Intelligent storage multi-AGV scheduling method and system

Abstract

The invention discloses an intelligent storage multi-AGV scheduling method and system, and relates to the technical field of storage scheduling. A graph optimization algorithm is combined with a multi-target scheduling tradeoff factor model to solve a task path, output a task allocation and path planning scheme, load the task allocation and path planning scheme to a time axis, and perform time sequence simulation on the path; potential congestion points or resource conflict areas in the paths are identified, part of AGV paths are optimized according to identification results, time passing pressure indexes and actual AGV operation states are used as input, scheduling verification is performed through multi-round offline simulation, a multi-AGV scheduling holographic data set is integrated, and a task state driven multi-AGV closed-loop scheduling scheme is constructed. According to the scheduling method, a multi-dimensional scheduling model fusing tasks, paths and resource information is constructed, and graph optimization, dynamic simulation and closed-loop control are combined, so that efficient collaboration and real-time response of multiple AGV systems are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse scheduling, and in particular to an intelligent warehouse multi-AGV scheduling method and system. Background Art

[0002] With the development of Industry 4.0 and smart logistics, traditional labor-intensive warehousing operations are gradually evolving towards automation and intelligence. Automated guided vehicles (AGVs) have been widely used in modern smart warehousing factories due to their high efficiency, safety, and sustainable operation, becoming one of the core logistics execution units. Compared with single AGV systems, multi-AGV systems can significantly improve task throughput and warehousing efficiency, and are particularly suitable for practical application needs in multi-tasking concurrency and highly dynamic environments.

[0003] The existing technology has the following defects:

[0004] Existing scheduling methods rely on static path planning, ignoring the dynamic resource conflicts and spatiotemporal coupling problems during task execution. They cannot effectively deal with the scheduling bottlenecks caused by intensive tasks and multi-vehicle collaboration in complex warehousing environments. Secondly, they adopt step-by-step task allocation and path planning, lacking multi-dimensional fusion modeling between task status, path resources and vehicle behavior, resulting in insufficient global optimization capabilities of scheduling strategies.

[0005] Based on this, the present invention proposes an intelligent warehousing multi-AGV scheduling method and system, which realizes efficient coordination and real-time response of multi-AGV systems by constructing a multi-dimensional scheduling model that integrates task, path and resource information, and combines graph optimization, dynamic simulation and closed-loop control. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent warehousing multi-AGV scheduling method and system to solve the shortcomings of the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a multi-AGV scheduling method for intelligent warehousing, the scheduling method comprising the following steps:

[0008] Step S1: The collection end obtains the structured layout information of the warehouse factory and initializes the task state map based on the current operating status of the AGV cluster;

[0009] Step S2: Mark the intersection and resource occupancy of AGVs on spatial paths and time resources to generate a multi-AGV collaborative scheduling map;

[0010] Step S3: Assign comprehensive scheduling weights to each feasible path and task allocation scheme, and construct a multi-objective scheduling trade-off factor model;

[0011] Step S4: Using a graph optimization algorithm combined with a multi-objective scheduling trade-off factor model to solve the task path, and outputting a task allocation and path planning solution;

[0012] Step S5: Load the task assignment and path planning scheme into the timeline, perform timing simulation on the path, identify potential congestion points or resource conflict areas in the path, and optimize some AGV paths based on the identification results;

[0013] Step S6: Count the time-traffic pressure index of each path within the scheduling period, use the time-traffic pressure index and the actual AGV operation status as input, and perform scheduling verification through multiple rounds of offline simulation;

[0014] Step S7: Integrate the multi-AGV scheduling holographic dataset and build a multi-AGV closed-loop scheduling solution driven by task status.

[0015] Preferably, a timing simulation is performed on the path to identify potential congestion points or resource conflict areas in the path, and part of the AGV path is optimized based on the identification results, including the following steps:

[0016] Construct each path in the task allocation and path planning scheme Time interval ;

[0017] The potential congestion point or resource conflict area judgment expression is: ,in, Indicates that the i-th AGV is in the path segment The actual occupied time interval on Indicates that the jth AGV is in the path segment The actual occupied time interval on

[0018] All paths that meet the judgment expression are marked as conflict-sensitive segments, and the time traffic pressure index is introduced. , which is used to describe the average AGV occupancy intensity on the path segment per unit time, sort the traffic pressure levels of all conflict-sensitive segments according to the time traffic pressure index, and execute the path conflict optimization strategy based on the simulation results, including staggered driving, path reselection and soft start control.

[0019] Preferably, the time-traffic pressure index of each path within the scheduling period is counted, and the time-traffic pressure index and the actual AGV operation status are used as inputs to perform scheduling verification through multiple rounds of offline simulation, including the following steps:

[0020] The average AGV passage frequency and task density The time-based traffic pressure index is obtained through weighted calculation;

[0021] Introducing dynamic feedback parameters for task execution, extracting each AGV's transit time and scheduling delay feedback from actual operation data;

[0022] The time-travel pressure indicators of all paths and the actual operating status of the AGV are input into multiple rounds of offline simulation programs to simulate the operating performance under different scheduling parameters.

[0023] Preferably, a comprehensive scheduling weight is assigned to each feasible path and task allocation scheme, and a multi-objective scheduling trade-off factor model is constructed, which includes the following steps:

[0024] Based on path distance and resource conflict costs Construct a comprehensive scheduling weight function of paths and tasks to evaluate AGVs Execute the task The overall dispatching cost .

[0025] Preferably, the resource conflict cost Defined as: ,in, Indicates AGV On the path Execute tasks on The time interval, n is the number of paths, Indicates the task time interval of other AGVs on the same path, function is an indicator function that outputs 1 when the two time intervals intersect, otherwise it outputs 0. Indicates AGV On the path Execute tasks on time interval, represents the intersection of two time intervals, If the intersection of the two time intervals is not empty, that is, there is a time overlap, the path is defined as a potential conflict segment.

[0026] Preferably, the intersection and resource occupation of AGVs on spatial paths and time resources are marked to generate a multi-AGV collaborative scheduling map, including the following steps:

[0027] Map the collected transport task queue to the constructed task state graph. Transport tasks include pickup, handling, and delivery.

