Scheduling control optimization method, device and equipment for automated guided vehicle, and medium

Abstract

The invention relates to an automatic guided vehicle scheduling control optimization method and device, equipment and a medium, and the method comprises the steps: randomly generating a plurality of different task execution scenes through employing a preset second scheduling control algorithm, determining the vehicle position distance between the automatic guided vehicles based on the task execution speed corresponding to each automatic guided vehicle, and triggering a plurality of path conflict solving strategies corresponding to the task execution scene when detecting that the vehicle position distance is smaller than a preset distance threshold value at a certain moment, the transport path track of each automatic guided vehicle under the plurality of path conflict solving strategies is determined; and calculating and determining the path conflict probability between the transportation path tracks of each automatic guided vehicle under the corresponding path conflict solving strategy, and taking the conflict solving strategy with the minimum path conflict probability as the optimal path conflict solving strategy under the task execution scene. The transportation task scheduling efficiency and flexibility of the discrete manufacturing workshop can be remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of manufacturing, and particularly to an optimization method for the scheduling control of an automated guided vehicle, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] An AGV (Automated Guided Vehicle) is an automated transportation device. The AGV system is relatively easy to implement digital twin technology due to its simple operating state and control instructions. Many enterprises have established AGV system digital twin platforms at various levels. Through digital twin technology, the actual operating information of the AGV, such as position, status, task, speed, etc., can be synchronized and updated to the digital twin model in real time, and the optimal processing solution can be obtained according to the corresponding algorithm. At the same time, the optimal decision made based on the digital twin model can be immediately converted into control instructions for the AGV entity. Therefore, AGV digital twin technology provides more intelligent, efficient, and practical decision-making services for enterprises, factory transportation, etc. Although AGV digital twin technology offers great potential and advantages, to fully utilize its advantages and achieve more intelligent, efficient, and practical decision-making, continuous exploration and research are still needed in the academic and industrial circles.

[0003] In a complex discrete manufacturing workshop, during the task execution process of an automated guided vehicle, problems such as unreasonable path planning, uneven task scheduling and resource allocation are likely to occur. At the same time, due to various constraints and changing factors in actual operations, such as conflicts between vehicles, dynamic environmental changes, etc., the existing scheduling control algorithms for automated guided vehicles cannot well handle complex actual production scenarios and cannot better adapt to and respond to changing requirements and environments.

[0004] In summary, in view of the problems in the prior art that during the task execution process of an automated guided vehicle, problems such as unreasonable path planning, uneven task scheduling and resource allocation are likely to occur, and it cannot well handle complex actual production scenarios, etc., the applicant has made corresponding explorations to solve this problem. Summary of the Invention

[0005] The purpose of the present application is to solve the above problems and provide an optimization method for the scheduling control of an automated guided vehicle, a corresponding device, an electronic device, and a computer-readable storage medium.

[0006] To achieve the various purposes of the present application, the following technical solutions are adopted: An optimization method for the scheduling control of an automated guided vehicle proposed for one of the purposes of the present application includes: Obtain the transportation task information corresponding to each transportation task to be transported in the transportation task pool of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided vehicle. Among them, the transportation task information includes task priority, and the vehicle status information includes vehicle performance parameters and vehicle load level; In the task execution stage, after performing fuzzy inference and defuzzification according to the vehicle performance parameters, the vehicle load level or the task priority by using a preset first scheduling control algorithm, to determine the task execution speed corresponding to each automatic guided vehicle; Use a preset second scheduling control algorithm to randomly generate multiple different task execution scenarios, determine the vehicle position distance between each automatic guided vehicle based on the task execution speed corresponding to each automatic guided vehicle. When it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, trigger multiple path conflict resolution strategies corresponding to the task execution scenario, to determine the transportation path trajectory of each automatic guided vehicle under the multiple path conflict resolution strategies; Calculate and determine the path conflict probability between the transportation path trajectories of each automatic guided vehicle under its corresponding path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario, to complete the scheduling control of the automatic guided vehicle.

[0007] Optionally, the step of determining the task execution speed corresponding to each automatic guided vehicle by performing fuzzy inference and defuzzification according to the vehicle performance parameters, the vehicle load level or the task priority by using a preset first scheduling control algorithm, includes: Obtain the input fuzzy linguistic variables of each input variable, where the input variables include task priority, vehicle performance parameters and vehicle load level; Call a preset fuzzy control rule table, and calculate the output fuzzy linguistic variable of the output variable corresponding to the input fuzzy linguistic variable based on the fuzzy control rule table; After defuzzifying the output fuzzy linguistic variable according to a preset defuzzification algorithm, to obtain the defuzzified output variable, where the output variable represents the task execution speed corresponding to each automatic guided vehicle.

[0008] Optionally, the step of determining the task execution speed corresponding to each automatic guided vehicle by performing fuzzy inference and defuzzification according to the vehicle performance parameters, the vehicle load level or the task priority by using a preset first scheduling control algorithm, includes: Determine the number of input fuzzy linguistic variables corresponding to each of the input variables, the number of output fuzzy linguistic variables corresponding to the output variable, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables; Based on the ratio method, calculate and determine the scale factor between the input variable and the output variable according to the number of input fuzzy linguistic variables, the number of output fuzzy linguistic variables, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables.

[0009] Optionally, use a preset second scheduling control algorithm to randomly generate multiple different task execution scenarios, determine the vehicle position distances between the automated guided vehicles based on the task execution speeds corresponding to the automated guided vehicles, and if it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, trigger multiple path conflict resolution strategies corresponding to the task execution scenario to determine the transportation path trajectories of the automated guided vehicles under the multiple path conflict resolution strategies. The steps include: Respond to the path conflict monitoring instruction and obtain the range of the duration to be detected during the task execution of the automated guided vehicle; Detect that the vehicle position distance between the automated guided vehicles is less than a preset distance threshold at a certain moment within the duration to be detected, and trigger multiple preset path conflict resolution strategies to determine the transportation path trajectories of the automated guided vehicles under the multiple path conflict resolution strategies. Among them, the control parameters corresponding to the path conflict resolution strategies include one or any combination of path adjustment parameters, speed change parameters, and status parameters.

[0010] Optionally, the steps of calculating and determining the path conflict probability between the transportation path trajectories of the automated guided vehicles under their corresponding path conflict resolution strategies and taking the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario include: Obtain the preset number of Monte Carlo simulations, the first transportation path trajectory corresponding to the first automated guided vehicle and the second transportation path trajectory corresponding to the second automated guided vehicle under each path conflict resolution strategy, where the second scheduling control algorithm is the Monte Carlo simulation algorithm; Use the preset Monte Carlo simulation algorithm to perform conflict judgment on the first transportation path trajectory and the second transportation path trajectory according to the path conflict judgment function until the preset number of Monte Carlo simulations is reached to determine the number of path conflicts under the path conflict resolution strategy; Calculate and determine the average value of the number of path conflicts in the preset number of Monte Carlo simulation times to determine the path conflict probability between the first automated guided vehicle and the second automated guided vehicle under the path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario.

