AGV scheduling method, device, medium, and product

Abstract

Provided in the present application are an AGV scheduling method, a device, a medium, and a product. The method comprises: on the basis of a scheduling objective of a target scheduling task in an AGV scheduling system, generating at least one candidate AGV scheduling scheme, which at least comprises at least one of path planning, task auction planning, traffic control planning, and scheduling strategy planning for the target scheduling task; simulating the at least one candidate AGV scheduling scheme by means of a digital twin model corresponding to the AGV scheduling system, so as to obtain a simulation result corresponding to each candidate AGV scheduling scheme; on the basis of the simulation result, determining an AGV scheduling scheme for the target scheduling task; and scheduling AGVs on the basis of the determined AGV scheduling scheme for the target scheduling task.

Description

AGV scheduling methods, equipment, media and products

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202510353394.7, filed on March 24, 2025, entitled "AGV Scheduling Method, Equipment, Media and Product", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of logistics processing, and in particular to an AGV scheduling method, equipment, medium and product. Background Technology

[0004] With the rapid development of industry and intelligent manufacturing, Automated Guided Vehicles (AGVs) have been widely used in logistics, manufacturing, warehousing, and other fields. AGVs significantly improve production efficiency and reduce labor costs through automated transportation. However, with the increasing number of AGVs and the increasing complexity of operating environments, how to efficiently and safely schedule AGVs has become a pressing issue.

[0005] Existing AGV scheduling systems typically use preset path planning and scheduling strategies to manage AGV operation. However, this approach is difficult to adapt to dynamically changing operating environments. Once the operating environment changes, such as the shelf position being adjusted or temporary obstacles appearing, the original path planning and scheduling strategies will no longer be applicable.

[0006] Therefore, there is an urgent need to propose a new AGV scheduling method to improve the reliability of AGV scheduling. Summary of the Invention

[0007] Based on the defects and shortcomings of the prior art, this application proposes an AGV scheduling method, equipment, medium and product that can improve the reliability of AGV scheduling.

[0008] According to a first aspect of the embodiments of this application, an AGV scheduling method is provided, the method comprising: generating at least one candidate AGV scheduling scheme based on the scheduling objective of a target scheduling task in the AGV scheduling system; the candidate AGV scheduling scheme including at least one of path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task; simulating the at least one candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain a simulation result corresponding to each candidate AGV scheduling scheme; determining the AGV scheduling scheme for the target scheduling task based on the simulation result; and scheduling AGVs according to the determined AGV scheduling scheme for the target scheduling task.

[0009] According to a second aspect of the present application, an electronic device is provided, comprising: a memory and a processor; the memory is connected to the processor and is used to store a program; the processor is used to implement the AGV scheduling method as described in the first aspect of the present application by running the program in the memory.

[0010] According to a third aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the AGV scheduling method as described in the first aspect of the present application.

[0011] According to a fourth aspect of the present application, a computer program product is provided, including computer program instructions that, when executed by a processor, cause the processor to implement the AGV scheduling method as described in the first aspect of the present application.

[0012] According to a fifth aspect of the embodiments of this application, a chip is provided, including a processor and a data interface, wherein the processor reads and runs a program stored in a memory through the data interface to execute the AGV scheduling method as described in any one of the first aspects of the embodiments of this application.

[0013] This application provides an AGV scheduling method, device, medium, and product. It generates at least one candidate AGV scheduling scheme based on the scheduling objective of a target scheduling task in the AGV scheduling system. Each candidate AGV scheduling scheme includes at least one of the following: path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task. The method simulates each candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each scheme. Based on the simulation results, the method determines the AGV scheduling scheme for the target scheduling task and schedules the AGVs according to the determined scheme. By utilizing a digital twin model corresponding to the AGV scheduling system to simulate each candidate AGV scheduling scheme generated based on the scheduling objective, and by determining the AGV scheduling scheme with performance indicators closest to the target based on the simulation results, the method adapts to dynamically changing operating environments, improving the reliability of AGV scheduling. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0015] Figure 1 is a flowchart illustrating the AGV scheduling method provided in an embodiment of this application;

[0016] Figure 2 is a flowchart illustrating an AGV scheduling scheme for determining target scheduling tasks based on simulation results, provided in an embodiment of this application.

[0017] Figure 3 is a flowchart illustrating an optimization method for optimizing task bidding planning provided in an embodiment of this application;

[0018] Figure 4 is a flowchart illustrating an optimization method for optimizing scheduling strategy planning provided in an embodiment of this application;

[0019] Figure 5 is a schematic diagram of the AGV scheduling device provided in the embodiment of this application;

[0020] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] First, the technical terms involved in the embodiments of this application will be explained:

[0023] Digital Twin Technology is a simulation process that integrates multiple disciplines, multiple physical quantities, multiple scales, and multiple probabilities. It reflects the entire life cycle of the corresponding physical equipment by completing mapping in virtual space.

[0024] AGV scheduling system: A software system used to manage and control the operation of Automated Guided Vehicles (AGVs). It achieves efficient, safe, and collaborative operation of AGV fleets through tasks such as task allocation, path planning, traffic control, and scheduling strategy planning, to meet material handling needs in production, warehousing, and logistics scenarios.

[0025] AGV path planning refers to planning a collision-free and safe travel path for an AGV from its starting point to its destination in the working environment, in order to achieve efficient and accurate material handling and other tasks. Commonly used path planning algorithms are the A* algorithm and the D* algorithm.

[0026] Task bidding rules: In scenarios involving multiple entities collaborating to complete a task, this provides an effective way to rationally allocate tasks and improve efficiency. In AGV scheduling, it determines which AGV will perform a specific task.

[0027] Traffic control for AGVs refers to the management and control of the AGV's path, speed, and stopping during operation to ensure its safe and efficient operation and avoid problems such as collisions and blockages.

[0028] AGV scheduling strategy: refers to the method of rationally allocating and controlling AGVs in an environment where multiple AGVs work together, in order to achieve efficient and stable material handling or other tasks.