[0028] Decompose the transportation task process into task units ,in For the transport missions, is the i-th subtask step, and s is the number of subtask steps;

[0029] Extracting the paths involved in task execution in space , and mapped to the spatial topology of the scheduling graph in the node dimension;

[0030] In the time dimension, the task process is time-sliced ​​according to the task time window to form a three-dimensional scheduling diagram data body. , forming a three-dimensional mapping structure of task-path-node;

[0031] In each path The time occupancy interval is defined above, and the resource occupancy tensor is introduced to describe the time domain competition relationship of AGV on system resources;

[0032] Based on the scheduling graph and resource occupancy tensor, the AGV behavior data and task path timing are integrated to generate a multi-AGV collaborative scheduling graph.

[0033] Preferably, a scheduling diagram data body with a three-dimensional structure is formed , expressed as: ,in, Represents the set of spatial nodes in a three-dimensional scheduling graph, is the set of path edges, It is a time layer structure used to describe the time interval occupied by each task unit on the path.

[0034] Preferably, the collection end obtains the structured layout information of the storage plant, including the spatial coordinates and capacity parameters of the storage sites, the topological structure and access constraints of the transportation paths, the resource scheduling priority and accessibility determination of the transfer nodes, and the operating capacity parameters of the operating platforms;

[0035] Obtain the dynamic operating status data of the AGV cluster, including the current location coordinates, remaining power, current load weight, and task queue status of each AGV.

[0036] Preferably, the collection end obtains the structured layout information of the storage factory and initializes the task state map based on the current operating state of the AGV cluster, including the following steps:

[0037] Combine structured layout information and operation status data to construct a task status graph, using a graph structure to represent the multiple relationships among AGVs, tasks, paths, and resources.

[0038] Each node in the task state graph represents a scheduling element, and each edge represents the task transfer path or resource occupancy relationship;

[0039] Task status graph Expressed as: ,in, Represents the node set in the graph, including AGV nodes, task nodes and resource nodes. Represents the set of edges between nodes, is the weight matrix.

[0040] The present application also provides an intelligent warehousing multi-AGV scheduling system, including a map generation module, a solution output module, a simulation verification module, and a scheduling solution construction module;

[0041] Graph generation module: This module obtains the structured layout information of the warehouse factory, initializes the task state graph based on the current operating status of the AGV cluster, marks the intersection and resource occupation of AGVs in spatial paths and time resources, and generates a multi-AGV collaborative scheduling graph;

[0042] Solution output module: Assigns comprehensive scheduling weights to each feasible path and task allocation solution, builds a multi-objective scheduling trade-off factor model, uses a graph optimization algorithm combined with the multi-objective scheduling trade-off factor model to solve the task path, and outputs the task allocation and path planning solution;

[0043] Simulation Verification Module: This module loads the task assignment and path planning scheme into the timeline, performs timing simulation on the path, identifies potential congestion points or resource conflict areas in the path, optimizes some AGV paths based on the identification results, calculates the time traffic pressure index of each path within the scheduling cycle, and uses the time traffic pressure index and the actual AGV operating status as input to perform scheduling verification through multiple rounds of offline simulation.

[0044] Scheduling solution construction module: Integrate multi-AGV scheduling holographic data sets to build a multi-AGV closed-loop scheduling solution driven by task status.

[0045] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0046] The present invention assigns a comprehensive scheduling weight to each feasible path and task allocation scheme, constructs a multi-objective scheduling trade-off factor model, uses a graph optimization algorithm combined with the multi-objective scheduling trade-off factor model to solve the task path, outputs the task allocation and path planning scheme, loads the task allocation and path planning scheme into the timeline, performs a time series simulation on the path, identifies potential congestion points or resource conflict areas in the path, and optimizes some AGV paths based on the identification results. The time traffic pressure index of each path within the scheduling cycle is calculated, and the time traffic pressure index and the actual AGV operating status are used as input. Scheduling verification is performed through multiple rounds of offline simulation, and a multi-AGV scheduling holographic data set is integrated to construct a task status-driven multi-AGV closed-loop scheduling scheme. This scheduling method achieves efficient coordination and real-time response of multi-AGV systems by constructing a multi-dimensional scheduling model that integrates task, path and resource information, and combines graph optimization, dynamic simulation and closed-loop control, significantly improving scheduling accuracy and operational stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0048] Figure 1 Flowchart of the scheduling method of the present invention.

[0049] Figure 2 This is a timing diagram of the scheduling method of the present invention.

[0050] Figure 3 This is an architectural diagram of the scheduling system of the present invention. DETAILED DESCRIPTION

[0051] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0052] Example 1: Please refer to Figure 1-Figure 2 As shown, this embodiment provides a multi-AGV scheduling method for intelligent warehousing, and the scheduling method includes the following steps:

[0053] Step S1: The acquisition end obtains the structured layout information of the warehouse factory, which includes storage locations, transportation routes, transfer nodes, and work platforms. Combined with the current operating status of the AGV cluster (location information, load status, power level, task queue, etc.), it initializes the task status map as the basic input for scheduling analysis.

[0054] Step S2: Map the current transport task queue to be executed to the task status map, establish a task-path-node three-dimensional scheduling diagram by decomposing the task process (such as picking up, moving, and delivering), and mark the potential intersections and resource occupation of AGVs in spatial paths and time resources to generate a multi-AGV collaborative scheduling map.

[0055] Step S3: Introduce path planning criteria (such as load balancing) and resource competition control mechanisms (such as avoidance priority), assign comprehensive scheduling weights to each feasible path and task allocation plan, and construct a multi-objective scheduling trade-off factor model.

[0056] Step S4: Use a graph optimization algorithm (such as improved A*) combined with a multi-objective scheduling trade-off factor model to solve the task path and output a set of task allocation and path planning solutions. The task allocation and path planning solutions record the task sequence, path nodes, expected execution time, and resource usage details of each AGV.

[0057] Step S5: Load the task assignment and path planning scheme into the timeline, perform timing simulation on the path, and identify potential congestion points or resource conflict areas in the path. Based on the identification results, optimize some AGV paths (such as staggered driving, path reselection, and slow start) to minimize path conflicts.

[0058] Step S6: Count the path load characteristics of each path during the scheduling cycle. The path load characteristics include the average AGV passage frequency and task density, and construct the path's time traffic pressure index. Combined with the task execution dynamic feedback parameters, which include data such as AGV passage time and scheduling delay feedback, the risk bottleneck section is identified to provide target area positioning for subsequent scheduling optimization. The time traffic pressure index and the actual AGV operating status are used as input. The scheduling stability and response efficiency are verified through multiple rounds of offline simulations, and the scheduling parameters are calibrated.