[0011] Optionally, after the step of obtaining the information of each to-be-transported task corresponding to the to-be-transported task pool in the discrete manufacturing workshop and the vehicle status information corresponding to each automated guided vehicle, it includes: Determine the information of each to-be-transported task corresponding to each to-be-transported task and the vehicle status information corresponding to each automated guided vehicle. Among them, the to-be-transported task information includes the arrival time of the transportation task, the loading point, and the processing point, and the vehicle status information includes whether the automated guided vehicle is in the transportation state. Adopt a preset vehicle scheduling strategy to allocate vehicles to each to-be-transported task according to the to-be-transported task information and the vehicle status information to determine the automated guided vehicle corresponding to each to-be-transported task. Among them, the vehicle scheduling strategy includes a task-driven assignment strategy and a vehicle-driven assignment strategy. The task-driven assignment strategy includes the nearest vehicle first rule, and the vehicle-driven assignment strategy includes the nearest task first rule and the earliest task first rule.

[0012] Optionally, the first scheduling control algorithm is a fuzzy control algorithm based on the Mamdani method, and the task execution scenario includes one or any combination of obstacle events, changes in the activities of automated guided vehicles, and task reset based on task time.

[0013] An automated guided vehicle scheduling control optimization device provided to meet another object of the present application includes: A task information determination module, configured to obtain the information of each to-be-transported task corresponding to the to-be-transported task pool in the discrete manufacturing workshop and the vehicle status information corresponding to each automated guided vehicle. Among them, the to-be-transported task information includes the task priority, and the vehicle status information includes the vehicle performance parameters and the vehicle load level. A task speed determination module, configured to, in the task execution stage, perform fuzzy inference and defuzzification according to the vehicle performance parameters, the vehicle load level, or the task priority by using a preset first scheduling control algorithm to determine the task execution speed corresponding to each automated guided vehicle. A transportation path determination module is configured to randomly generate multiple different task execution scenarios by using a preset second scheduling control algorithm, determine the vehicle position distances between various automated guided vehicles based on the task execution speeds corresponding to the respective automated guided vehicles, and if it is detected that the vehicle position distances are less than a preset distance threshold at a certain moment, trigger multiple path conflict resolution strategies corresponding to the task execution scenarios to determine the transportation path trajectories of the respective automated guided vehicles under the multiple path conflict resolution strategies; An optimal strategy determination module is configured to calculate and determine the path conflict probabilities between the transportation path trajectories of the respective automated guided vehicles under their corresponding path conflict resolution strategies, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automated guided vehicles.

[0014] An electronic device provided to meet another object of the present application includes a central processing unit and a memory. The central processing unit is configured to call and run a computer program stored in the memory to execute the steps of the automated guided vehicle scheduling control optimization method of the present application.

[0015] A computer-readable storage medium provided to meet another object of the present application stores a computer program implemented according to the automated guided vehicle scheduling control optimization method in the form of computer-readable instructions. When the computer program is called and run by a computer, it executes the steps included in the corresponding method.

[0016] As can be seen from the above embodiments, compared with the prior art, the present application aims at the problems in the prior art that the path planning of automated guided vehicles is prone to be unreasonable, and the task scheduling and resource allocation are uneven during the task execution process. At the same time, due to various constraint conditions and changing factors in actual operations, the existing automated guided vehicle scheduling control algorithms cannot well handle complex actual production scenarios and other problems. The present application includes but is not limited to the following beneficial effects: First, the automated guided vehicle scheduling control optimization method of the present application can significantly improve the transportation task scheduling efficiency and flexibility. Through the fuzzy control algorithm, according to the vehicle's performance, load level, and task priority, the task execution speeds of the respective automated guided vehicles (AGVs) are flexibly determined, enabling the scheduling system to better adapt to the dynamic changes in the workshop. The scheduling of the automated guided vehicles (AGVs) not only considers the priority but also can make appropriate adjustments according to the real-time conditions of the vehicles, thereby improving the efficiency of task scheduling; Second, the automatic guided vehicle scheduling control optimization method of the present application can effectively address path conflicts and dynamic environmental changes. By using the Monte Carlo simulation algorithm, multiple different task execution scenarios are randomly generated. It can not only effectively simulate various possible task execution situations but also predict and handle potential path conflict problems in advance based on the execution speed and actual position of the AGV. When the vehicle distance is less than the preset safety threshold, multiple path conflict resolution strategies are triggered, thereby reducing the probability of conflicts and avoiding vehicle collisions or task delays.

[0017] Third, the automatic guided vehicle scheduling control optimization method of the present application can automatically select the strategy with the lowest conflict probability by calculating the conflict probability under different path conflict resolution strategies, thereby obtaining the optimal path planning. It can minimize the interference between vehicles and improve the overall efficiency and safety of the transportation system.

[0018] Fourth, the automatic guided vehicle scheduling control optimization method of the present application enables the automatic guided vehicle to dynamically adapt to changes in the production environment and requirements. Traditional automatic guided vehicle (AGV) scheduling methods usually rely on static parameters and rules and are difficult to cope with dynamic changes in the workshop environment, such as sudden increases in tasks, equipment failures, or adjustments to the workshop layout. By calculating factors such as task priorities, vehicle status, and task scenario simulation in real time, the system can adjust the scheduling strategy in real time to adapt to different production requirements and environmental changes.

[0019] Fifth, the automatic guided vehicle scheduling control optimization method of the present application greatly improves resource utilization and significantly reduces production costs. By reasonably allocating tasks and optimizing vehicle scheduling, it ensures that each AGV performs appropriate tasks at the right time, avoiding problems such as task congestion, vehicle idleness, or overloading. Combining task priorities, vehicle loads, and performance information, the scheduling strategy can be dynamically adjusted to balance the workload and improve the utilization efficiency of workshop resources.

[0020] Furthermore, by combining the fuzzy control algorithm, Monte Carlo simulation, and path conflict optimization strategy, the present application solves problems existing in traditional automatic guided vehicle (AGV) scheduling, such as uneven task scheduling, unreasonable path planning, and high probability of conflict occurrence. It can perform dynamic scheduling based on actual vehicle performance, load status, and task priorities, optimize path planning and resource allocation, maximize workshop production efficiency, reduce conflict risks, improve the flexibility, robustness, and safety of the system, and thus better cope with the complex and changeable discrete manufacturing workshop environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the drawings, where: Figure 1It is a schematic flow chart of the method for optimizing the scheduling control of an automated guided vehicle in an embodiment of the present application; Figure 2 It is a schematic flow chart of determining the automated guided vehicle corresponding to each transportation task to be transported in an embodiment of the present application; Figure 3 It is a schematic flow chart of determining the task execution speed corresponding to each automated guided vehicle in an embodiment of the present application; Figure 4 It is a schematic flow chart of determining the scale factor between the input variable and the output variable in an embodiment of the present application; Figure 5 It is a schematic flow chart of determining the transportation path trajectory of each automated guided vehicle under multiple path conflict resolution strategies in an embodiment of the present application; Figure 6 It is a schematic flow chart of determining the optimal path conflict resolution strategy under each task execution scenario in an embodiment of the present application; Figure 7 It is a principle block diagram of the device for optimizing the scheduling control of an automated guided vehicle in an embodiment of the present application; Figure 8 It is a schematic structural diagram of a computer device in an embodiment of the present application. Detailed implementation manners

[0022] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be construed as a limitation of the present application.

