monitoring of the coordinates of each AGV and detecting path conflicts at key routes and key nodes, the system can detect and resolve problems in a timely manner. Once a conflict is detected, the system can quickly re-plan the path to ensure that orders with high importance (the largest sum of scheduling priorities) are transported first, thereby avoiding transportation interruptions and delays and ensuring the stability and reliability of the logistics system.

[0066] In one embodiment, step S101 includes:

[0067] Obtain historical order data, extract product attributes in the historical order data as a feature matrix, and preprocess the data in the feature matrix to obtain a target feature matrix;

[0068] Initialize the data set in the target feature matrix as a cluster set, calculate the similarity between any group of clusters in the cluster set, and merge the group of clusters if the similarity is greater than the similarity threshold; a group of clusters contains multiple clusters;

[0069] Iteratively merge the cluster sets until the clusters in the cluster set are merged into one cluster or the preset number of merges is reached to obtain a hierarchical clustering model;

[0070] Determine the position of each order in the order list in the hierarchical clustering model, and determine the scheduling priority based on the position of the order.

[0071] In one implementation, historical order data is obtained and the product attributes (e.g., product price, product purchase quantity, etc.) are used as a feature matrix. Preprocessing such as standardization, padding, and outlier removal is performed to ensure data accuracy and consistency. The feature matrix refers to representing multiple features of an order in the form of a matrix, with each row representing an order and each column representing a feature.

[0072] In one implementation, the hierarchical clustering model (binary tree model) reflects the hierarchical clustering relationship of commodities in historical order data. The aggregation degree of commodities (i.e., the depth or position of the node in the tree) is related to the demand degree of commodities. The higher the aggregation degree of commodities (i.e., the closer the node is to the root of the tree), the higher the demand degree is usually. The higher the demand degree is, the higher the scheduling priority is. Therefore, the commodities corresponding to the order will be arranged for transportation first. By initializing the data set in the target feature matrix as a cluster set and calculating the similarity between clusters (calculating the Euclidean distance), the system can automatically classify orders into different categories. Clustering methods based on similarity help to discover the internal connections and rules between orders, such as which orders belong to the same customer group, which commodities are often purchased together, etc. When the similarity is greater than the similarity threshold, the system merges the relevant clusters, thereby gradually building a hierarchical clustering model.

[0073] In one embodiment, step S102 includes:

[0074] According to the target task in the task list, determine the storage location, starting point and destination of each order in the target task, and generate a target array according to the storage location, starting point and destination coordinates of each order;

[0075] The target array is used as the initial population, and the initial population is updated through the whale algorithm, and spirally updated through the golden sine spiral motion; the update operations include: surrounding the prey, spiral update and random search, and any whale individual represents a driving path;

[0076] The fitness of the whales is calculated and the whale with the highest fitness is taken as the update target for iterative update until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined based on the optimal whale individual; the optimal path is the shortest path.

[0077] In one implementation, the target array consists of the location numbers of the starting point, multiple pickup locations, and the end point. Each number is unique and represents a storage location. An array containing these location numbers is generated by a random permutation generator. This array is an initial solution, which represents a possible driving path. In this array, the order of the location numbers is the order in which the cargo guide vehicle should visit these locations. The initial solutions are generated by random permutations, so they may not be the optimal solutions. Therefore, the path optimization is performed through the whale algorithm. By simulating the whale's predation behavior, iterative updates, and golden sine spiral motion, the optimal path is efficiently searched and approximated in the complex solution space, thereby improving the quality and efficiency of path planning.

[0078] In one implementation, the whale algorithm can strike a balance between global search and local development by simulating the prey behavior of whales. The steps of circling prey, spiral updating, and random search in the whale algorithm enable individual whales to effectively explore the new solution space and optimize existing solutions, thereby enhancing the global search capability. The distribution of individual whales is adjusted by the golden ratio to ensure that the individual whales have good distribution characteristics in the search space and avoid excessive concentration. At the same time, the sine function is introduced to update the position of the individual whales, introducing periodic changes and enhancing the global search capability. The golden sine algorithm optimizes the optimization method of the basic whale algorithm by combining the position update formula of the golden ratio and the sine function, leading the individual to steadily approach the optimal value, coordinating the global exploration and local development capabilities of the algorithm, thereby improving the optimization accuracy and speed of the algorithm.

[0079] In one embodiment, step S104 includes:

[0080] If the repetition degree of a route or node on the transportation path is greater than the repetition threshold, the route or node is determined to be a key route or key node;

[0081] Determine the real-time coordinates of each automated guided vehicle during the operation, and if the next route or node of the target automated guided vehicle on the transport path is a critical route or critical node, perform path conflict judgment;

[0082] If there are multiple automated guided vehicles at the target time, and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles, it is determined that there is a path conflict.