[0059] Step S7: Integrate the multi-AGV scheduling holographic dataset, which includes the task state map, the multi-AGV collaborative scheduling map, the AGV path optimization results and the scheduling simulation verification results, and build a task state-driven multi-AGV closed-loop scheduling scheme to realize the task loading-path generation-state feedback-path reconstruction loop control mode, thereby realizing efficient, robust and adaptive collaborative scheduling of multi-AGV systems in complex dynamic warehousing scenarios.

[0060] This application assigns a comprehensive scheduling weight to each feasible path and task allocation scheme, constructs a multi-objective scheduling trade-off factor model, uses a graph optimization algorithm combined with a multi-objective scheduling trade-off factor model to solve the task path, outputs the task allocation and path planning scheme, loads the task allocation and path planning scheme into the timeline, performs time-series simulation on the path, identifies potential congestion points or resource conflict areas in the path, and optimizes some AGV paths based on the identification results. The time traffic pressure index of each path within the scheduling cycle is counted, and the time traffic pressure index and the actual AGV operating status are used as input. Scheduling verification is performed through multiple rounds of offline simulation, and a multi-AGV scheduling holographic data set is integrated to construct a task status-driven multi-AGV closed-loop scheduling scheme. This scheduling method achieves efficient coordination and real-time response of multi-AGV systems by constructing a multi-dimensional scheduling model that integrates task, path and resource information, and combines graph optimization, dynamic simulation and closed-loop control, significantly improving scheduling accuracy and operational stability.

[0061] See also Figure 3 As shown, this embodiment provides an intelligent warehousing multi-AGV scheduling system, including a map generation module, a solution output module, a simulation verification module, and a scheduling solution construction module;

[0062] Graph generation module: obtains the structured layout information of the warehouse factory, initializes the task state graph based on the current operating status of the AGV cluster, marks the intersection and resource occupation of AGVs in spatial paths and time resources, and generates a multi-AGV collaborative scheduling graph. The task state graph and multi-AGV collaborative scheduling graph are sent to the scheduling plan construction module, and the task state graph is sent to the plan output module;

[0063] Solution output module: Assigns comprehensive scheduling weights to each feasible path and task allocation solution, builds a multi-objective scheduling trade-off factor model, uses a graph optimization algorithm combined with the multi-objective scheduling trade-off factor model to solve the task path, and outputs the task allocation and path planning solution. The task allocation and path planning solution is sent to the simulation verification module;

[0064] Simulation Verification Module: Loads the task assignment and path planning scheme into the timeline, performs timing simulation on the path, identifies potential congestion points or resource conflict areas in the path, optimizes some AGV paths based on the identification results, calculates the time traffic pressure index of each path within the scheduling cycle, uses the time traffic pressure index and the actual AGV operating status as input, performs scheduling verification through multiple rounds of offline simulation, and sends the AGV path optimization results and scheduling simulation verification results to the scheduling scheme construction module;

[0065] Scheduling solution construction module: Integrate multi-AGV scheduling holographic data sets to build a multi-AGV closed-loop scheduling solution driven by task status.

[0066] Example 2: Step S1: The acquisition end obtains the structured layout information of the storage factory, which includes storage locations, transportation routes, transfer nodes, and work platforms, etc., and initializes the task status map based on the current operating status of the AGV cluster (position information, load status, power level, task queue, etc.) as the basic input for scheduling analysis.

[0067] The data collection end first obtains structured warehouse layout information through Industrial IoT devices, warehouse management systems (WMS), and manufacturing execution systems (MES). This information covers multiple dimensions, including the spatial coordinates and capacity parameters of storage locations, the topology and access constraints of transport routes, the resource scheduling priorities and accessibility of transfer nodes, and the operational capacity parameters of workstations (such as processing cycle time, loading and unloading efficiency, and operating time windows). This information collectively forms the foundation for the digital representation of the warehouse's physical space and serves as the core support for subsequent AGV scheduling modeling.

[0068] On this basis, the system obtains the dynamic operating status data of the AGV cluster, including: the current position coordinates of each AGV, the remaining power, and the current load weight. To further support intelligent scheduling analysis, it is necessary to construct a task state graph (Task-State-Mapping-Graph) to represent the multiple relationships between AGVs, tasks, paths, and resources in a graph structure. Each node in the graph represents a scheduling element (such as an AGV or a task site), and each edge represents the transfer path or resource occupancy relationship of the task. The edge weight can be weighted according to time cost, energy consumption, traffic priority, etc. This graph can be formalized as: ,in, Represents the node set in the graph, including AGV nodes, task nodes and resource nodes. Represents the set of edges between nodes, is a weight matrix that reflects the scheduling cost function (such as path length, task priority, etc.). The elements in the weight matrix are defined as: ,in, represents the scheduling cost from node i to j; is the path distance from node i to j, is the total path length.

[0069] The establishment of the above-mentioned task status map not only provides the scheduling system with comprehensive cognitive capabilities of existing resources and task status, but also provides a unified data foundation and modeling context for subsequent path optimization, task allocation and simulation prediction. It is the starting point and core input of the entire multi-AGV scheduling method.

[0070] Step S2: Map the current transport task queue to be executed to the task status map, establish a task-path-node three-dimensional scheduling diagram by decomposing the task process (such as picking up, moving, and delivering), and mark the potential intersections and resource occupation of AGVs in spatial paths and time resources to generate a multi-AGV collaborative scheduling map.

[0071] The collected transport task queue is mapped to the constructed task state map, and detailed modeling is carried out based on the operational process of the task life cycle. Transport tasks usually include several operational units, such as pickup, transport, and drop-off, and their processes have obvious spatial continuity and time constraints. Therefore, in order to more accurately depict the interactive relationship between tasks, paths, and resources, the transport task process needs to be decomposed into task units. ,in is the kth transportation task, is the i-th subtask step, and s is the number of subtask steps.