[0023] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the", and "said" used herein may also include the plural forms. It should be further understood that the term "including" used in the specification of the present application means the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more related listed items.

[0024] Those skilled in the art of the present technology can understand that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as the general understanding of those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the context of the prior art, and will not be interpreted in an idealized or overly formal sense unless specifically defined as here.

[0025] Those skilled in the art of the present technology can understand that the "client", "terminal", and "terminal device" used herein include both devices with a wireless signal receiver that only has the ability to receive without transmitting, and devices with receiving and transmitting hardware that can conduct two-way communication on a two-way communication link. Such devices can include: cellular or other communication devices such as personal computers, tablet computers, etc., which have a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; PCS (Personal Communications Service), which can combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant), which can include a radio frequency receiver, pager, Internet / intranet access, web browser, notepad, calendar, and / or GPS (Global Positioning System) receiver; conventional laptop and / or palm-top computers or other devices, which are conventional laptop and / or palm-top computers or other devices with and / or including a radio frequency receiver. The "client", "terminal", and "terminal device" used herein can be portable, transportable, installed in a vehicle (air, sea, and / or land), or suitable for and / or configured to run locally, and / or run in a distributed form at any other location on the earth and / or in space. The "client", "terminal", and "terminal device" used herein can also be a communication terminal, an Internet access terminal, a music / video playback terminal, for example, it can be a PDA, MID (Mobile Internet Device), and / or a mobile phone with music / video playback function, or can also be devices such as a smart TV, a set-top box, etc.

[0026] The hardware referred to by names such as "server", "client", and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components as revealed by the von Neumann principle, including a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. A computer program is stored in its memory, and the central processing unit loads the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input / output devices to complete specific functions.

[0027] It should be noted that the concept of "server" in this application can similarly be extended to apply to server clusters. According to the network deployment principles understood by those skilled in the art, the various servers should be logically partitioned. Physically, these servers can either be independent of each other but can be invoked through interfaces, or integrated into a single physical computer or a set of computer clusters. Those skilled in the art should understand this flexibility and should not be restricted by it in the implementation of the network deployment method of this application.

[0028] One or several technical features of this application, unless expressly specified, can either be deployed on the server and accessed by the client remotely invoking the online service interface provided by the server, or directly deployed and run on the client for access.

[0029] The neural network models cited or possibly cited in this application, unless expressly specified, can either be deployed on a remote server and remotely invoked on the client, or deployed on a client with sufficient device capabilities for direct invocation. In some embodiments, when it runs on the client, its corresponding intelligence can be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid over-occupying the client's hardware operating resources.

[0030] All kinds of data involved in this application, unless expressly specified, can either be remotely stored on the server or stored on the local terminal device, as long as it is suitable for being invoked by the technical solution of this application.

[0031] Those skilled in the art should be aware that although the various methods of this application are described based on the same concept and thus show commonality with each other, unless otherwise specified, these methods can all be executed independently. Similarly, for the various embodiments disclosed in this application, they are all proposed based on the same inventive concept. Therefore, for concepts with the same expression, as well as concepts that are only appropriately transformed for convenience although the concept expressions are different, they should be equivalently understood.

[0032] For each embodiment to be disclosed in this application, unless explicitly stated as mutually exclusive, the relevant technical features involved in each embodiment can be cross - combined to flexibly construct new embodiments, as long as such combination does not deviate from the creative spirit of this application and can meet the requirements in the prior art or solve certain deficiencies in the prior art. Those skilled in the art should be aware of this flexibility.

[0033] Please refer to Figure 1 , in one embodiment of the automatic guided vehicle scheduling control optimization method of this application, it includes: Step S10: Obtain the transportation task information corresponding to each transportation task in the transportation task pool of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided vehicle. Among them, the transportation task information includes task priority, and the vehicle status information includes vehicle performance parameters and vehicle load level; The automatic guided vehicle scheduling control system in the terminal device can respond to the automatic guided vehicle scheduling control optimization method of this application to obtain the transportation task information corresponding to each transportation task in the transportation task pool of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided vehicle. Among them, the transportation task information includes task priority, and the vehicle status information includes vehicle performance parameters and vehicle load level; Specifically, the transportation task information reflects various attributes and characteristics of each transportation task. The transportation task information includes task priority, arrival time of the transportation task, loading point, processing point, etc. The task priority represents the importance or urgency of each transportation task in the entire scheduling system. Generally, tasks with higher priority should be given priority in scheduling to ensure that they can be completed as soon as possible. The priority can be divided based on the timeliness of the task, the size of the task, the requirements of the production line, or other relevant business rules.

[0034] The vehicle status information reflects the current working state of each automatic guided vehicle (AGV), its vehicle performance parameters, vehicle load level, etc. The vehicle performance parameters include but are not limited to battery power, speed capacity, position accuracy, and health status, etc. The vehicle load level includes but is not limited to the current load weight and load status, etc.

[0035] In some embodiments, please refer to Figure 2 , after the step of obtaining the transportation task information corresponding to each transportation task in the transportation task pool of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided vehicle, it includes: Step S101: Determine the transportation task information corresponding to each transportation task to be carried out and the vehicle status information corresponding to each automated guided vehicle (AGV). Among them, the transportation task information includes the arrival time of the transportation task, the loading point, and the processing point, and the vehicle status information includes whether the AGV is in a transportation state. Step S102: Use a preset vehicle scheduling strategy to allocate vehicles for each transportation task to be carried out according to the transportation task information and the vehicle status information, so as to determine the AGV corresponding to each transportation task to be carried out. Among them, the vehicle scheduling strategy includes a task-driven assignment strategy and a vehicle-driven assignment strategy. The task-driven assignment strategy includes the nearest vehicle first rule, and the vehicle-driven assignment strategy includes the nearest mission first rule and the earliest mission first rule.

[0036] Specifically, a transportation task to be carried out in the transportation task pool can be expressed as {begin, finish, t}, where begin represents the loading point, finish represents the processing point, and t represents the arrival time of the transportation task. In terms of vehicle allocation and scheduling, use a preset vehicle scheduling strategy to allocate vehicles for each transportation task to be carried out according to the transportation task information and the vehicle status information, so as to determine the AGV corresponding to each transportation task to be carried out. The nearest vehicle first rule (NVF), the nearest mission first rule (NMF), and the earliest mission first rule (EMF) can be adopted; if there is an idle AGV, the nearest vehicle first rule is used. When the arrival time of a generated transportation task is later than the current system time, the system scheduling module will drive the discrete simulation module to run and advance the system time until the arrival time of the transportation task. When simulating to the arrival time of the task, if there is an idle AGV, the task-driven assignment strategy is adopted to select an AGV; if all AGVs are performing other transportation tasks, the task is cached in the task pool, and the discrete simulation module is driven to advance the simulation until an idle AGV appears in the system. The transportation tasks to be carried out arriving during this period will also be cached in the task pool; when there is an idle AGV, the vehicle-driven assignment strategy (the nearest mission first rule or the earliest mission first rule) is adopted to select each transportation task to be carried out.