[0083] In one implementation, if many transport routes pass through the same route or node, and the repetition degree (the number of routes passed) is greater than the repetition threshold, the route or node is determined to be a critical route or critical node, which means that the critical route or critical node is relatively busy and prone to congestion and conflict problems; the coordinates of each automatic guided vehicle are determined in real time, and based on this, it is judged whether the target automatic guided vehicle is about to enter the critical route or node (judged on the previous route or node), and the transportation process is dynamically monitored and warned. Through early judgment, potential path conflict problems can be discovered in time, providing sufficient time for subsequent scheduling and path adjustment. The real-time performance brought by the above steps not only improves transportation efficiency, but also enhances the flexibility and response speed of the system.

[0084] In one implementation, by comparing the dispatching priorities of the target AGV and other AGVs, it is possible to accurately determine whether there is a path conflict when there are multiple AGVs at the target time, because each AGV has a feature tag (the sum of dispatching priorities), and because the dispatching priorities are arranged in descending order, there is no possibility of the same dispatching priority. This conflict judgment method based on dispatching priorities ensures orderliness and fairness in the transportation process. It avoids transportation delays and inefficiencies caused by path conflicts and improves the operating efficiency of the entire logistics system.

[0085] In one embodiment, step S104 further includes:

[0086] Determine the target coordinates of the target AGV, the storage location and target destination of the remaining orders, use the target coordinates as the target starting point, and use the remaining orders as the target transportation tasks;

[0087] The target transportation route is obtained by performing route planning based on the target starting point, the storage location of the remaining orders and the target destination;

[0088] The target transportation task and the target transportation path are sent to the automatic guided vehicle, so that the automatic guided vehicle performs the target transportation task according to the target transportation path.

[0089] In one implementation, by determining the target coordinates of the target automated guided vehicle, the storage location of the remaining orders, and the target destination, the starting point and end point of the automated guided vehicle mission, as well as the specific goods to be transported, are set. The above-mentioned setting of the transport mission ensures that the automated guided vehicle can perform the transport mission efficiently and accurately, reducing resource waste and time delays caused by path conflicts.

[0090] In one implementation, path planning is performed based on the target starting point, the storage location of the remaining orders, and the target destination, and an optimal or suboptimal target transportation path can be obtained. Optimizing the transportation path again is equivalent to optimizing the local transportation efficiency, thereby ensuring the efficiency and accuracy of the entire logistics system during the transportation process.

[0091] Based on the same inventive concept, the present invention also provides a path planning device for an automatic guided vehicle for intelligent warehousing. Figure 2 , Figure 2 A schematic diagram of the structure of an automatic guided vehicle path planning device for intelligent warehousing provided by an embodiment of the present invention includes: a task determination module, a task allocation module, a task execution module and a local optimization module:

[0092] The task determination module is used to obtain the order list of the intelligent warehousing and determine the scheduling priority of the order list, and allocate the transportation tasks according to the scheduling priority to obtain the task list;

[0093] A task allocation module, used for generating a shortest path for any transport task in the task list to obtain a path list, and determining an automatic guided vehicle for each transport path in the path list in turn;

[0094] A task execution module, used for sending the transport tasks in the task list to the automatic guided vehicle, so that the automatic guided vehicle executes the transport tasks according to the transport path;

[0095] The local optimization module is used to determine the key routes and key nodes on the transportation path, monitor the coordinates of each automatic guided vehicle in real time, and perform path planning again if there is a path conflict on the key route or key node.

[0096] An automatic guided vehicle path planning device for intelligent warehousing provided in an embodiment of the present invention obtains an order list and determines a scheduling priority through an intelligent warehousing system, gives priority to key orders and ensures the transportation efficiency of key orders, generates the shortest path according to the transportation tasks in the task list, reduces transportation time and cost, reduces energy consumption, monitors and resolves path conflicts in real time, performs local path optimization, ensures the stability and reliability of the logistics system, and improves the operating efficiency of the overall logistics system.

[0097] In one embodiment, the task determination module includes: a feature matrix generation module, a cluster merging module, an iterative merging module and a scheduling priority determination module:

[0098] A feature matrix generation module is used to obtain historical order data, extract commodity attributes in the historical order data as a feature matrix, and preprocess the data in the feature matrix to obtain a target feature matrix;

[0099] The cluster merging module is used to initialize the data set in the target feature matrix into a cluster set, calculate the similarity between any group of clusters in the cluster set, and merge the group of clusters if the similarity is greater than the similarity threshold; a group of clusters contains multiple clusters;

[0100] An iterative merging module, used for iteratively merging the cluster set until the clusters in the cluster set are merged into one cluster or a preset number of merging times is reached to obtain a hierarchical clustering model;

[0101] The scheduling priority determination module is used to determine the position of each order in the order list in the hierarchical clustering model and determine the scheduling priority according to the position of the order.