[0072] In space, the system extracts the paths involved in task execution , and mapped to the spatial topology of the scheduling graph in the node dimension; in the time dimension, the task process is time-sliced ​​according to the system beat or task time window to form a three-dimensional scheduling graph data body , recorded as: ,in, Represents the set of spatial nodes in a three-dimensional scheduling graph, is the set of path edges, The time-layer structure describes the time interval of each task unit on the path, forming a three-dimensional mapping structure of "task-path-node". To achieve collaborative scheduling, the system needs to further identify conflict areas such as path overlap, time intersection, and resource competition between AGVs on the three-dimensional scheduling diagram.

[0073] On each path, the time interval is defined as: ,in, For the task On the path The actual occupied time interval on is the time of entering the path, is the departure time. If there are two tasks , which are on the same path Satisfaction on: , For the task On the path The actual occupied time interval on represents the intersection of two time intervals, If the intersection of these two time intervals is not empty, that is, there is a time overlap, then the path is defined as a potential conflict segment. It is necessary to introduce a coordination mechanism to lock resources or stagger tasks. To describe the time domain competition relationship between AGVs for system resources, the resource occupancy tensor is introduced: ,in, It is a three-dimensional occupancy tensor, which can be used to quickly calculate the AGV density and conflict frequency on any road section at any time, serving as the basic data structure for subsequent scheduling optimization.

[0074] Assume that in an intelligent warehousing system, there is a route segment R12, which is a shared channel that several transport tasks must pass through. The system needs to determine whether there is time overlap between multiple tasks on this route segment, thereby triggering resource locking or task scheduling adjustments.

[0075] Suppose there are two tasks:

[0076] By AGV Execution, plan on the path on the pass; By AGV Execution also requires a path The scheduling system records the following time occupancy:

[0077] Second;

[0078] Second;

[0079] According to the judgment rules: , we can see that the intersection of the two time segments is [108, 110], that is, there is a 2-second overlap, so: path segment Identified as a potential conflict segment;

[0080] The system needs to introduce a collaborative mechanism, such as setting up AGV Delay entry for 3 seconds , that is, staggered traffic, or set the section as a "mutually exclusive section" to allow only one AGV to pass at the same time; or enable a priority strategy (such as urgent orders are given priority).

[0081] Ultimately, the system generates a Multi-AGV Cooperative Scheduling Graph based on the scheduling graph and resource utilization tensor, integrating AGV behavior data with task path timing. This graph is used for overall scheduling strategy design and conflict management mechanism deduction. This graph not only preserves the task structure and resource dynamics but also embeds collaborative conflict annotations, making it an essential intermediate result for subsequent scheduling trade-off modeling and path optimization.

[0082] Step S3: Introduce path planning criteria (such as load balancing) and resource competition control mechanisms (such as avoidance priority), assign comprehensive scheduling weights to each feasible path and task allocation plan, and construct a multi-objective scheduling trade-off factor model.

[0083] To improve the scheduling system's adaptability to complex task environments and overall resource utilization efficiency, it is necessary to build a scheduling trade-off factor model with multi-objective optimization capabilities. First, path planning criteria such as load balancing, shortest-path, and deadline-aware strategies are introduced to guide the initial direction of task allocation. At the same time, the system considers resource competition control mechanisms, including yielding priority, mutual exclusion of segments, and energy-aware constraints, to avoid conflicts or resource overlap among AGVs on the path.

[0084] In order to quantitatively integrate the above scheduling objectives, a comprehensive scheduling weight function of paths and tasks is constructed. The comprehensive scheduling weight function of paths and tasks is constructed based on path distance and resource conflict cost to evaluate AGV The comprehensive scheduling cost of executing the task. The weight function is defined as follows: ,in, For AGV Execute the task Required path distance (Distance), For AGV Execute the task Conflict-Cost of resources, is the scheduling weight factor, where the resource conflict cost It can be further defined as: ,in, Indicates AGV On the path Execute tasks on The time interval, n is the number of paths, Indicates the task time interval of other AGVs on the same path, function is an indicator function that outputs 1 when the two time intervals intersect, otherwise it outputs 0. Indicates AGV On the path Execute tasks on time interval, represents the intersection of two time intervals, If the intersection of these two time intervals is not empty, that is, there is a time overlap, then the path is defined as a potential conflict segment, and a coordination mechanism needs to be introduced to lock resources or stagger tasks.

[0085] The system periodically calculates the path conflict frequency Average path delay , to dynamically adjust : ,in, Indicates the proportion of path conflicts in the current scheduling cycle; this setting is increased when conflicts are frequent. weights, enhancing the scheduling tendency towards conflict avoidance.

[0086] Using this weighting function, the system establishes a comparable scheduling scoring system for each AGV-task-path triplet, enabling scheduling strategies to achieve a controllable multi-objective trade-off between efficiency and safety. Ultimately, the resulting Multi-Objective-Scheduling-Trade-Off-Model provides a clear cost metric for subsequent path optimization and task assignment, serving as a key foundation for achieving a globally optimal scheduling solution.

[0087] Step S4: Use a graph optimization algorithm (such as improved A*) combined with a multi-objective scheduling trade-off factor model to solve the task path and output a set of task allocation and path planning solutions. The task allocation and path planning solutions record the task sequence, path nodes, expected execution time, and resource usage details of each AGV.

[0088] Based on the aforementioned multi-objective scheduling trade-off model, a graph optimization algorithm (such as the heuristically enhanced A* algorithm and the time-extended graph model) is employed to globally solve the path for each transport task, yielding a set of scheduling results that balance path optimality and resource coordination. This process not only focuses on the traditional shortest path but also incorporates scheduling costs, multi-vehicle interference, and resource conflicts into the optimization objectives, ultimately outputting a comprehensive task routing solution that is both executable and scheduling-stable.

[0089] Specifically, the warehouse scheduling environment is modeled as a directed weighted graph ,in is a set of spatial nodes (including storage locations, transfer stations, delivery points, etc.), is the set of traversable path edges. Each edge Assigned a scheduling cost , indicating AGV Execute the task through the edge The calculation method of the comprehensive scheduling cost required is based on the weight function in step S3.

[0090] Adoption Improvement The algorithm performs path search and heuristic function The definition is as follows:

[0091] ,in, is the total cost estimate of the current search node g, is the cumulative scheduling weight from the starting point to the current node, is the heuristic value of the minimum remaining cost from the current node to the target node, the heuristic value The minimum congestion guidance strategy can be used to dynamically guide the search away from the path hotspot area. , the system performs path search and completes task assignment at the same time, forming its task sequence set And the corresponding path node sequence K is the total number of tasks, and M is the number of path nodes.