[0037] In some embodiments, the algorithmic process of the task-driven assignment strategy includes: traversing all transportation tasks to be processed; selecting a nearest available Automated Guided Vehicle (AGV) from all AGVs according to the task to be transported and the nearest vehicle first rule, and a time limit is also set, that is, finding an available AGV within 30 seconds; if an available AGV is selected, then perform task assignment and assign the task to the selected AGV; remove the successfully assigned task from the task pool.

[0038] As can be seen from the above embodiments, each task in the task pool selects an available AGV to execute through the nearest vehicle first rule. The selection basis is calculated according to the path length from the loading point of the task to the AGV, and the nearest AGV is selected; if the task is successfully assigned, the task is removed from the task pool.

[0039] In some embodiments, the algorithmic process of the vehicle-driven assignment strategy includes: checking whether there are unprocessed tasks in the task pool, and if so, entering the task selection stage; selecting a task to be transported from the task pool to be transported according to the nearest task first rule (NMF), and the nearest task first rule characterizes selecting the task to be transported with the earliest arrival time; assigning the selected task to the currently available AGV; after assigning the task, removing the task from the task pool; if the task pool is empty, that is, there are no tasks to be processed, the program continues.

[0040] As can be seen from the above embodiments, if there are tasks in the task pool, the tasks will be cached when there are no available AGVs. If an AGV is available, the tasks are selected through the vehicle-driven strategy and assigned to the available AGV. The strategy here is to select the nearest task rule (NMF) or the earliest task rule (EMF) to ensure that the tasks are processed in a timely manner.

[0041] Specifically, during scheduling, the system performs scheduling based on the status of tasks and the idle status of automated guided vehicles (AGVs). If there are idle AGVs, the system uses the nearest vehicle first rule. Specifically, the system calculates the path length from each idle AGV to the starting point (begin) of the task and selects the AGV closest to the task starting point to execute the task, and this process will be completed within 30 seconds. If a new transportation task arrives, but the arrival time of the task is later than the current system time, the system advances the system time through the simulation module until the task arrives. When the task arrives, if there are idle AGVs, the system selects an AGV according to the specified task-driven assignment strategy; if there are no idle AGVs, the system caches the task in the task pool and continues to advance the simulation until an AGV becomes idle. The system checks all tasks in the task pool and selects the most suitable AGV for each task. For each task, the system selects the AGV closest to the starting point (begin) of the task for execution, and the selection strategy is the nearest vehicle first. If a suitable AGV is found, the system assigns the task to the AGV and removes the task from the task pool. If there are still tasks to be processed in the task pool, the system selects a task according to the nearest task first or the earliest task first in the vehicle-driven strategy. Once a task is selected, the system assigns it to a suitable AGV to execute the task and removes the task from the task pool. If there are no tasks to be processed, the system continues to loop and cache the tasks in the task pool, waiting for an idle AGV to perform task allocation.

[0042] Step S20, in the task execution stage, after performing fuzzy inference and defuzzification according to the vehicle usage performance parameters, the vehicle load level, or the task priority by using a preset first scheduling control algorithm, to determine the task execution speed corresponding to each automated guided vehicle; After obtaining the transportation task information corresponding to each transportation task in the transportation task pool of the discrete manufacturing workshop and the vehicle status information corresponding to each automated guided vehicle, in the task execution stage, after performing fuzzy inference and defuzzification according to the vehicle usage performance parameters, the vehicle load level, or the task priority by using a preset first scheduling control algorithm, to determine the task execution speed corresponding to each automated guided vehicle; wherein, the first scheduling control algorithm is a fuzzy control algorithm based on the Mamdani method.

[0043] During the task execution process, the Automated Guided Vehicle (AGV) will adopt a triple mechanism (Three Distribution Mechanisms, TDM) as the core driving force for task execution. The triple mechanism includes a control mechanism, an anti-duplication and anti-leakage mechanism, and a task execution mechanism. The use of this triple mechanism can improve the reliability and efficiency of the Automated Guided Vehicle (AGV) in task execution while ensuring the completion of the task.

[0044] However, in the actual production process of the factory, due to the instability and diversity of environmental factors, the traditional linear judgment method cannot meet the requirements of the actual production process. In view of the defects of the traditional technology, this application incorporates a fuzzy control algorithm based on the Mamdani method in the task execution stage.

[0045] The Fuzzy Control Algorithm (FCA) is a control strategy based on fuzzy logic to handle uncertainty and fuzziness problems. Different from traditional binary logic, fuzzy logic can handle fuzziness, uncertainty, and fuzzy concepts expressed in human language, describe these fuzzy concepts as control rules, and then use these rules to control the system. Therefore, the fuzzy control algorithm can be applied to multiple scenarios, especially when there is uncertainty in the system or flexible decision-making is required. For example, scenarios such as the speed control and task scheduling of the Automated Guided Vehicle (AGV) can use the fuzzy control algorithm.

[0046] In some embodiments, please refer to Figure 3 , the steps of performing fuzzy inference and defuzzification according to a preset first scheduling control algorithm based on the vehicle usage performance parameters, the vehicle load level, or the task priority to determine the task execution speed corresponding to each Automated Guided Vehicle include: Step S201, obtain the input fuzzy linguistic variables of each input variable, where the input variables include task priority, vehicle usage performance parameters, and vehicle load level; Step S202, call a preset fuzzy control rule table, and calculate the output fuzzy linguistic variables of the output variables corresponding to the input fuzzy linguistic variables based on the fuzzy control rule table; Step S203, perform defuzzification on the output fuzzy linguistic variables according to a preset defuzzification algorithm to obtain the defuzzified output variables, where the output variables represent the task execution speeds corresponding to each Automated Guided Vehicle.

[0047] In a further embodiment, please refer to Figure 4, the step of performing fuzzy inference and defuzzification according to the vehicle use performance parameters, the vehicle load level or the task priority by using a preset first scheduling control algorithm to determine the task execution speed corresponding to each automatic guided vehicle, includes: Step S2001, determining the number of input fuzzy linguistic variables corresponding to each of the input variables, the number of output fuzzy linguistic variables corresponding to the output variable, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables; Step S2002, calculating and determining the scale factor between the input variable and the output variable based on the ratio method according to the number of input fuzzy linguistic variables, the number of output fuzzy linguistic variables, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables.

[0048] Specifically, during the task execution stage, the automatic guided vehicle scheduling control system uses a multi-dimensional fuzzy controller to determine the task execution speed corresponding to the automatic guided vehicle (AGV), which consists of a fuzzification interface, fuzzy inference, defuzzification, a rule base, etc. Its input variables include multiple factors such as task priority, the vehicle use performance parameters corresponding to the automatic guided vehicle (AGV), the vehicle load level corresponding to the automatic guided vehicle (AGV), and the current speed of the automatic guided vehicle (AGV), and the output variable represents the task execution speed corresponding to each automatic guided vehicle.