[0102] In one embodiment, the task allocation module includes: an array determination module, an update optimization module and an optimal path output module:

[0103] An array determination module is used to determine the storage location, the starting point and the destination of each order in the target task according to the target task in the task list, and generate a target array according to the storage location and the coordinates of the starting point and the destination of each order;

[0104] The update optimization module is used to use the target array as the initial population, perform update operations on the initial population through the whale algorithm, and perform spiral updates through golden sine spiral motion; the update operations include: surrounding prey, spiral update and random search, and any whale individual represents a driving path;

[0105] The optimal path output module is used to calculate the fitness of the whales and iteratively update the whale with the highest fitness as the update target until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined based on the optimal whale individual; the optimal path is the shortest path.

[0106] In one embodiment, the local optimization module includes: a key route node judgment module, a path conflict judgment module and a path conflict determination module:

[0107] A critical route node judgment module is used to judge a route or node as a critical route or critical node if the repetition degree of a route or node on a transportation path is greater than a repetition threshold;

[0108] A path conflict judgment module is used to determine the real-time coordinates of each automated guided vehicle during the operation process. If the next route or node of the target automated guided vehicle on the transportation path is a critical route or critical node, a path conflict judgment is performed;

[0109] The path conflict determination module is used to determine that there is a path conflict when there are multiple automated guided vehicles at a target time and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles.

[0110] In one embodiment, the local optimization module further includes: a remaining task determination module, a local path optimization module and a remaining task execution module:

[0111] The remaining task determination module is used to determine the target coordinates of the target automated guided vehicle, the storage location and target destination of the remaining orders, and use the target coordinates as the target starting point and the remaining orders as the target transportation tasks;

[0112] The local path optimization module is used to plan the path according to the target starting point, the storage location of the remaining orders and the target destination to obtain the target transportation path;

[0113] The remaining task execution module is used to send the target transportation task and the target transportation path to the automatic guided vehicle, so that the automatic guided vehicle executes the target transportation task according to the target transportation path.

[0114] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for automatic guided vehicle path planning for intelligent warehousing, characterized in that: The method comprises: Obtain the order list of smart warehousing and determine the scheduling priority of each order, and assign transportation tasks according to the scheduling priority to obtain a task list; Generate a shortest path for any transport task in the task list to obtain a path list, and determine an automatic guided vehicle for each transport path in the path list in turn; Sending the transport tasks in the task list to an automated guided vehicle so that the automated guided vehicle performs the transport tasks according to a transport path; Determine the key routes and key nodes on the transport route, monitor the coordinates of each automated guided vehicle in real time, and perform path planning again if there is a path conflict on the key routes or key nodes.

2. The method for automatic guided vehicle path planning for intelligent warehousing according to claim 1, characterized in that: Obtaining the order list of smart warehousing and determining the scheduling priority of each order includes: Acquire historical order data, extract commodity attributes in the historical order data as a feature matrix, and preprocess the data in the feature matrix to obtain a target feature matrix; Initializing the data set in the target feature matrix as a cluster set, calculating the similarity between any group of clusters in the cluster set, and merging the group of clusters if the similarity is greater than a similarity threshold; a group of clusters includes multiple clusters; Iteratively merging the cluster set until the clusters in the cluster set are merged into one cluster or a preset number of merging times is reached to obtain a hierarchical clustering model; The position of each order in the order list in the hierarchical clustering model is determined, and the scheduling priority is determined according to the position of the order.

3. The method for automatic guided vehicle path planning for intelligent warehousing according to claim 1, characterized in that: Generating the shortest path for any task in the task list to obtain a path list includes: According to the target task in the task list, determine the storage location, the starting place and the destination of each order in the target task, and generate a target array according to the storage location and the coordinates of the starting place and the destination of each order; The target array is used as the initial population, and the initial population is updated by the whale algorithm, and the spiral update is performed by the golden sine spiral motion; the update operation includes: surrounding the prey, spiral update and random search, and any whale individual represents a driving path; The fitness of the whales is calculated and the whale with the highest fitness is taken as the update target for iterative update until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined according to the optimal whale individual; the optimal path is the shortest path.

4. The method for automatic guided vehicle path planning for intelligent warehousing according to claim 1, characterized in that: Path conflict judgment for key routes or key nodes includes: If the repetition degree of a route or node on the transportation path is greater than the repetition threshold, the route or node is determined to be a key route or key node; Determine the real-time coordinates of each automated guided vehicle during the operation, and if the next route or node of the target automated guided vehicle on the transport path is a critical route or critical node, perform path conflict judgment; If there are multiple automated guided vehicles at the target time, and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles, it is determined that there is a path conflict.