[0092] Consider an automated guided vehicle (AGV) A1 in a smart warehousing system. It needs to travel from its current node S (the starting point) to its target node (the work point) to complete a transport task. The path includes multiple candidate nodes, and the system uses a modified A* algorithm for path planning to determine the optimal path with the lowest cost.

[0093] Assume the path is as follows:

[0094] S—A—B—E

[0095] \ /

[0096] C-D

[0097] The AGV currently starts from S and aims to reach E. When the scheduling system calculates the current candidate node B, it has the following information:

[0098] g(B)=10: the cumulative cost from the starting point S to B (may include path length, congestion cost, etc.); h(B)=4: the minimum estimated cost from B to the target E (based on the shortest remaining distance + traffic heat); then the total cost: f(B)=g(B)+h(B)=10+4=14. At the same time, the system also considers node D: g(D)=11, h(D)=2, then f(D)=13. At this time, the system will give priority to expanding node D because it has a smaller f(n) estimate, that is, the current total cost path is better.

[0099] Assume that the AGV is assigned a task sequence: , the system performs an improved A* search on the graph for each task and obtains the corresponding path node sequence:

[0100] ,in Indicates the total number of tasks, is the total number of all path nodes, and finally forms the complete execution path graph of the AGV.

[0101] In order to realize system operation simulation and scheduling conflict detection, the system also needs to record the expected execution time of each AGV's corresponding task path. , used for subsequent scheduling beat control and timing analysis; resource occupancy details, defined as the start and end time of each path occupied by the AGV , to support dynamic conflict detection. Among them, AGV The estimated execution time of a task can be calculated by normalizing the path cost as follows: ,in, For AGV The average running speed, Path edge The final output scheduling solution is a set of all AGV paths and task matching sets: ,in, represents the complete set of scheduling solutions, represents the i-th AGV, For AGV Assigned task sequence set, For AGV The path node sequence, Indicates AGV The expected task execution time, Indicates AGV A detailed resource usage breakdown is shown, where N is the number of AGVs. Each tuple in the set represents the complete scheduling path and task information for an AGV. Through this path optimization process, the system can efficiently search for routing solutions with minimal conflicts and optimal resource utilization within the scheduling graph, ensuring coordinated operation and dynamic response among AGVs in complex mission scenarios. This provides high-quality input for subsequent time-domain simulations and traffic pressure assessments.

[0102] Step S5: Load the task assignment and path planning scheme into the timeline, perform timing simulation on the path, and identify potential congestion points or resource conflict areas in the path. Based on the identification results, optimize some AGV paths (such as staggered driving, path reselection, and slow start) to minimize path conflicts.

[0103] The task allocation and path planning scheme generated in the previous step are embedded in the time dimension to form a dynamic execution sequence for multi-AGV scheduling, further constructing a scheduling timing simulation environment. This process uses the path node sequence, task execution time, and resource usage details as input. Each AGV's path segment, beat information, and resource requests are mapped to a unified timeline. A task allocation and path planning scheme (Path-Time-Graph) is then created for simulation analysis to identify potential congestion points and resource conflict areas, enabling dynamic optimization of the scheduling scheme.

[0104] First, the system constructs each path in the task allocation and path planning scheme The time occupation interval is defined by the formula as follows: ,in, For AGV On the path The occupied time interval on is the time when the AGV enters the path, The time of departure is determined by the AGV speed, path length and task beat parameters. Subsequently, the system performs time interval overlap judgment on all paths to identify whether there is a time and space overlap conflict between any two AGV paths. The judgment criteria are: ,in, Indicates that the i-th AGV is in the path segment The actual occupied time interval on Indicates that the jth AGV is in the path segment The actual occupied time interval on Indicates that the intersection is not empty, that is, there is overlap in the time intervals, that is, two AGVs have overlapping travel time intervals on the same path, indicating that there is a potential conflict. The system marks all paths that meet the above conditions as conflict-sensitive segments and further optimizes them. In order to quantify the congestion level of each path, the system introduces the time passage pressure index , which is used to describe the average AGV occupancy intensity on the path segment per unit time. The calculation formula is: , where S is the total simulation cycle time, N is the number of AGVs, Indicates AGV On the path The length of time a route is occupied. This indicator can be used to sort the traffic pressure levels of all conflict-sensitive sections, thereby locating bottleneck sections and high-risk conflict points in the system. For the identified conflicting paths and high-pressure traffic areas, the system implements a path conflict optimization strategy based on the simulation results, including:

[0105] Time-Shifted-Execution: Set time offsets for conflicting AGVs , delay its entry time to stagger the overlapping areas;

[0106] Re-Routing: Re-search for alternative paths in the dispatch graph, prioritizing avoiding the current high-voltage section;

[0107] Slow-Start-Control: Reduces the AGV's running speed at the initial start-up and dynamically adjusts the arrival rhythm of subsequent paths.

[0108] For example, off-peak travel can be achieved by modifying the entry time expression: ,in, is the adjusted entry time, A time offset is set for conflicting AGVs. After optimization is complete, the system re-evaluates the conflicts in task assignments and path planning solutions to verify whether the conflict-minimization goal has been achieved. This means reducing resource overlap and path crossing frequency in the system to below a set threshold without significantly increasing total execution time or path length.

[0109] Assume that in an intelligent warehousing system, there are three AGVs (numbered ), the scheduling system assigns them transportation tasks respectively. Assume that the path segment This is one of the main passages in the warehouse, shared by multiple tasks. The system needs to determine whether there is a traffic conflict on this path.

[0110] The scheduling system monitors each AGV on the path segment The actual travel times are as follows: The travel time interval is Second, The travel time interval is Second; The travel time interval is Seconds, according to the judgment formula: , we found that: and In the path segment The time overlap on is [12, 14], so , there is a conflict; and There is no overlap in time; and There is no overlap in time. Therefore, the system will mark the path segment It is a conflict-sensitive segment and enters the optimization phase. , set the scheduling period Seconds, the traffic pressure index is: , indicating that the traffic pressure on this route is high. The system will optimize the route based on the conflict area and pressure index, such as: The start time is delayed by 3 seconds and adjusted to [15, 19] to avoid overlap; or Change to path segment R6, use the spare channel, and reduce the pressure on R5; or Set to slow start to delay its entry time by reducing the initial speed.