[0049] Fuzzification refers to the process of matching the input variables and the output variables into linguistic values, that is, converting the input variables into fuzzy sets for fuzzy inference. The automatic guided vehicle scheduling control system has two types of input variables. One is the input variable X belonging to the function, and the other is the input variable Y belonging to the function, and the output variable is the output variable Z belonging to the function. Usually, the system defines that the number of input fuzzy linguistic variables is 3 or 5, and the number of output fuzzy linguistic variables is 5. The specific definitions are as follows: ， (1) ， (2) ， (3) Next, according to the preset algorithm control rules, it is necessary to convert the domains of the input fuzzy language variables and the output fuzzy language variables into their corresponding finite integer discrete domains. Based on the ratio method, according to the number of input fuzzy language variables, the number of output fuzzy language variables, the finite integer discrete domain corresponding to the input fuzzy language variables, and the finite integer discrete domain corresponding to the output fuzzy language variables, the scale factor between the input variables and the output variables is calculated and determined.

[0050] In a further embodiment, the establishment of the rule base is a necessary prerequisite for performing the fuzzy control algorithm. The rule base contains empirical knowledge related to process operations. For example, when the priority of the task is high, the load level is low, and the performance is excellent, the task execution status of the automatic guided vehicle (AGV) controlled by the triple mechanism can be assigned as excellent. Here, the objective function of the task execution status of the automatic guided vehicle (AGV) is defined as the task execution speed. According to the 5 output fuzzy language variables of the output variable, it includes PS2 (extremely small), PS1 (small), PM (medium), PB1 (large), PB2 (extremely large).

[0051] By analogy with the above method, a fuzzy control rule table is established based on expert knowledge and operator experience. The fuzzy control rule table is shown in Table 1.

[0052] Table 1 Fuzzy Control Rule Table

[0053] Based on the above fuzzy rule control table, according to the Mamdani inference method, for the vehicle performance parameters of the input automatic guided vehicle (AGV) and the vehicle load level of the automatic guided vehicle (AGV) the membership functions respectively belong to and . The fuzzy relationship is R. When the fuzzy value of the input variable is , the corresponding output variable value is . Then there are the following relationships, which include: ， (4) ， (5) The result obtained through fuzzy inference is a fuzzy set. However, in practice, a definite value is required to control the task execution of an Automated Guided Vehicle (AGV). The process of determining a precise value from the fuzzy set inferred that can best reflect the result of this fuzzy inference is called defuzzification, also known as de-fuzzification. The defuzzification algorithms include the maximum membership function method, the centroid method, the weighted average method, etc. The above methods can be used to obtain the output objective function , and obtain the precise output variable after defuzzification .

[0054] As can be seen from the above steps, through fuzzy inference of different input variables such as vehicle performance parameters, vehicle load levels, and task priorities, the system can dynamically adjust the task execution speed of the Automated Guided Vehicle (AGV) according to the real-time state, enabling the Automated Guided Vehicle (AGV) to automatically optimize its task execution speed under different working conditions, avoiding overly fixed or mechanized scheduling methods, thereby improving the overall work efficiency. The task execution environment in reality is often full of uncertainties, such as load changes, performance fluctuations, task priority adjustments, etc. Fuzzy control can effectively handle these uncertainties and fuzziness. Through fuzzy inference, the system can comprehensively consider various factors according to the membership functions of different fuzzy sets, and thus make decisions that better meet the actual needs, rather than simply relying on precise numerical data. The adoption of fuzzy control enables the system to have better adaptability to environmental changes. For example, the execution speed of the Automated Guided Vehicle (AGV) can be automatically adjusted by the fuzzy control system under different task priorities or different load conditions, enabling it to operate efficiently in various dynamic situations. This makes the scheduling control system of the Automated Guided Vehicle have strong flexibility and adaptability, and can cope with complex and changeable actual working environments.

[0055] Through automated fuzzy control, the system can self-adjust the task execution speed without real-time manual intervention. This reduces the dependence on operators, improves the automation level of the system, and reduces the risks brought by human operation errors. By adjusting the task execution speed through the fuzzy control algorithm, it can ensure that the speed of the Automated Guided Vehicle (AGV) matches factors such as task priority, load, and performance parameters, thus enabling more reasonable allocation and utilization of resources. For example, when the task priority is high, the system can increase the task execution speed of the Automated Guided Vehicle (AGV), while when the load is heavy, the system may reduce the speed to avoid overloading and ensure the rational use of resources. Fuzzy control can smoothly adjust the task execution speed of the Automated Guided Vehicle (AGV), avoiding overly drastic speed fluctuations and ensuring the smooth operation of the system. Through reasonable fuzzy inference and defuzzification, the Automated Guided Vehicle (AGV) can maintain a stable operating state in a complex environment, reducing mechanical wear and energy waste caused by excessive acceleration or deceleration. The fuzzy control algorithm has strong robustness and can make reasonable decisions in the face of incomplete or inaccurate data. In a complex or ever-changing environment, the system can reason based on existing fuzzy rules, avoiding system failure due to data errors or environmental fluctuations and improving the reliability of decision-making.

[0056] Furthermore, by adopting a preset fuzzy control algorithm and performing fuzzy inference and defuzzification in combination with factors such as vehicle performance, load level, and task priority, the AGV scheduling system can achieve more efficient, flexible, and precise control of the task execution speed in a complex and changeable environment. This method can not only improve the automation level of the system, reduce manual intervention, but also optimize resource allocation and enhance the adaptability and stability of the system.

[0057] Step S30: Randomly generate multiple different task execution scenarios using a preset second scheduling control algorithm. Based on the task execution speeds corresponding to each Automated Guided Vehicle, determine the vehicle position distances between each Automated Guided Vehicle. When it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, trigger multiple path conflict resolution strategies corresponding to the task execution scenario to determine the transportation path trajectories of each Automated Guided Vehicle under the multiple path conflict resolution strategies; During the task execution phase, after performing fuzzy inference and defuzzification according to the vehicle usage performance parameters, the vehicle load level, or the task priority using a preset first scheduling control algorithm to determine the task execution speed corresponding to each automated guided vehicle, a preset second scheduling control algorithm is used to randomly generate multiple different task execution scenarios. Based on the task execution speed corresponding to each automated guided vehicle, the vehicle position distance between each automated guided vehicle is determined. When it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, multiple path conflict resolution strategies corresponding to the task execution scenario are triggered to determine the transportation path trajectory of each automated guided vehicle under the multiple path conflict resolution strategies. Among them, the second scheduling control algorithm is the Monte Carlo simulation algorithm, and the task execution scenario includes one or any combination of obstacle events, changes in the activities of automated guided vehicles, and task reset based on task time.

[0058] During the task execution phase, after performing fuzzy inference and defuzzification according to the vehicle usage performance parameters, the vehicle load level, or the task priority using a preset first scheduling control algorithm to determine the task execution speed corresponding to each automated guided vehicle, in terms of solving multi-vehicle collaboration, a conflict-solving strategy (CSS) is adopted: when a path conflict occurs, corresponding handling solutions are tried according to the type of conflict. If it is determined that the conflict cannot be resolved, the corresponding automated guided vehicle (AGV) is terminated; if it can be resolved, the next path is selected to continue working. This strategy mainly includes a conflict-avoidance strategy (CAS) and a minimum stoppage strategy (MS).