[0029] AGV deadlock: In an AGV system, this refers to a situation where two or more AGVs are unable to move forward because they are waiting for each other to release resources (such as paths, loading / unloading stations, etc.), causing the entire system to come to a standstill. For example, if one AGV occupies a path, and another AGV also needs to traverse that path to complete its task, but the former cannot leave the path in time for some reason, while the latter is waiting for the former to leave, this creates a situation of mutual waiting, i.e., a deadlock. Deadlock severely impacts the operational efficiency and reliability of AGV systems, leading to problems such as production interruptions and material transport delays.

[0030] AGV deadlock resolution: refers to the process of taking a series of measures to break the deadlock state and restore the system to normal operation when a deadlock occurs in the AGV system.

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only one component of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0032] Before introducing the solution proposed in this application, the relevant technologies will first be introduced:

[0033] With the rapid development of industry and intelligent manufacturing, Automated Guided Vehicles (AGVs) are widely used in logistics, manufacturing, warehousing, and many other fields. Leveraging automated transportation capabilities, AGVs significantly improve production efficiency and reduce labor costs. However, with the continuous increase in the number of AGVs and the increasing complexity of operating environments, achieving efficient and safe scheduling of AGVs has become a critical challenge that urgently needs to be addressed.

[0034] Currently, most AGV scheduling systems on the market use preset path planning and scheduling strategies to manage AGV operation. However, this approach has significant shortcomings when facing dynamically changing operating environments. Once situations arise, such as rearrangement of shelving locations or unexpected temporary obstacles, the originally set path planning and scheduling strategies become ineffective. Therefore, there is an urgent need to propose a new AGV scheduling method to improve the reliability of AGV scheduling and better meet actual operational needs.

[0035] Based on this, embodiments of this application provide a novel AGV scheduling method, device, medium, and product. By generating at least one candidate AGV scheduling scheme according to the scheduling objective of the target scheduling task in the AGV scheduling system, each candidate AGV scheduling scheme includes at least path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task. Simulations are performed on at least one candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme. Based on the simulation results, the AGV scheduling scheme for the target scheduling task is determined. Because the candidate AGV scheduling schemes generated based on the scheduling objective are simulated using a digital twin model corresponding to the AGV scheduling system, and the AGV scheduling scheme with performance indicators closest to the scheduling objective is determined based on the simulation results and implemented, the formulated AGV scheduling scheme adapts to dynamically changing operating environments, improving the reliability of AGV scheduling.

[0036] The AGV scheduling method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0037] Exemplary methods

[0038] Figure 1 is a flowchart illustrating the AGV scheduling method provided in an embodiment of this application. Referring to Figure 1, in an exemplary embodiment, the provided AGV scheduling method may include the following steps 110 to 140:

[0039] Step 110: Generate at least one candidate AGV scheduling scheme based on the scheduling objective of the target scheduling task in the AGV scheduling system; the candidate AGV scheduling scheme includes at least one of the following: path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task. Step 120: Simulate at least one candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme. Step 130: Determine the AGV scheduling scheme for the target scheduling task based on the simulation results. Step 140: Schedule the AGVs according to the determined AGV scheduling scheme for the target scheduling task.

[0040] The AGV scheduling scheme is a series of plans and arrangements designed to achieve the scheduling objectives of the target scheduling task. The scheduling objectives of the target scheduling task may include improving handling efficiency, optimizing travel paths, real-time monitoring of AGV status, timely handling of faults, and coordinating multiple AGVs to work simultaneously to achieve efficient collaboration in order to meet the needs of large-scale production handling.

[0041] It should be understood that the specific scheduling template can be set according to the actual operation requirements, and this embodiment does not impose any specific limitations on it.

[0042] Among them, the candidate AGV scheduling scheme refers to the AGV scheduling scheme generated based on the scheduling target but not simulated by the digital twin model corresponding to the AGV scheduling system, while the output after simulation by the digital twin model is the final AGV scheduling scheme of the AGV scheduling system.

[0043] At least one candidate AGV scheduling scheme is a different AGV scheduling scheme that is generated based on the scheduling objective of the AGV scheduling system and is available for selection. Each AGV scheduling scheme may include at least one of the following in the AGV scheduling system for the target scheduling task: path planning, task bidding planning, traffic control planning, and scheduling strategy planning.

[0044] Path planning for target scheduling tasks involves planning the travel path for AGVs from the starting point to the target point. This requires considering factors such as obstacles, aisle width, and traffic rules in the working environment to ensure the AGVs can reach their destination safely and efficiently. For example, in a warehouse environment, it's necessary to plan how AGVs navigate through aisles between shelves to avoid collisions with other AGVs, shelves, or personnel.

[0045] Task bidding planning for target scheduling tasks is a type of task allocation mechanism. When there are multiple AGVs and multiple scheduling tasks, by setting task bidding rules, AGVs can "bid" for tasks based on their own status, such as location, battery level, and current task load. The scheduling system then allocates tasks to suitable AGVs based on the bidding results, thereby improving the rationality and efficiency of task allocation. For example, AGVs closer to the task start point and with fewer current tasks may have an advantage in the bidding and thus obtain tasks first.

[0046] Traffic control planning is essential for target scheduling tasks to ensure the orderly operation of multiple AGVs within the same work area. This includes establishing AGV driving rules, such as driving direction, priority, and yielding rules. For example, AGVs on main roads may be given priority, and traffic light-like mechanisms may be implemented at intersections to control the passage order of different AGVs, preventing traffic congestion and collisions.

[0047] The scheduling strategy for the target task determines the operation of the entire AGV scheduling system. Different scheduling strategies, such as first-come, first-served, shortest path first, and task priority-based scheduling, will have different impacts on the task allocation and execution order of AGVs. For example, when using a task priority scheduling strategy, urgent production tasks will be prioritized for AGV execution to meet urgent production needs.

[0048] Each candidate AGV scheduling scheme takes into account the above four aspects to form a complete AGV scheduling scheme for the target scheduling task, so as to adapt to complex and ever-changing AGV operation scenarios.

[0049] After generating at least one candidate AGV scheduling scheme based on the scheduling objective, the at least one candidate AGV scheduling scheme is simulated using a pre-built digital twin model corresponding to the AGV scheduling system. This simulates the operation of each candidate AGV scheduling scheme. If problems occur during the simulation, the candidate AGV scheduling scheme can be adjusted accordingly to ensure that the candidate AGV scheduling scheme can enable the AGV to complete the target scheduling task efficiently and stably in actual application.