[0111] This closed-loop simulation-optimization-verification process significantly enhances the robustness of the scheduling strategy in actual operation, improves the collaborative efficiency between AGVs, and lays a time-series data foundation for subsequent traffic pressure modeling and feedback scheduling control.

[0112] Step S6: Count the path load characteristics of each path during the scheduling cycle. The path load characteristics include the average AGV passage frequency and task density, and construct the path's time traffic pressure index. Combined with the task execution dynamic feedback parameters, which include data such as AGV passage time and scheduling delay feedback, the risk bottleneck section is identified to provide target area positioning for subsequent scheduling optimization. The time traffic pressure index and the actual AGV operating status are used as input. The scheduling stability and response efficiency are verified through multiple rounds of offline simulations, and the scheduling parameters are calibrated.

[0113] In step S6, the system conducts path load analysis and scheduling verification based on the actual operational performance of the scheduling plan to achieve stability assessment and parameter calibration of the scheduling strategy. This step first statistically analyzes the traffic behavior of each path during the scheduling cycle and extracts its path load characteristics, mainly including two key indicators: average AGV traffic frequency and task density distribution. This constructs a time-based traffic pressure index that comprehensively represents the path operation status and is used to identify high-risk bottleneck areas in the scheduling process.

[0114] Among them, the average AGV passage frequency Indicates the path The average number of times an AGV passes through during the entire scheduling cycle can be expressed as: ,in, For path The frequency of passage, is the total scheduling cycle time, is the number of AGVs, is the indicator function, when AGV Passing the path within the cycle When , the value is 1, otherwise it is 0. Task density The task coverage on the path is measured and defined as the total number of times a unit-length path is visited by tasks within the scheduling period. The specific calculation is as follows: ,in, For path The task density, is the physical length of the path, is the total number of tasks, Indicates a task Whether the path is involved.

[0115] Based on the above two characteristics, define the path Time traffic pressure index for:

[0116] ,in, and are the weight coefficients of the travel frequency and task density (usually determined according to the importance of the path). This indicator is used to comprehensively measure the load intensity of the path. For path The task density, For path frequency of passage.

[0117] The system calculates the average traffic frequency fluctuation coefficient of each route segment over multiple scheduling cycles. and task density fluctuation coefficient , and dynamically adjust the weight accordingly: ,If the frequency fluctuation is larger, the system pays more attention to its traffic influence; otherwise, the task density dominates.

[0118] At the same time, the system introduces task execution dynamic feedback parameters (Task-Execution-Feedback-Metrics) to extract the following information for each AGV from actual operation data:

[0119] Passing time : Indicates AGV Through the path The actual time taken;

[0120] Scheduling delay feedback : Indicates AGV The delay between the execution of a task and its scheduled execution.

[0121] Dynamic bottle pre-scoring to further define the path , combined with static passage pressure and dynamic feedback as follows: ,in, For path The average of all AGV transit times, is the average scheduling delay of all tasks associated with the path, is the feedback coefficient, which is used to adjust the proportion of dynamic performance in the score.

[0122] By counting historical scheduling cycles:

[0123] Calculate the mean and standard deviation of the transit time of all AGVs along the path, and divide the standard deviation by the mean to obtain the coefficient of variation of the transit time of all AGVs along the path.

[0124] Calculate the average scheduling delay and scheduling delay standard deviation of all tasks associated with the path, and divide the scheduling delay standard deviation by the average scheduling delay to obtain the scheduling delay variation coefficient;

[0125] Normalize the two and use them as the feedback coefficient: , where For path The coefficient of variation of the time it takes for all AGVs to pass through the vehicle is: For path The coefficient of variation of all AGV scheduling delays is automatically increased when the path performance fluctuates greatly. , pay more attention to traffic stability; when the scheduling delay fluctuates greatly, improve , pay more attention to scheduling timeliness.

[0126] high The value path will be marked as a risk bottleneck segment (Bottleneck-Segment), which will serve as the key intervention target for subsequent scheduling optimization. Ultimately, the system will input the time traffic pressure indicators of all paths and the actual operating status of the AGV into multiple rounds of offline simulation programs (Offline-Simulation-Engine) to simulate the operating performance under different scheduling parameters. The simulation objectives include:

[0127] The system ensures that path conflict frequency and latency fluctuations remain within acceptable ranges across multiple rounds of task execution. It also analyzes trends in average task completion time, AGV turnover rate, and resource utilization. Based on simulation output, the system automatically adjusts scheduling parameters, enabling calibration and adaptive optimization of scheduling model parameters, providing empirical input and a foundation for strategy enhancement for subsequent closed-loop scheduling control.

[0128] Step S7: Integrate the multi-AGV scheduling holographic dataset, which includes the task state map, the multi-AGV collaborative scheduling map, the AGV path optimization results and the scheduling simulation verification results, and build a task state-driven multi-AGV closed-loop scheduling scheme to realize the task loading-path generation-state feedback-path reconstruction loop control mode, thereby realizing efficient, robust and adaptive collaborative scheduling of multi-AGV systems in complex dynamic warehousing scenarios.

[0129] By integrating a multi-AGV holographic scheduling dataset (HSD), a closed-loop multi-AGV scheduling solution with task-state driven capabilities is constructed, implementing a closed-loop control mechanism for the entire process, from task input to scheduling output, and then to system feedback and path reconstruction. This dataset integrates core information from key aspects of the scheduling system, including: task state maps (representing task distribution and resource requirements), multi-AGV collaborative scheduling maps (representing the interaction between AGVs on paths and time), path optimization results (task allocation and path node sequences), and scheduling simulation verification results (reflecting scheduling execution efficiency and operational feedback data). Through the dynamic integration and updating of this dataset, the system can perceive state changes in real time during operation and quickly adapt scheduling strategies.

[0130] The closed-loop scheduling solution is centered around a task-state driven mechanism. Its essence lies in using task changes as triggers to link path selection and scheduling optimization, forming the following control loop:

[0131] Task loading → path generation → state feedback → path reconstruction, in which the task loading phase is composed of the task queue When a new task is triggered in the task state graph, the system obtains the spatial target, time constraint and execution priority of the current task from the task state graph, and calls the scheduling model accordingly.