[0059] During the discrete simulation of the automated guided vehicle scheduling control system, the simulation clock advances sequentially forward according to the moments when a series of discrete events occur. The most important event in this discrete event simulation module is the automated guided vehicle (AGV) activity event, which includes three types: path change, position change, and path termination. According to each different discrete time, the priority needs to be substituted and a choice needs to be made to better coordinate and efficiently complete the overall task.

[0060] In addition to the activities of automated guided vehicles (AGVs), there are other discrete events that need to be considered. One is the obstacle event, including the appearance and disappearance of random obstacles (non-AGVs) at nodes. To simplify the obstacle event, when an obstacle randomly appears at a node, if there is already an automated guided vehicle (AGV) at this node, it can leave normally after completing the ongoing task. After that, all automated guided vehicles (AGVs) will no longer be assigned tasks at this processing point, and the task will be returned to the cache. The automated guided vehicle (AGV) cannot enter this node until the obstacle disappears. In addition, when the conflict response strategy in the system scheduling module is set to the conflict active avoidance strategy (CAS) or the minimum pause strategy (MS), since the AGVs need to be scheduled in real time (time interval 30s to 60s), the effect of the AGV completing tasks caused by the scheduling event is also a discrete event.

[0061] The above discrete events may occur at the same time. Among them, the probability that the three subclasses of the automated guided vehicle (AGV) activity event occur simultaneously is 0, so there is no clear priority among them. However, in the case of other discrete events occurring, except for the automated guided vehicle (AGV) position change event, the priority order of handling the remaining events has no impact on the simulation results, so it can be processed in a random order in practice. For multiple simultaneous automated guided vehicle (AGV) position change events, if there are multiple AGVs with the same next position selection, the process tasks will be processed according to the arrival order of the automated guided vehicles (AGVs), and the priority will be sorted according to the arrival time. Among them, the priority order of the AGV activity time and discrete time is shown in Table 2.

[0062] Table 2 Priority order of AGV activity time and discrete time

[0063] Task assignment will be processed according to the above priorities to ensure the efficient scheduling of multiple automated guided vehicles (AGVs) and prevent events such as collisions. After obtaining random samples through multiple repeated simulation experiments, the conflict solution strategy (CSS) can be optimized based on multiple sample data to better solve and avoid conflict events.

[0064] In a further embodiment, the present application uses the Monte Carlo simulation algorithm to optimize the conflict resolution strategy (CSS). Monte Carlo simulation is a method of evaluating the behavior of a system through random sampling. In the conflict resolution strategy (CSS), Monte Carlo simulation can be used to evaluate the probability of conflicts occurring, which helps to optimize the decision-making for conflict resolution. Specifically, in Monte Carlo simulation, given several resolution strategies, through a large number of random scenario simulations, the probability of each strategy leading to conflicts is predicted, and thus the optimal strategy is selected for execution.

[0065] First, in the conflict resolution strategy (CSS), it is necessary to detect whether there is a conflict between the transportation path trajectories of any two automated guided vehicles (AGVs). If a conflict is detected, it is necessary to enter the conflict handling stage.

[0066] In a specific embodiment, please refer to Figure 5 , and a preset second scheduling control algorithm is used to randomly generate multiple different task execution scenarios. Based on the task execution speeds corresponding to each automated guided vehicle, the vehicle position distances between each automated guided vehicle are determined. If it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, then multiple path conflict resolution strategies corresponding to the task execution scenario are triggered to determine the transportation path trajectories of each automated guided vehicle under the multiple path conflict resolution strategies. The steps include: Step S301: Respond to the path conflict monitoring instruction and obtain the range of the duration to be detected during the task execution of the automated guided vehicle; Step S302: Detect that the vehicle position distance between each automated guided vehicle is less than a preset distance threshold at a certain moment within the duration to be detected, and then trigger a preset multiple path conflict resolution strategies to determine the transportation path trajectories of each automated guided vehicle under the multiple path conflict resolution strategies. Among them, the control parameters corresponding to the path conflict resolution strategy include one or any combination of a path adjustment parameter, a speed change parameter, and a state parameter.

[0067] More specifically, the present application sets the paths of two AGVs to be and , then the positions at time t are: ， (6) ， (7) Set the conflict condition within the duration to be detected as: ， (8) Among them, is the minimum distance at which a conflict occurs, that is, a preset distance threshold. is the predicted time range, that is, the range of the duration to be detected.

[0068] Step S40: Calculate and determine the path conflict probability between the transportation path trajectories of each automated guided vehicle under its corresponding path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automated guided vehicle.

[0069] Use a preset second scheduling control algorithm to randomly generate multiple different task execution scenarios. Based on the task execution speeds corresponding to each automated guided vehicle, determine the vehicle position distances between each automated guided vehicle. When it is detected that the vehicle position distance is less than the preset distance threshold at a certain moment, trigger the multiple path conflict resolution strategies corresponding to the task execution scenario. After determining the transportation path trajectories of each automated guided vehicle under the multiple path conflict resolution strategies, calculate and determine the path conflict probability between the transportation path trajectories of each automated guided vehicle under its corresponding path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automated guided vehicle.

[0070] In some embodiments, refer to Figure 6 The step of calculating and determining the path conflict probability between the transportation path trajectories of each automated guided vehicle under its corresponding path conflict resolution strategy, and using the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario includes: Step S401: Obtain the preset number of Monte Carlo simulation times, the first transportation path trajectory corresponding to the first automated guided vehicle under each path conflict resolution strategy, and the second transportation path trajectory corresponding to the second automated guided vehicle, where the second scheduling control algorithm is the Monte Carlo simulation algorithm; Step S402: Use the preset Monte Carlo simulation algorithm to perform conflict judgment on the first transportation path trajectory and the second transportation path trajectory according to the path conflict judgment function until the preset number of Monte Carlo simulation times is reached to determine the number of path conflicts under the path conflict resolution strategy; Step S403: Calculate and determine the average value of the number of path conflicts in the preset number of Monte Carlo simulation times to determine the path conflict probability between the first automated guided vehicle and the second automated guided vehicle under the path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario.

[0071] Specifically, to evaluate the effectiveness of the path conflict resolution strategy, the Monte Carlo simulation algorithm creates multiple different task execution scenarios, each of which is based on the following activities, including obstacle events, changes in the activities of automated guided vehicles (AGVs), and task resets based on task time. Then, the set of path conflict resolution strategies corresponding to each task execution scenario is , and each path conflict resolution strategy corresponds to different control parameters. The control parameters corresponding to the path conflict resolution strategy include one or any combination of path adjustment parameters, speed change parameters, and state parameters.

[0072] After each path conflict resolution strategy is applied to the system, a new set of paths will be generated and . Among them, , different random scenarios will be obtained after executing different strategies on the new paths. For example, if the path deviates, let and be the path deviation amount, which follows the normal distribution law. Then, the formula for the random task execution scenario can be deduced as: ， (9) ， (10) Under the path conflict resolution strategy , the path conflict probability is estimated through the Monte Carlo simulation algorithm, which is expressed as: ， (11) where N is the number of simulations, represents the first transportation path trajectory of the nth simulation, represents the second transportation path trajectory of the nth simulation, represents the path conflict probability.

[0073] Finally, compare the magnitudes of the conflict probabilities and select the strategy with the lowest conflict probability as the optimal path conflict resolution strategy for resolving conflicts.