[0050] The digital twin model is a precise mapping of the AGV scheduling system in a virtual environment. Specifically, when constructing the digital twin model, the operating environment model, path planning model, task bidding model, traffic control model, scheduling strategy model, and multiple AGV vehicle models of the AGV scheduling system can be built using digital twin technology. Furthermore, based on the spatial constraints and process coupling relationships between the operating environment model, the path planning model, the task bidding model, the traffic control model, the scheduling strategy model, and the multiple AGV vehicle models, the digital twin model of the AGV scheduling system is constructed. The spatial constraints refer to the spatial positional relationships between the models within the operating environment corresponding to the operating environment model, and the process coupling relationships refer to the association relationships between the models when executing the target scheduling task.

[0051] Specifically, digital twin technology is used to digitally model the actual physical environment in which the AGV scheduling system operates. For example, in a factory setting, the layout of the factory, the location of equipment, the placement of shelves, and the condition of aisles are presented in virtual digital form, providing basic spatial information for subsequent model building.

[0052] Based on the spatial information provided by the operating environment model, the AGV's travel route from the starting point to the destination is simulated and planned. Considering factors such as obstacle avoidance, shortest path selection, and traffic flow changes at different times, multiple possible path planning schemes are generated through algorithms, and simulated operation tests are conducted in digital space.

[0053] To rationally allocate tasks to different AGVs, a task bidding model is constructed. This model simulates the process of different AGVs bidding for tasks based on their own status (such as battery level, current position, remaining carrying capacity, etc.). The system sets bidding rules, such as bidding based on the estimated time and energy consumption to complete the task. The model simulates the bidding behavior of each AGV and the final task allocation result.

[0054] To simulate traffic control measures for AGVs in actual operations, AGV driving rules are formulated based on the channel layout in the operating environment model, such as one-way travel, traffic priority at intersections, and avoidance strategies. The model simulates how multiple AGVs operate in an orderly manner according to traffic control rules within the same area, avoiding collisions and congestion.

[0055] To simulate the impact of different scheduling strategies on AGV system operation, such as the first-come, first-served strategy where tasks are assigned to AGVs in the order they are received, and the priority-based strategy where high-priority tasks are assigned to suitable AGVs first, the model simulates task completion time, resource utilization, and other indicators under different strategies to provide a reference for the selection of actual scheduling strategies.

[0056] Simultaneously, each actual AGV is digitally modeled, including its physical parameters (size, weight, maximum speed, etc.), operational parameters (battery capacity, charging time, carrying capacity, etc.), and control parameters (acceleration, deceleration, steering angle range, etc.). Each AGV model possesses behaviors and state changes corresponding to the actual vehicle in digital space.

[0057] After constructing the operating environment model, path planning model, task bidding model, traffic control model, scheduling strategy model, and multiple AGV vehicle models of the AGV scheduling system, specific spatial relationships exist between each basic model (paths in the path planning model, AGV-task related positions in the task bidding model, rule-based areas in the traffic control model, AGV movement trajectories under the scheduling strategy model, and the positions of multiple AGV vehicle models) in the virtual space depicted by the operating environment model. These spatial relationships constitute spatial constraints. When constructing the digital twin model, these relationships are used to rationally arrange and integrate each basic model in the virtual space, ensuring the consistency of spatial logic between models.

[0058] During the execution of target scheduling tasks, there are close connections between the various basic models. For example, the path planning model plans the travel path for the AGV vehicle model, the task bidding model determines the tasks executed by the AGV vehicle model, the traffic control model constrains the AGV vehicle model's driving behavior on the path, and the scheduling strategy model influences task allocation and the AGV running order as a whole. The relationships between these models in the task execution process are called process coupling relationships. When constructing a digital twin model, the functions and operational logic of each basic model are linked and coordinated based on process coupling relationships, enabling the entire digital twin model to accurately simulate the dynamic operation process of the actual AGV scheduling system when executing tasks.

[0059] It is evident that the digital twin model of the AGV scheduling system constructed using digital twin technology can comprehensively and accurately simulate the operation of the actual system in a virtual environment, providing strong support for optimizing scheduling schemes and predicting potential problems.

[0060] The digital twin model of the established AGV scheduling system is used to simulate at least one candidate AGV scheduling scheme. The simulation results include the performance indicators corresponding to each candidate AGV scheduling scheme.

[0061] Specifically, during the simulation of each candidate AGV scheduling scheme, the system collects a series of metrics that reflect the effectiveness of the scheme's execution. These metrics may include the total time required to complete the target scheduling task, the total energy consumption of the AGVs, the accuracy of task completion (e.g., whether the goods are accurately moved to the designated location), and the number of collisions or blockages between AGVs. These performance metrics demonstrate the actual performance of each candidate scheme from different perspectives.

[0062] In determining the AGV scheduling scheme for the target scheduling task based on the simulation results, as shown in Figure 2, the specific implementation steps may include the following steps 210 to 230:

[0063] Step 210: Compare the performance indicators of each candidate AGV scheduling scheme with the scheduling target to obtain simulation results. Step 220: Based on the simulation results, determine a target candidate AGV scheduling scheme from the at least one candidate AGV scheduling scheme; the target candidate AGV scheduling scheme is the candidate AGV scheduling scheme whose performance indicators are closest to the scheduling target among the at least one candidate AGV scheduling schemes. Step 230: Optimize the target candidate AGV scheduling scheme based on an optimization algorithm to obtain the AGV scheduling scheme of the AGV scheduling system.

[0064] In step 210, the performance indicators of each candidate AGV scheduling scheme need to be compared and analyzed one by one with the pre-set scheduling targets. The scheduling targets are expected results determined based on actual business needs, such as expecting the task completion time to be within a certain threshold, minimizing energy consumption, and achieving 100% task completion accuracy. This comparison clearly shows the extent to which each candidate scheme meets the scheduling targets, thus obtaining the corresponding simulation results. For example, if candidate scheme A completes the task in 30 minutes, while the scheduling target requires completion within 25 minutes, then the comparison clearly shows the gap between scheme A and the target in terms of time performance.