5. The method for automatic guided vehicle path planning for intelligent warehousing according to claim 1, characterized in that: Path planning again includes: Determine the target coordinates of the target automated guided vehicle, the storage location and the target destination of the remaining orders, use the target coordinates as the target starting point, and use the remaining orders as the target transportation tasks; Performing path planning according to the target starting place, the storage location of the remaining orders and the target destination to obtain a target transportation path; The target transportation task and the target transportation path are sent to an automatic guided vehicle, so that the automatic guided vehicle performs the target transportation task according to the target transportation path.

6. An automatic guided vehicle path planning device for intelligent warehousing, characterized in that: The device comprises: a task determination module, a task allocation module, a task execution module and a local optimization module: The task determination module is used to obtain the order list of the intelligent warehousing and determine the dispatch priority of each order, and to allocate the transportation tasks according to the dispatch priority to obtain the task list; The task allocation module is used to generate the shortest path for any transport task in the task list to obtain a path list, and determine the automatic guided vehicles for the transport paths in the path list in turn; The task execution module is used to send the transportation tasks in the task list to the automatic guided vehicle, so that the automatic guided vehicle executes the transportation tasks according to the transportation path; The local optimization module is used to determine the key routes and key nodes on the transportation route, monitor the coordinates of each automatic guided vehicle in real time, and perform path planning again if there is a path conflict on the key routes or key nodes.

7. The automatic guided vehicle path planning device for intelligent warehousing according to claim 6, characterized in that: The task determination module includes: a feature matrix generation module, a cluster merging module, an iterative merging module and a scheduling priority determination module: The feature matrix generation module is used to obtain historical order data, extract commodity attributes in the historical order data as a feature matrix, and pre-process the data in the feature matrix to obtain a target feature matrix; The cluster merging module is used to initialize the data set in the target feature matrix into a cluster set, calculate the similarity between any group of clusters in the cluster set, and merge the group of clusters if the similarity is greater than a similarity threshold; a group of clusters includes multiple clusters; The iterative merging module is used to iteratively merge the cluster set until the clusters in the cluster set are merged into one cluster or a preset number of merging times is reached to obtain a hierarchical clustering model; The scheduling priority determination module is used to determine the position of each order in the order list in the hierarchical clustering model, and determine the scheduling priority according to the position of the order.

8. The automatic guided vehicle path planning device for intelligent warehousing according to claim 6, characterized in that: The task allocation module includes: an array determination module, an update optimization module and an optimal path output module: The array determination module is used to determine the storage location, the starting place and the destination of each order in the target task according to the target task in the task list, and generate a target array according to the storage location and the coordinates of the starting place and the destination of each order; The update optimization module is used to use the target array as the initial population, perform an update operation on the initial population through the whale algorithm, and perform spiral update through the golden sine spiral motion; the update operation includes: surrounding the prey, spiral update and random search, and any whale individual represents a driving path; The optimal path output module is used to calculate the fitness of the whales and iteratively update the whale with the highest fitness as the update target until the preset number of iterations or fitness threshold is reached, then the optimal whale individual is output, and the optimal path is determined based on the optimal whale individual; the optimal path is the shortest path.

9. The automatic guided vehicle path planning device for intelligent warehousing according to claim 6, characterized in that: The local optimization module includes: a key route node judgment module, a path conflict judgment module and a path conflict determination module: The key route node judgment module is used to judge the route or node as a key route or key node if the repetition degree of the route or node on the transportation path is greater than the repetition threshold; The path conflict judgment module is used to determine the real-time coordinates of each automated guided vehicle during the operation, and if the next route or node of the target automated guided vehicle on the transportation path is a critical route or critical node, a path conflict judgment is performed; The path conflict determination module is used to determine that a path conflict exists when there are multiple automated guided vehicles at a target time and the scheduling priority of the target automated guided vehicle is lower than that of other automated guided vehicles.

10. The automatic guided vehicle path planning device for intelligent warehousing according to claim 6, characterized in that: The local optimization module also includes: a remaining task determination module, a local path optimization module and a remaining task execution module: The remaining task determination module is used to determine the target coordinates of the target automated guided vehicle, the storage location and the target destination of the remaining orders, and use the target coordinates as the target starting point and the remaining orders as the target transportation tasks; The local path optimization module is used to perform path planning according to the target starting place, the storage location of the remaining orders and the target destination to obtain a target transportation path; The remaining task execution module is used to send the target transportation task and the target transportation path to the automatic guided vehicle, so that the automatic guided vehicle executes the target transportation task according to the target transportation path.

Images