[0132] The path generation phase combines the trade-off factor model with the collaborative scheduling graph to dynamically calculate the path scheduling cost: ,in, Indicates AGV At the moment The scheduling cost of the path selected for executing the task, Indicates AGV The path distance of the path selected to execute the task at time t, Indicates AGV The time traffic pressure of the path selected to execute the task at time t, It is a dynamically adjusted weighting coefficient that is updated in real time with system status feedback.

[0133] The system adjusts two weighted coefficients in real time based on the overall congestion level and traffic smoothness of the current path network: The current system average path traffic pressure: , let the ideal congestion tolerance upper limit be , the adjustment strategy is as follows: , when the overall traffic pressure is small, Higher weight (focus on efficiency); when the congestion level increases, Ascend (preferentially avoid high-voltage paths). The state feedback phase consists of operating data and simulation predictions. Real-time operating data includes the AGV's current node position, vehicle passing time, power changes, waiting delays, etc. Simulation predictions are based on bottleneck identification and efficiency analysis indicators output by the scheduling simulation verification module. Feedback data into the system can construct a state offset function: ,in, represents the state offset of the i-th AGV at time t, is the ideal state trajectory, The actual execution status. If the offset exceeds the set threshold, the path reconstruction mechanism is triggered. Re-evaluate whether the scheduling cost of the current path is still optimal. The system schedules the path based on the new cost. Re-search the path and generate a new task path sequence to ensure that the scheduling system can quickly converge to an effective scheduling solution when path conflicts, task mutations, or resource bottlenecks occur. Through this closed-loop mechanism, the scheduling system can achieve:

[0134] Efficiency: Dynamically optimize paths and task allocation without stopping operations;

[0135] Robustness: The system has the ability to quickly recover from emergencies such as AGV failure and channel blockage;

[0136] Adaptability: Continuously adjust scheduling parameters and priority strategies as task flows change.

[0137] Ultimately, this closed-loop scheduling strategy not only improves the overall system throughput efficiency and resource utilization, but also provides sustainable and scalable operation guarantees for multi-AGV scheduling in intelligent warehousing systems in multi-tasking, dynamic, and high-concurrency environments.

[0138] Example 3: The following is a typical application of the intelligent warehouse multi-AGV scheduling method in an actual industrial scenario, which helps to understand the role and value of each step in a real environment:

[0139] A national e-commerce company established a large-scale FMCG warehousing and distribution center at a logistics hub. The warehouse, spanning 20,000 square meters, is equipped with over 60 AGVs (automated guided vehicles), responsible for picking and delivering over 100,000 orders daily during peak periods. The warehousing system utilizes a dynamic scheduling model, achieving high concurrency, low latency, and zero congestion throughout the entire material flow process.

[0140] The warehousing center uses 3D modeling and IoT sensing devices to collect spatial data such as storage areas, main / auxiliary transportation channels, entry and exit ports, and picking platforms; at the same time, it collects the location, load, power, and task queues of 60 AGVs in real time, constructs a task status map, and provides dynamic input for the scheduling system.

[0141] The order system generates thousands of sorting tasks in real time, each consisting of "picking - moving - delivery - empty return." The system maps these tasks into a graph, constructing a three-dimensional model of tasks, paths, and nodes, annotating potential intersections such as main aisles and merging areas, and generating a multi-AGV collaborative scheduling graph for the current scheduling cycle.

[0142] The dispatch system considers factors such as route length, current traffic pressure, and the remaining AGV battery level to assign weights to tasks. For example, heavily loaded AGVs prioritize smooth routes, low-battery AGVs automatically avoid high-conflict areas, and urgent tasks prioritize avoiding busy areas. This forms a comprehensive dispatch weighting model.

[0143] The system uses an improved A* algorithm combined with scheduling weights to plan paths for all tasks and match them to AGVs. It automatically outputs each AGV's task sequence, path nodes, estimated completion time, and resource usage interval. Results are generated within 2 seconds, requiring no human intervention.

[0144] Mapping the route plan to the scheduling timeline revealed peak congestion between 9:30 AM and 10:00 AM, with dense AGV traffic on main channel R12 potentially causing congestion. The system automatically implemented staggered starts, detours, and slow starts for some AGVs to achieve avoidance optimization.

[0145] The system calculates the average travel frequency and task density of all route segments within the scheduling cycle. Combined with actual AGV transit times and task delays, it identifies three high-risk bottlenecks (R12, R19, and R27). Simulation analysis reveals that these areas impact overall throughput efficiency by 12%. Based on these simulation results, the system calibrates scheduling weights and automatically adjusts scheduling parameters for the next cycle.

[0146] By integrating task status graphs, scheduling graphs, path results, and verification data, the scheduling system forms a comprehensive multi-AGV scheduling dataset and implements a closed-loop control mechanism driven by task status. The system automatically updates status every 5 seconds, reconstructing paths and task assignments in real time. During peak periods, the system maintained a 99.3% undelayed execution rate and reduced the average AGV idle rate by 22%. The application results are summarized in the table below:

[0147]

[0148] This technical solution is particularly well-suited for multi-tasking, high-density, and dynamically changing smart warehousing environments. Whether it's e-commerce logistics, pharmaceutical distribution, or industrial finished product sorting, it can significantly improve the efficiency, stability, and intelligence of scheduling systems.

[0149] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0150] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-AGV scheduling method for intelligent warehousing, characterized by: The scheduling method comprises the following steps: Step S1: The collection end obtains the structured layout information of the warehouse factory and initializes the task state map based on the current operating status of the AGV cluster; Step S2: Mark the intersection and resource occupancy of AGVs on spatial paths and time resources to generate a multi-AGV collaborative scheduling map; Step S3: Assign comprehensive scheduling weights to each feasible path and task allocation scheme, and construct a multi-objective scheduling trade-off factor model; Step S4: Using a graph optimization algorithm combined with a multi-objective scheduling trade-off factor model to solve the task path, and outputting a task allocation and path planning solution; Step S5: Load the task assignment and path planning scheme into the timeline, perform timing simulation on the path, identify potential congestion points or resource conflict areas in the path, and optimize some AGV paths based on the identification results; Step S6: Count the time-traffic pressure index of each path within the scheduling period, use the time-traffic pressure index and the actual AGV operation status as input, and perform scheduling verification through multiple rounds of offline simulation; Step S7: Integrate the multi-AGV scheduling holographic dataset and build a multi-AGV closed-loop scheduling solution driven by task status.