[0065] In step 220, based on the simulation results obtained in step 210, the scheme with the performance indicators closest to the scheduling target is selected from all candidate AGV scheduling schemes and determined as the target candidate AGV scheduling scheme. This means that this scheme, considering all performance indicators, is most likely to meet the actual business requirements for AGV scheduling. For example, among multiple candidate schemes, scheme B has a task completion time close to the target time, relatively ideal energy consumption, and a high task completion accuracy. Compared with other schemes, its overall performance indicators are closest to the scheduling target, so scheme B is determined as the target candidate AGV scheduling scheme.

[0066] In step 230, although the target candidate AGV scheduling scheme performs best among many candidate schemes, there may still be some areas for improvement. At this point, optimization algorithms are used for further optimization. Optimization algorithms can be various mathematical optimization methods, such as genetic algorithms and particle swarm optimization algorithms. These algorithms attempt to find better solutions by adjusting and searching the parameters of the target candidate scheme. For example, by using a genetic algorithm to adjust the AGV's travel path planning parameters and task allocation rules in the target candidate scheme, the performance indicators of the scheme can be further improved, ultimately obtaining an AGV scheduling scheme suitable for the AGV scheduling system to better meet the complex needs of actual production and logistics scenarios.

[0067] According to the technical solution of this embodiment, by simulating, comparing, screening and optimizing candidate AGV scheduling schemes, it is ensured that the final determined AGV scheduling scheme can efficiently and reliably complete the target scheduling task, thereby improving the overall performance of the AGV scheduling system.

[0068] To optimize path planning in the target candidate AGV scheduling scheme, this embodiment specifically utilizes the path planning model to obtain operational environment awareness information and risk assessment results. Based on the operational environment awareness information and the risk assessment results, the path planning for the target scheduling task is optimized in real time.

[0069] Specifically, the path planning model can acquire environmental awareness information by utilizing various sensor data (such as distance information of surrounding objects detected by LiDAR and environmental image information captured by vision sensors). This information can reflect the real-time status of the AGV's environment, such as whether new equipment has been placed in the channel and the real-time positions of other AGVs. By analyzing the environmental awareness information, the path planning model can provide risk assessment results. For example, it can determine the degree of congestion risk in a certain area of ​​the current travel path and the probability of collision with other objects based on the acquired information.

[0070] Subsequently, based on the operational environment awareness information and risk assessment results, real-time optimization of the path planning for the target scheduling task can be achieved. In practical applications, real-time path planning can include path optimization for the appearance of new obstacles, as well as predictive planning based on historical data.

[0071] Specifically, for path optimization when new obstacles appear, the AGV model's travel path can be replanned when a new obstacle is detected on the path of the AGV model executing the target scheduling task. For predictive planning based on historical data, the future positions of obstacles on the AGV model's travel path can be predicted based on historical path planning data corresponding to the target scheduling task, thus enabling predictive planning of the AGV model's travel path.

[0072] In some cases, when an AGV (Automated Guided Vehicle) model detects a new obstacle on its path while performing a target scheduling task, the path planning model needs to recalculate the AGV's path to ensure it can continue to complete the task safely and efficiently. For example, in a warehouse environment, if a worker suddenly places a box of goods on the AGV's original path, the path planning model will use the new environmental perception information to avoid the obstacle and recalculate a new path from the current location to the target location, ensuring the AGV can successfully bypass the obstacle and reach its destination.

[0073] The path planning model can also predict the future locations of obstacles on the AGV's travel path based on historical path planning data corresponding to the target scheduling task. For example, during fixed periods each day, goods handling operations are frequent in a certain area, and past data shows that goods may be temporarily piled up in that area during those periods. The path planning model can predict in advance the possible appearance of obstacles in that area at a future point in time based on these historical patterns. Based on this prediction, predictive planning of the AGV's travel path can be performed, adjusting the travel path in advance to avoid forced interruptions or replanning of the path due to temporary obstacles during travel, thereby improving overall scheduling efficiency and operational stability.

[0074] In order to optimize the task bidding planning in the target candidate AGV scheduling scheme, as shown in Figure 3, the optimization process in this embodiment may include the following steps 310 to 350:

[0075] Step 310: Upon receiving a new scheduling task, obtain the task characteristics of the new scheduling task through the task bidding model, and set a priority for the new scheduling task. Step 320: Publish the task information of the new scheduling task through the task bidding model. Step 330: Receive the bidding value calculated by each AGV model in the operating environment based on its own state and the task information through the task bidding model. Step 340: Determine the AGV model to execute the new scheduling task based on the bidding value and bidding rules through the task bidding model. Step 350: Optimize the task bidding plan for the target scheduling task in real time based on the task information of the new scheduling task and the AGV model to execute the new scheduling task.

[0076] Specifically, when the AGV scheduling system receives a new scheduling task, the task bidding model first obtains the task's characteristics. These characteristics may include the urgency of the task (e.g., whether it is a material handling task urgently needed by the production line), the complexity of the task (e.g., whether the goods being handled require special handling methods or equipment), and the workload of the task (the quantity or weight of the goods being handled). Based on these task characteristics, a priority is assigned to the new scheduling task. Urgent and important scheduling tasks are given higher priority so that they are processed first in subsequent task allocation.

[0077] Next, the task bidding model publishes the task information for the new scheduling task. This information, in addition to task characteristics and priority, may also include the starting position, target position, and estimated completion time of the scheduling task. The purpose of publishing task information is to enable each AGV model in the operating environment to obtain relevant information so that they can perform subsequent bidding operations based on their own status.

[0078] After receiving task information, each AGV model in the operating environment calculates its bidding value based on its own status (such as current position, battery level, whether it is currently performing other tasks, and the progress of its task) and task information. For example, an AGV that is closer to the task's starting position, has a lighter current task load, and sufficient battery power may offer a relatively higher bidding value, indicating that it is more capable and willing to perform the task. Each AGV feeds back its calculated bidding value to the task bidding model.

[0079] The task bidding model determines the AGV (Automated Guided Vehicle) model to execute a new scheduled task based on the received bid value and pre-defined bidding rules. The bidding rules may comprehensively consider factors such as task priority and bid value. For example, for high-priority tasks, AGVs with higher bid values ​​are selected first; for medium-priority tasks, under certain conditions, the AGV with the best bid value is selected. In this way, tasks are assigned to the most suitable AGV to improve task execution efficiency and effectiveness.