[0074] In some embodiments, a tolerance conflict probability threshold can be set for comparison with the lowest conflict probability. If the lowest conflict probability is still greater than the tolerance conflict probability threshold, then it is selected not to resolve the conflict and the corresponding automated guided vehicle (AGV) is terminated.

[0075] As can be seen from the above embodiments, compared with the prior art, this application addresses the problems in the prior art where automatic guided vehicles are prone to unreasonable path planning, uneven task scheduling and resource allocation during task execution. At the same time, due to various constraints and changing factors in actual operations, the existing scheduling control algorithms for automatic guided vehicles cannot well handle complex actual production scenarios. This application includes but is not limited to the following beneficial effects: First, the scheduling control optimization method for automatic guided vehicles in this application can significantly improve the efficiency and flexibility of transportation task scheduling. Through the fuzzy control algorithm, according to the vehicle's performance, load level and task priority, it flexibly determines the task execution speed of each automatic guided vehicle (AGV), enabling the scheduling system to better adapt to the dynamic changes in the workshop. The scheduling of automatic guided vehicles (AGV) not only considers priority but also makes appropriate adjustments according to the vehicle's real-time status, thus improving the efficiency of task scheduling; Second, the scheduling control optimization method for automatic guided vehicles in this application can effectively handle path conflicts and dynamic environmental changes. By using the Monte Carlo simulation algorithm, it randomly generates multiple different task execution scenarios, which can not only effectively simulate various possible task execution situations but also predict and handle potential path conflict problems in advance according to the AGV's execution speed and actual position. When the vehicle distance is less than the preset safety threshold, multiple path conflict resolution strategies will be triggered, thus reducing the probability of conflicts and avoiding vehicle collisions or task delays.

[0076] Third, the scheduling control optimization method for automatic guided vehicles in this application can automatically select the strategy with the lowest conflict probability by calculating the conflict probability under different path conflict resolution strategies, thus obtaining the optimal path planning, which can minimize the interference between vehicles and improve the overall efficiency and safety of the transportation system.

[0077] Fourth, the scheduling control optimization method for automatic guided vehicles in this application can enable automatic guided vehicles to dynamically adapt to production environment and demand changes. Traditional scheduling methods for automatic guided vehicles (AGV) usually rely on static parameters and rules and are difficult to handle the dynamic changes in the workshop environment, such as sudden task increases, equipment failures or adjustments to the workshop layout. By calculating factors such as task priority, vehicle status, and task scenario simulation in real time, the system can adjust the scheduling strategy in real time to adapt to different production demands and environmental changes.

[0078] Fifthly, the automatic guided vehicle scheduling control optimization method of the present application greatly improves resource utilization rate and significantly reduces production costs. By reasonably allocating tasks and optimizing vehicle scheduling, it ensures that each AGV performs appropriate tasks at the right time, avoiding problems such as task congestion, vehicle idleness, or overloading. Combining task priorities, vehicle loads, and performance information, the scheduling strategy can be dynamically adjusted to balance the workload and improve the utilization efficiency of workshop resources.

[0079] Furthermore, by combining fuzzy control algorithms, Monte Carlo simulations, and path conflict optimization strategies, the present application solves problems existing in traditional automatic guided vehicle (AGV) scheduling, such as uneven task scheduling, unreasonable path planning, and high probability of conflicts. It can perform dynamic scheduling according to the actual vehicle performance, load status, and task priorities, optimize path planning and resource allocation, maximize workshop production efficiency, reduce conflict risks, and improve the flexibility, robustness, and safety of the system, thus better coping with the complex and changeable discrete manufacturing workshop environment.

[0080] Please refer to Figure 7, An automatic guided vehicle scheduling control optimization device provided to meet one of the purposes of the present application, including a task information determination module 1100, a task speed determination module 1200, a transportation path determination module 1300, and an optimal strategy determination module 1400. Among them, the task information determination module 1100 is configured to obtain the to-be-transported task information corresponding to each to-be-transported task in the to-be-transported task pool of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided vehicle. Among them, the to-be-transported task information includes the task priority, and the vehicle status information includes the vehicle usage performance parameters and the vehicle load level; the task speed determination module 1200 is configured to, in the task execution stage, perform fuzzy reasoning and defuzzification according to the vehicle usage performance parameters, the vehicle load level, or the task priority by using a preset first scheduling control algorithm to determine the task execution speed corresponding to each automatic guided vehicle; the transportation path determination module 1300 is configured to randomly generate a plurality of different task execution scenarios by using a preset second scheduling control algorithm, determine the vehicle position distance between each automatic guided vehicle based on the task execution speed corresponding to each automatic guided vehicle, and when it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, trigger a plurality of path conflict resolution strategies corresponding to the task execution scenario to determine the transportation path trajectory of each automatic guided vehicle under the plurality of path conflict resolution strategies; the optimal strategy determination module 1400 is configured to calculate and determine the path conflict probability between the transportation path trajectories of each automatic guided vehicle under the corresponding path conflict resolution strategy, and use the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automatic guided vehicle.

[0081] Based on any embodiment of the present application, please refer to Figure 8 , Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device. As Figure 8 shown, the internal structure schematic diagram of the computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected through a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The control information sequence can be stored in the database. When the computer-readable instructions are executed by the processor, the processor can implement an automatic guided vehicle scheduling control optimization method. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The computer-readable instructions can be stored in the memory of the computer device. When the computer-readable instructions are executed by the processor, the processor can execute the automatic guided vehicle scheduling control optimization method of the present application. The network interface of the computer device is used to connect and communicate with the terminal. Those skilled in the art can understand,Figure 8 The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0082] In this embodiment, the processor is used to execute Figure 7 the specific functions of each module in . The memory stores the program codes and various types of data required to execute the above modules. The network interface is used for data transmission between the user terminal and the server. The memory in this embodiment stores the program codes and data required to execute all modules in the automatic guided vehicle scheduling control optimization device of this application, and the server can call the program codes and data of the server to execute the functions of all sub-modules.

[0083] This application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the steps of the automatic guided vehicle scheduling control optimization method described in any embodiment of this application.

[0084] This application also provides a computer program product, including computer programs / instructions. When the computer programs / instructions are executed by one or more processors, the steps of the automatic guided vehicle scheduling control optimization method described in any embodiment of this application are implemented.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments of this application can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above methods. Among them, the foregoing storage medium may be a computer-readable storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0086] The above are only some embodiments of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. An automatic guided vehicle scheduling control optimization method, characterized in that: include: Acquire the task information corresponding to each task to be transported in the task pool to be transported of the discrete manufacturing workshop, and the vehicle status information corresponding to each automatic guided transport vehicle, wherein the task information to be transported includes the task priority, and the vehicle status information includes the vehicle performance parameters and the vehicle load level; In the task execution stage, a preset first scheduling control algorithm is used to perform fuzzy reasoning and defuzzification according to the vehicle performance parameters, the vehicle load level or the task priority to determine the task execution speed corresponding to each automated guided transport vehicle; A preset second scheduling control algorithm is used to randomly generate a plurality of different task execution scenarios, and the vehicle position distance between each automated guided transport vehicle is determined based on the task execution speed corresponding to each automated guided transport vehicle. If it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, a plurality of path conflict resolution strategies corresponding to the task execution scenario are triggered to determine the transport path trajectory of each automated guided transport vehicle under the plurality of path conflict resolution strategies; The path conflict probability between the transport path trajectories of each automated guided transport vehicle under its corresponding path conflict resolution strategy is calculated and determined, and the conflict resolution strategy with the smallest path conflict probability is used as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automated guided transport vehicle.