2. The intelligent warehousing multi-AGV scheduling method according to claim 1, characterized in that: Perform timing simulation on the path to identify potential congestion points or resource conflict areas in the path, and optimize some AGV paths based on the identification results. This includes the following steps: Construct each path in the task allocation and path planning scheme Time interval ; The potential congestion point or resource conflict area judgment expression is: ,in, Indicates that the i-th AGV is in the path segment The actual occupied time interval on Indicates that the jth AGV is in the path segment The actual occupied time interval on All paths that meet the judgment expression are marked as conflict-sensitive sections, and the time traffic pressure index is introduced. , which is used to describe the average AGV occupancy intensity on the path segment per unit time, sort the traffic pressure levels of all conflict-sensitive segments according to the time traffic pressure index, and execute the path conflict optimization strategy based on the simulation results, including staggered driving, path reselection and soft start control.

3. The intelligent warehousing multi-AGV scheduling method according to claim 2, characterized in that: The time-traffic pressure index of each path within the scheduling period is calculated. The time-traffic pressure index and the actual AGV operation status are used as inputs. The scheduling verification is performed through multiple rounds of offline simulation, including the following steps: The average AGV passage frequency and task density The time-based traffic pressure index is obtained by weighted calculation; Introducing dynamic feedback parameters for task execution, extracting each AGV's transit time and scheduling delay feedback from actual operation data; The time-travel pressure indicators of all paths and the actual operating status of the AGV are input into multiple rounds of offline simulation programs to simulate the operating performance under different scheduling parameters.

4. The intelligent warehousing multi-AGV scheduling method according to claim 3 is characterized by: Assign a comprehensive scheduling weight to each feasible path and task allocation scheme, and build a multi-objective scheduling trade-off factor model, which includes the following steps: Based on path distance and resource conflict costs Construct a comprehensive scheduling weight function of paths and tasks for evaluation Execute the task The overall dispatching cost .

5. The intelligent warehousing multi-AGV scheduling method according to claim 4, characterized in that: The resource conflict cost Defined as: ,in, express On the path Execute tasks on The time interval, n is the number of paths, Indicates the task time interval of other AGVs on the same path, function is an indicator function that outputs 1 when the two time intervals intersect, otherwise it outputs 0. express On the path Execute tasks on time interval, represents the intersection of two time intervals, If the intersection of the two time intervals is not empty, that is, there is a time overlap, the path is defined as a potential conflict segment.

6. The intelligent warehousing multi-AGV scheduling method according to claim 5, characterized in that: The intersection and resource occupancy of AGVs in spatial paths and time resources are marked to generate a multi-AGV collaborative scheduling graph, which includes the following steps: Map the collected transport task queue to the constructed task state graph. Transport tasks include pickup, handling, and delivery. Decompose the transportation task process into task units ,in For the transport missions, is the i-th subtask step, and s is the number of subtask steps; Extracting the paths involved in task execution in space , and mapped to the spatial topology of the scheduling graph in the node dimension; In the time dimension, the task process is time-sliced ​​according to the task time window to form a three-dimensional scheduling diagram data body. , forming a three-dimensional mapping structure of task-path-node; In each path The time occupancy interval is defined above, and the resource occupancy tensor is introduced to describe the time domain competition relationship of AGV on system resources; Based on the scheduling graph and resource occupancy tensor, the AGV behavior data and task path timing are integrated to generate a multi-AGV collaborative scheduling graph.

7. The intelligent warehousing multi-AGV scheduling method according to claim 6, characterized in that: Scheduling diagram data body forming a three-dimensional structure , expressed as: ,in, Represents the set of spatial nodes in a three-dimensional scheduling graph, is the set of path edges, It is a time layer structure used to describe the time interval occupied by each task unit on the path.

8. The intelligent warehousing multi-AGV scheduling method according to claim 7, characterized in that: The data collection end obtains the structured layout information of the storage plant, including the spatial coordinates and capacity parameters of the storage sites, the topological structure and access constraints of the transportation paths, the resource scheduling priority and accessibility determination of the transfer nodes, and the operating capacity parameters of the operating platforms. Obtain the dynamic operating status data of the AGV cluster, including the current location coordinates, remaining power, current load weight, and task queue status of each AGV.

9. The intelligent warehousing multi-AGV scheduling method according to claim 8, characterized in that: The collection end obtains the structured layout information of the warehouse factory and initializes the task state map based on the current operating status of the AGV cluster, including the following steps: Combine structured layout information and operation status data to construct a task status graph, using a graph structure to represent the multiple relationships among AGVs, tasks, paths, and resources. Each node in the task state graph represents a scheduling element, and each edge represents the task transfer path or resource occupancy relationship; Task status graph Expressed as: ,in, Represents the node set in the graph, including AGV nodes, task nodes and resource nodes. Represents the set of edges between nodes, is the weight matrix.

10. An intelligent warehousing multi-AGV scheduling system, used to implement the scheduling method according to any one of claims 1 to 9, characterized in that: It includes graph generation module, solution output module, simulation verification module and scheduling solution construction module; Graph generation module: This module obtains the structured layout information of the warehouse factory, initializes the task state graph based on the current operating status of the AGV cluster, marks the intersection and resource occupation of AGVs in spatial paths and time resources, and generates a multi-AGV collaborative scheduling graph; Solution output module: Assigns comprehensive scheduling weights to each feasible path and task allocation solution, constructs a multi-objective scheduling trade-off factor model, uses a graph optimization algorithm combined with the multi-objective scheduling trade-off factor model to solve the task path, and outputs the task allocation and path planning solution; Simulation Verification Module: This module loads the task assignment and path planning scheme into the timeline, performs timing simulation on the path, identifies potential congestion points or resource conflict areas in the path, optimizes some AGV paths based on the identification results, calculates the time traffic pressure index of each path within the scheduling cycle, and uses the time traffic pressure index and the actual AGV operating status as input to perform scheduling verification through multiple rounds of offline simulation. Scheduling solution construction module: Integrate multi-AGV scheduling holographic data sets to build a multi-AGV closed-loop scheduling solution driven by task status.

Images