[0080] Subsequently, based on the task information of the new scheduling task and the AGV vehicle model used to execute the new scheduling task, the task bidding plan for the target scheduling task is optimized in real time.

[0081] In the process of real-time optimization of task bidding rules, the scheduling effect under different bidding rules can be predicted based on historical task bidding planning data corresponding to the target scheduling task, the task information of the new scheduling task, and the AGV vehicle model used to execute the new scheduling task. Based on the scheduling effect, the bidding rules are dynamically optimized to determine the AGV vehicle model used to execute the new scheduling task based on the optimized bidding rules.

[0082] In other words, to further optimize task bidding planning, the AGV scheduling system uses historical task bidding planning data corresponding to the target scheduling task, combined with the task information of the new scheduling task and the AGV model determined to execute the new scheduling task, to predict the scheduling effect under different bidding rules. Historical task bidding planning data includes information such as the bidding situation of similar tasks in the past, task allocation results, and final execution effects. By analyzing this data, the system simulates the possible operational results of the new scheduling task and the entire AGV scheduling system under different bidding rules, such as changes in task completion time, AGV utilization rate, and energy consumption.

[0083] Based on the predicted scheduling effects under different bidding rules, the AGV scheduling system dynamically optimizes the bidding rules. For example, if the prediction results indicate that the current bidding rules will lead to overworked AGVs in some areas while idle AGVs in others, the AGV scheduling system may adjust the bidding rules, such as by adding consideration to the current distribution of AGV locations, guiding a more balanced task allocation. The optimized bidding rules will be used for the allocation of subsequent new tasks, including re-determining the AGV model used to execute the current new scheduling task, in order to continuously improve the performance and efficiency of the entire AGV scheduling system and better adapt to dynamically changing task requirements and operating environments.

[0084] To optimize path planning in the target candidate AGV scheduling scheme, in this embodiment, the AGV's operating trajectory and traffic flow can be obtained through the traffic control model. Based on the operating trajectory and traffic flow, the path planning for the target scheduling task is optimized in real time.

[0085] Specifically, the traffic control model uses the positioning devices (such as laser positioning and visual positioning) and communication systems carried by the AGVs themselves to obtain the location information of each AGV model in real time during operation, and then generates its running trajectory. These running trajectories reflect the movement path of the AGV models at different points in time, and can intuitively show the travel route of the AGV models in the operating environment.

[0086] By statistically analyzing data such as the number of AGV (Automated Guided Vehicle) models in each area and the frequency of their passage through a certain road segment, traffic control models can calculate traffic flow at different times and on different road segments. For example, in areas of a warehouse where goods are frequently moved, the traffic flow in that area can be determined by statistically analyzing the number of AGV models passing through that area per unit time.

[0087] Based on the acquired operational trajectory and traffic flow data, the traffic control model can perform analysis. If, on a certain road segment, the operational trajectories of a large number of AGV models intersect or converge, and the traffic flow on that segment remains at a high level, then that road segment is likely to become a potential congestion point. Conversely, when the operational trajectories of different AGV models have a high probability of intersecting in certain areas, and this intersection may lead to collisions or mutual obstruction, these areas are designated as conflict zones. For example, in a narrow passage in a warehouse where multiple AGV operational trajectories converge, and a large number of AGV models pass through per unit time, this passage is identified as a potential congestion point and conflict zone.

[0088] After identifying potential congestion points and conflict areas through analysis, the path planning for the target scheduling task can be optimized in real time. Specifically, potential congestion points and conflict areas in the operating environment can be determined based on the operating trajectory and traffic flow. Based on historical traffic control data corresponding to the target scheduling task, as well as the potential congestion points and conflict areas, the operating trend of the AGV model is predicted, enabling predictive traffic control of the AGV model.

[0089] In other words, by combining historical traffic control data corresponding to the target scheduling task, which includes information such as traffic conditions, the time and location of congestion, conflict situations, and corresponding handling measures and results in similar past scenarios, the traffic control model combines this data with currently identified potential congestion points and conflict areas. Through data analysis and model prediction, it forecasts the operating trends of the AGV (Automated Guided Vehicle) model. For example, based on historical data, it is found that the operating speed of the AGV model near a potential congestion point decreases significantly during specific times of the day. Combining this with the current traffic flow and operating trajectory in that area, it is predicted that the operating speed of the AGV model in that area will also decrease during similar times in the future, potentially leading to more severe congestion.

[0090] Based on the predicted operational trends of the AGV (Automated Guided Vehicle) models, the traffic control model proactively manages traffic for these models. For example, for predicted congestion points, the model adjusts the routes of relevant AGV models in advance, guiding them to avoid congested areas. For areas where conflicts may occur, the model avoids conflicts by setting traffic priorities and adjusting the departure times of the AGV models. For instance, if it predicts that a certain intersection may become congested in 10 minutes, the traffic control model sends instructions to AGV models approaching that intersection, instructing them to choose alternative routes. This achieves predictive traffic control for the AGV models, improving the operational efficiency and safety of the entire AGV scheduling system.

[0091] In order to optimize the scheduling strategy planning in the target candidate AGV scheduling scheme, as shown in Figure 4, the optimization process may include the following steps 410 to 440:

[0092] Step 410: Obtain operational data from the operating environment using the scheduling strategy model. Step 420: Based on the operational data, determine potential deadlock modes. Step 430: Based on the potential deadlock modes, determine the risk level of deadlock in the AGV scheduling system. Step 440: When the risk level is high, optimize the scheduling strategy planning.

[0093] Specifically, the scheduling strategy model collects various operational data from the AGV scheduling system's operating environment. This data includes, but is not limited to, the real-time location, speed, current task status (whether a task is being executed, task progress, etc.), and resource occupancy on each path (which paths are being used by AGVs, which paths are idle). Through this operational data, the scheduling strategy model can gain a comprehensive understanding of the system's operational status.