2. The automatic guided vehicle scheduling control optimization method according to claim 1 is characterized in that: The step of using a preset first scheduling control algorithm to perform fuzzy reasoning and defuzzification according to the vehicle usage performance parameters, the vehicle load level or the task priority to determine the task execution speed corresponding to each automated guided transport vehicle includes: Obtaining input fuzzy linguistic variables of each input variable, wherein the input variables include task priority, vehicle usage performance parameters, and vehicle load level; Calling a preset fuzzy control rule table, and calculating output fuzzy linguistic variables of output variables corresponding to the input fuzzy linguistic variables based on the fuzzy control rule table; The output fuzzy linguistic variables are defuzzified according to a preset defuzzification algorithm to obtain defuzzified output variables, wherein the output variables represent the task execution speed corresponding to each automated guided transport vehicle.

3. The automatic guided vehicle scheduling control optimization method according to claim 1 is characterized in that: The step of using a preset first scheduling control algorithm to perform fuzzy reasoning and defuzzification according to the vehicle usage performance parameters, the vehicle load level or the task priority to determine the task execution speed corresponding to each automated guided transport vehicle includes: Determine the number of input fuzzy linguistic variables corresponding to each input variable, the number of output fuzzy linguistic variables corresponding to the output variable, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables; Based on the ratio method, the proportional factor between the input variable and the output variable is calculated and determined according to the number of the input fuzzy linguistic variables, the number of the output fuzzy linguistic variables, the finite integer discrete domain corresponding to the input fuzzy linguistic variables, and the finite integer discrete domain corresponding to the output fuzzy linguistic variables.

4. The automatic guided vehicle scheduling control optimization method according to claim 1, characterized in that: The steps of randomly generating a plurality of different task execution scenarios by using a preset second scheduling control algorithm, determining the vehicle position distance between each automatic guided transport vehicle based on the task execution speed corresponding to each automatic guided transport vehicle, and detecting that the vehicle position distance is less than a preset distance threshold at a certain moment, triggering a plurality of path conflict resolution strategies corresponding to the task execution scenario, and determining the transport path trajectory of each automatic guided transport vehicle under the plurality of path conflict resolution strategies, include: In response to the path conflict monitoring instruction, the detection time range of the automatic guided transport vehicle during the task execution is obtained; If it is detected that the vehicle position distance between each automated guided transport vehicle within the time range to be detected is less than a preset distance threshold at a certain moment, multiple preset path conflict resolution strategies are triggered to determine the transport path trajectories of each automated guided transport vehicle under the multiple path conflict resolution strategies, wherein the control parameters corresponding to the path conflict resolution strategies include one or any multiple of path adjustment parameters, speed change parameters and state parameters.

5. The automatic guided vehicle scheduling control optimization method according to claim 1, characterized in that: The steps of calculating and determining the path conflict probability between the transport path trajectories of the various automated guided transport vehicles under their corresponding path conflict resolution strategies, and taking the conflict resolution strategy with the minimum path conflict probability as the optimal path conflict resolution strategy in the task execution scenario, include: Obtaining a preset number of Monte Carlo simulations, a first transport path trajectory corresponding to the first automated guided transport vehicle under each path conflict resolution strategy, and a second transport path trajectory corresponding to the second automated guided transport vehicle, wherein the second scheduling control algorithm is a Monte Carlo simulation algorithm; Using a preset Monte Carlo simulation algorithm according to a path conflict judgment function, conflict judgment is performed on the first transport path trajectory and the second transport path trajectory until a preset Monte Carlo simulation number is reached, so as to determine the number of path conflicts under the path conflict resolution strategy; The average value of the number of path conflicts in a preset number of Monte Carlo simulations is calculated to determine the probability of path conflict between the first automated guided transport vehicle and the second automated guided transport vehicle under the path conflict resolution strategy, and the conflict resolution strategy with the smallest path conflict probability is used as the optimal path conflict resolution strategy in the task execution scenario.

6. The automatic guided vehicle scheduling control optimization method according to claim 1, characterized in that: After the step of obtaining the to-be-transported task information corresponding to each to-be-transported task in the to-be-transported task pool of the discrete manufacturing workshop and the vehicle status information corresponding to each automatic guided transport vehicle, the method includes: Determine the task information corresponding to each task and the vehicle status information corresponding to each automated guided transport vehicle, wherein the task information includes the arrival time, loading point and processing point of the transport task, and the vehicle status information includes whether the automated guided transport vehicle is in a transport state; A preset vehicle scheduling strategy is used to assign vehicles to each task to be transported according to the information of the task to be transported and the vehicle status information, so as to determine the automatic guided transport vehicle corresponding to each task to be transported, wherein the vehicle scheduling strategy includes a task-driven assignment strategy and a vehicle-driven assignment strategy, the task-driven assignment strategy includes a nearest vehicle priority rule, and the vehicle-driven assignment strategy includes a nearest task priority rule and an earliest task priority rule.

7. The automatic guided vehicle scheduling control optimization method according to any one of claims 1 to 6, characterized in that: The first scheduling control algorithm is a fuzzy control algorithm based on the Mamdani method, and the task execution scenario includes one or more of an obstacle event, an activity change of an automated guided transport vehicle, and a task reset based on task time.

8. An automatic guided vehicle dispatching control optimization device, characterized in that: include: A task information determination module is configured to obtain task information corresponding to each task to be transported in a task pool to be transported of a discrete manufacturing workshop, and vehicle status information corresponding to each automated guided transport vehicle, wherein the task information to be transported includes a task priority, and the vehicle status information includes a vehicle performance parameter and a vehicle load level; The task speed determination module is configured to use a preset first scheduling control algorithm to perform fuzzy reasoning and defuzzification according to the vehicle performance parameters, the vehicle load level or the task priority in the task execution phase to determine the task execution speed corresponding to each automated guided transport vehicle; A transport path determination module is configured to randomly generate a plurality of different task execution scenarios using a preset second scheduling control algorithm, determine the vehicle position distance between each automated guided transport vehicle based on the task execution speed corresponding to each automated guided transport vehicle, and trigger a plurality of path conflict resolution strategies corresponding to the task execution scenario when it is detected that the vehicle position distance is less than a preset distance threshold at a certain moment, so as to determine the transport path trajectory of each automated guided transport vehicle under the plurality of path conflict resolution strategies; The optimal strategy determination module is configured to calculate and determine the path conflict probability between the transport path trajectories of each automated guided transport vehicle under its corresponding path conflict resolution strategy, and use the conflict resolution strategy with the smallest path conflict probability as the optimal path conflict resolution strategy in the task execution scenario to complete the scheduling control of the automated guided transport vehicle.

9. An electronic device, comprising a central processing unit and a memory, characterized in that: The central processing unit is used to call and run the computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images