[0094] Based on the acquired operational data, the scheduling strategy model analyzes and processes the data to identify potential deadlock patterns. For example, a deadlock may occur when multiple AGV models are waiting for each other's path resources, forming a circular waiting state. The scheduling strategy model uses algorithms and logical judgments to identify such potential circular waiting or other situations that may lead to deadlock in the system, thus determining the potential deadlock patterns.

[0095] Based on the identified potential deadlock patterns, the scheduling strategy model further assesses the likelihood of deadlock in the AGV scheduling system and determines the corresponding risk level. Risk levels can be categorized as low, medium, and high. For example, if only occasional minor deadlock-prone situations occur that can be avoided with simple adjustments, the risk level might be classified as low. However, if multiple severe potential deadlock patterns exist and are interconnected, easily triggering large-scale deadlocks, the risk level would be classified as high.

[0096] When the identified risk level is high, it indicates a greater likelihood of deadlock in the AGV scheduling system. To reduce the probability of deadlock, the scheduling strategy needs to be optimized. Optimization methods may include adjusting the task allocation strategy to prevent multiple AGV models from competing for the same critical path resource simultaneously; and changing the driving rules of the AGV models, such as setting more reasonable priorities or avoidance mechanisms, to reduce the possibility of conflicts and circular waiting.

[0097] In one embodiment, for a deadlock that has already occurred, this embodiment also provides a method to dynamically resolve the deadlock. Specifically, when a deadlock is detected, the AGVs and path resources affected by the deadlock are determined. Based on the AGVs and path resources affected by the deadlock, the scheduling strategy is dynamically adjusted. According to the dynamically adjusted scheduling strategy, the deadlock resolution operation is performed through the AGV scheduling system.

[0098] Specifically, when a deadlock is detected, the first step is to determine which AGV models are affected by the deadlock and which path resources are occupied by these AGVs, leading to the deadlock. For example, by using monitoring systems and operational data records, it can be determined which specific AGV models are in a deadlocked state and which path resources they are occupying.

[0099] Based on the identified AGV models and path resources affected by deadlock, the scheduling strategy is dynamically adjusted. This may include reallocating tasks to other available AGV models, releasing occupied path resources; changing the travel paths of AGV models to avoid deadlock areas; or adjusting the priority relationships between AGV models to break deadlock cycles, etc.

[0100] Based on the dynamically adjusted scheduling strategy, the AGV scheduling system sends instructions to the affected AGV models to perform deadlock resolution operations. For example, some AGV models may be instructed to reverse or change their direction of travel to release the occupied paths, allowing other AGV models to continue running, ultimately resolving the deadlock and restoring the system to normal operation.

[0101] According to the technical solution of this embodiment, the AGV scheduling system can detect and handle deadlock problems in a timely manner during operation, thereby improving the stability and reliability of the system.

[0102] It should be noted that the solution in this embodiment also provides a monitoring center to display the real-time operating status of the digital twin model, facilitating decision support for management personnel. Furthermore, the monitoring center provides an intuitive user interface, allowing operators to monitor the status of the AGV model, deadlock risks, and deadlock resolution processes through this interface.

[0103] Exemplary device

[0104] Accordingly, this application also provides an apparatus, as shown in FIG5. The AGV scheduling apparatus 500 provided in this embodiment may include: a generation module 510, a simulation module 520, a determination module 530, and a scheduling module 540.

[0105] The generation module 510 is used to generate at least one candidate AGV scheduling scheme based on the scheduling target of the target scheduling task in the AGV scheduling system; the candidate AGV scheduling scheme includes at least one of the following: path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task.

[0106] The simulation module 520 is used to simulate at least one of the candidate AGV scheduling schemes using a digital twin model corresponding to the AGV scheduling system, so as to obtain the simulation results corresponding to each candidate AGV scheduling scheme.

[0107] The determination module 530 is used to determine the AGV scheduling scheme for the target scheduling task based on the simulation results.

[0108] The scheduling module 540 is used to schedule AGVs according to the determined AGV scheduling scheme of the target scheduling task.

[0109] In some exemplary embodiments, the simulation results include performance metrics corresponding to each of the candidate AGV scheduling schemes. Specifically, the simulation module 520 can be used to compare the performance metrics of each candidate AGV scheduling scheme with the scheduling target to obtain simulation results. Based on the simulation results, a target candidate AGV scheduling scheme is determined from the at least one candidate AGV scheduling scheme; the target candidate AGV scheduling scheme is the candidate AGV scheduling scheme whose performance metrics are closest to the scheduling target among the at least one candidate AGV scheduling schemes. The target candidate AGV scheduling scheme is optimized based on an optimization algorithm to obtain the AGV scheduling scheme of the AGV scheduling system.

[0110] In some exemplary embodiments, the apparatus further includes a construction module for constructing, based on digital twin technology, an operating environment model, a path planning model, a task bidding model, a traffic control model, a scheduling strategy model, and multiple AGV vehicle models of the AGV scheduling system. The module also constructs a digital twin model of the AGV scheduling system based on the spatial constraints and process coupling relationships between the operating environment model, the path planning model, the task bidding model, the traffic control model, the scheduling strategy model, and the multiple AGV vehicle models. The spatial constraints refer to the spatial positional relationships between the models within the operating environment corresponding to the operating environment model, and the process coupling relationships refer to the association relationships between the models when executing the target scheduling task.

[0111] In some exemplary embodiments, the simulation module 520 is specifically used to obtain operational environment awareness information and risk assessment results through the path planning model. Based on the operational environment awareness information and the risk assessment results, the path planning for the target scheduling task is optimized in real time.

[0112] In some exemplary embodiments, the simulation module 520 is specifically used to replan the travel path of the AGV vehicle model when a new obstacle is detected on the travel path of the AGV vehicle model performing the target scheduling task; or, based on historical path planning data corresponding to the target scheduling task, predict the future position of the obstacle on the travel path of the AGV vehicle model to perform predictive planning of the travel path of the AGV vehicle model.

[0113] In some exemplary embodiments, the simulation module 520 is specifically configured to, upon receiving a new scheduling task, obtain the task characteristics of the new scheduling task through the task bidding model, and set a priority for the new scheduling task. It also publishes the task information of the new scheduling task through the task bidding model. Furthermore, it receives the bidding value calculated by each AGV vehicle model in the operating environment based on its own state and the task information through the task bidding model. Finally, it determines the AGV vehicle model to execute the new scheduling task based on the bidding value and bidding rules through the task bidding model. Based on the task information of the new scheduling task and the AGV vehicle model to execute the new scheduling task, it performs real-time optimization of the task bidding plan for the target scheduling task.

[0114] In some exemplary embodiments, the simulation module 520 is specifically used to predict the scheduling effect under different bidding rules based on historical task bidding planning data corresponding to the target scheduling task, the task information of the new scheduling task, and the AGV vehicle model used to execute the new scheduling task. Based on the scheduling effect, the bidding rules are dynamically optimized to determine the AGV vehicle model used to execute the new scheduling task based on the optimized bidding rules.

[0115] In some exemplary embodiments, the simulation module 520 is specifically used to obtain the AGV's operating trajectory and traffic flow through the traffic control model. Based on the operating trajectory and traffic flow, the path planning for the target scheduling task is optimized in real time.

[0116] In some exemplary embodiments, the simulation module 520 is specifically used to determine potential congestion points and conflict areas in the operating environment based on the operating trajectory and the traffic flow. Based on historical traffic control data corresponding to the target scheduling task, and the potential congestion points and conflict areas, the simulation module predicts the operating trend of the AGV model to perform predictive traffic control on the AGV model.

[0117] In some exemplary embodiments, the simulation module 520 is specifically used to acquire operational data in the operating environment through the scheduling strategy model. Based on the operational data, potential deadlock modes are determined. According to the potential deadlock modes, the risk level of deadlock in the AGV scheduling system is determined. When the risk level is high, the scheduling strategy planning is optimized.

[0118] In some exemplary embodiments, the simulation module 520 is further configured to, upon detecting a deadlock, determine the AGVs and path resources affected by the deadlock. Based on the AGVs and path resources affected by the deadlock, the scheduling strategy plan is dynamically adjusted. According to the dynamically adjusted scheduling strategy plan, a deadlock resolution operation is performed through the AGV scheduling system.

[0119] The AGV scheduling device provided in this embodiment belongs to the same concept as the AGV scheduling method provided in the above embodiments of this application. It can execute the AGV scheduling method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the AGV scheduling method. Technical details not described in detail in this embodiment can be found in the specific processing content of the AGV scheduling method provided in the above embodiments of this application, and will not be repeated here.

[0120] It should be understood that the modules in the above device can be implemented by a processor calling software. For example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit of the device. The processor can be a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. By designing the hardware circuits, some or all of the unit functions can be implemented. The hardware circuits can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented by a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files to implement the functions of some or all of the above units. All units of the above device can be implemented entirely by a processor calling software, entirely by hardware circuits, or partially by a processor calling software with the remaining parts implemented by hardware circuits.

[0121] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or DSP. In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0122] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0123] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0124] Exemplary electronic devices

[0125] This application provides an electronic device, as shown in FIG6, which includes a memory 600 and a processor 610 connected to the memory 600.

[0126] The memory 600 is used to store programs.

[0127] The processor 610 is configured to execute any of the AGV scheduling methods described in any of the above embodiments, generating at least one candidate AGV scheduling scheme based on the scheduling objective of the target scheduling task in the AGV scheduling system; the candidate AGV scheduling scheme includes at least one of path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task; simulating at least one candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme; determining the AGV scheduling scheme for the target scheduling task based on the simulation results; and scheduling AGVs according to the determined AGV scheduling scheme for the target scheduling task. Because the candidate AGV scheduling schemes generated based on the scheduling objective are simulated using a digital twin model corresponding to the AGV scheduling system, and the AGV scheduling scheme with the performance indicators closest to the scheduling objective is determined based on the simulation results and implemented, the formulated AGV scheduling scheme adapts to dynamically changing operating environments, improving the reliability of AGV scheduling.

[0128] For details on the specific processing procedure of the processor 610 described above, please refer to the description of the above method embodiments. For details on the specific implementation of the processor 610, please refer to the description of the above embodiments.

[0129] Specifically, the aforementioned electronic device may also include: a bus, a communication interface 620, an input device 630, and an output device 640.

[0130] The processor 610, memory 600, communication interface 620, input device 630, and output device 640 are interconnected via a bus. Among them:

[0131] A bus can include a pathway for transmitting information between various components of a computer system.

[0132] The processor 610 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0133] The processor 610 may include a main processor, as well as a baseband chip, modem, etc.

[0134] The memory 600 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 600 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0135] Input device 630 may include a device for receiving user input data and information, such as an error microphone, keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0136] Output device 640 may include devices that allow information to be output to a user, such as a speaker, display screen, printer, etc.

[0137] The communication interface 620 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0138] The processor 610 executes the program stored in the memory 600 and calls other devices, which can be used to implement the various steps of any of the AGV scheduling methods provided in the above embodiments of this application.

[0139] This application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored in the memory through the data interface to execute the AGV scheduling method described in any of the above embodiments. For the specific processing procedure and its beneficial effects, please refer to the above embodiments of the AGV scheduling method.

[0140] Exemplary computer program products and storage media

[0141] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the AGV scheduling methods according to various embodiments of this application as described in any of the above embodiments of this specification.

[0142] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0143] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor using the steps of the AGV scheduling method according to various embodiments of this application described in any of the above embodiments of this specification. Specifically, the following steps can be implemented:

[0144] Step 110: Generate at least one candidate AGV scheduling scheme based on the scheduling objective of the target scheduling task in the AGV scheduling system; the candidate AGV scheduling scheme includes at least one of the following: path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task. Step 120: Simulate at least one candidate AGV scheduling scheme using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme. Step 130: Determine the AGV scheduling scheme for the target scheduling task based on the simulation results. Step 140: Schedule the AGVs according to the determined AGV scheduling scheme for the target scheduling task.

[0145] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are merely several embodiments of this application, and the actions and modules involved are not necessarily essential to this application.

[0146] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0147] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0148] The modules and sub-modules in the various embodiments of the present application's devices and terminals can be merged, divided, and deleted according to actual needs.

[0149] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0150] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0151] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0152] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0153] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0154] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0155] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An AGV scheduling method, characterized in that, The method includes: Based on the scheduling objective of the target scheduling task in the AGV scheduling system, at least one candidate AGV scheduling scheme is generated; the candidate AGV scheduling scheme includes at least one of the following: path planning, task bidding planning, traffic control planning, and scheduling strategy planning for the target scheduling task. At least one of the candidate AGV scheduling schemes is simulated using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme. Based on the simulation results, the AGV scheduling scheme for the target scheduling task is determined; The AGVs are scheduled according to the determined AGV scheduling scheme for the target scheduling task.

2. The method according to claim 1, characterized in that, The simulation results include the performance metrics corresponding to each of the candidate AGV scheduling schemes. The step of determining the AGV scheduling scheme for the target scheduling task based on the simulation results includes: The performance metrics of each candidate AGV scheduling scheme are compared with the scheduling target to obtain simulation results; Based on the simulation results, a target candidate AGV scheduling scheme is determined from the at least one candidate AGV scheduling scheme; the target candidate AGV scheduling scheme is the candidate AGV scheduling scheme whose performance index is closest to the scheduling target among the at least one candidate AGV scheduling schemes. The target candidate AGV scheduling scheme is optimized based on the optimization algorithm to obtain the AGV scheduling scheme of the AGV scheduling system.

3. The method according to claim 2, characterized in that, Before simulating at least one of the candidate AGV scheduling schemes using a digital twin model corresponding to the AGV scheduling system to obtain simulation results for each candidate AGV scheduling scheme, the method further includes: Based on digital twin technology, an operating environment model, a path planning model, a task bidding model, a traffic control model, a scheduling strategy model, and multiple AGV vehicle models are constructed for the AGV scheduling system. Furthermore, based on the spatial constraints and process coupling relationships among the operating environment model, the path planning model, the task bidding model, the traffic control model, the scheduling strategy model, and the multiple AGV vehicle models, a digital twin model of the AGV scheduling system is constructed. The spatial constraints refer to the spatial positional relationships between the models within the operating environment corresponding to the operating environment model, and the process coupling relationships refer to the association relationships between the models when executing the target scheduling task.

4. The method according to claim 3, characterized in that, The optimization of the target candidate AGV scheduling scheme based on the optimization algorithm includes: The path planning model is used to obtain operational environment awareness information and risk assessment results. Based on the operational environment awareness information and the risk assessment results, the path planning for the target scheduling task is optimized in real time.

5. The method according to claim 4, characterized in that, The real-time optimization of the path planning for the target scheduling task includes: When a new obstacle is detected on the travel path of the AGV model executing the target scheduling task, the travel path of the AGV model is replanned; or, Based on historical path planning data corresponding to the target scheduling task, the future positions of obstacles on the AGV vehicle model's driving path are predicted to perform predictive planning of the AGV vehicle model's driving path.

6. The method according to claim 3, characterized in that, The optimization of the target candidate AGV scheduling scheme based on the optimization algorithm includes: When a new scheduling task is received, the task characteristics of the new scheduling task are obtained through the task bidding model, and a priority is set for the new scheduling task. The task information of the new scheduling task is published through the task bidding model; The task bidding model receives the bidding value calculated by each AGV vehicle model in the operating environment based on its own status and the task information. The AGV vehicle model for executing the new scheduling task is determined based on the bidding value and bidding rules through the task bidding model. Based on the task information of the new scheduling task and the AGV vehicle model used to execute the new scheduling task, the task bidding plan for the target scheduling task is optimized in real time.

7. The method according to claim 6, characterized in that, The step of optimizing the task bidding plan for the target scheduling task in real time based on the task information of the new scheduling task and the AGV model used to execute the new scheduling task includes: Based on the historical task bidding planning data corresponding to the target scheduling task, the task information of the new scheduling task, and the AGV car model used to execute the new scheduling task, the scheduling effect under different bidding rules is predicted. Based on the scheduling effect, the bidding rules are dynamically optimized to determine the AGV vehicle model to execute the new scheduling task based on the optimized bidding rules.

8. The method according to claim 3, characterized in that, The optimization of the target candidate AGV scheduling scheme based on the optimization algorithm includes: The AGV's trajectory and traffic flow are obtained through the traffic control model. Based on the operating trajectory and traffic flow, the path planning for the target scheduling task is optimized in real time.

9. The method according to claim 8, characterized in that, The real-time optimization of the path planning for the target scheduling task based on the running trajectory and traffic flow includes: Based on the operating trajectory and the traffic flow, potential congestion points and conflict areas in the operating environment are identified; Based on historical traffic control data corresponding to the target scheduling task, as well as the potential congestion points and conflict areas, the operating trend of the AGV vehicle model is predicted in order to perform predictive traffic control on the AGV vehicle model.

10. The method according to claim 3, characterized in that, The optimization of the target candidate AGV scheduling scheme based on the optimization algorithm includes: The scheduling strategy model is used to obtain runtime data from the runtime environment; Based on the aforementioned operational data, potential deadlock modes are identified; Based on the potential deadlock modes, determine the risk level of deadlock in the AGV scheduling system; When the risk level is high, the scheduling strategy is optimized.

11. The method according to claim 10, characterized in that, After optimizing the scheduling strategy plan, the method further includes: When a deadlock is detected, identify the AGVs and path resources affected by the deadlock; Based on the AGV affected by deadlock and the path resources, the scheduling strategy is dynamically adjusted. According to the dynamically adjusted scheduling strategy, the deadlock resolution operation is performed through the AGV scheduling system.

12. The method according to claim 11, characterized in that, The method further includes: The monitoring center displays the operational status of the digital twin model in real time. The monitoring center's user interface allows for the monitoring of the AGV vehicle model's status, deadlock risk, and deadlock resolution process.

13. An electronic device, characterized in that, include: Memory and processor; The memory is connected to the processor and is used to store programs; The processor is configured to implement the AGV scheduling method as described in any one of claims 1-12 by running a program in the memory.

14. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the AGV scheduling method as described in any one of claims 1-12.

15. A computer program product, characterized in that, It includes computer program instructions that, when executed by a processor, cause the processor to implement the AGV scheduling method as described in any one of claims 1 to 12.

Images