Multi-agent system efficient task allocation method and system based on reinforcement learning

Abstract

The invention discloses an efficient task allocation method and system for a multi-agent system based on reinforcement learning, and relates to the field of task allocation of a distribution logistics multi-agent system, and the method comprises the steps: dividing a total region into a plurality of sub-regions with the same area through the system; the system obtains the total number of distribution tasks to be distributed and the corresponding demand data and environment data, determines the priority for each distribution task according to the demand data, and counts the number of distribution tasks in each sub-region based on the target distribution position information. The system obtains the total number of transportation intelligent agents capable of executing distribution tasks and distance information from the center point of each sub-region to the distribution point of the total region. And generating the maximum delivery quantity of each sub-region in combination with the environment data and the delivery task quantity in the sub-region. And according to the task priority and the maximum delivery quantity of each sub-region, the transportation intelligent agent is reasonably arranged to execute task delivery, and the adaptability and stability in a complex environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of task allocation for a multi-agent system in distribution logistics, and specifically to a method and system for efficient task allocation for a multi-agent system based on reinforcement learning. Background Art

[0002] With the rapid development of e-commerce and logistics industries, the complexity and number of delivery tasks have increased significantly. Especially in urban environments, due to factors such as traffic congestion and weather changes, traditional delivery methods can no longer meet the needs of efficient and timely logistics. In recent years, multi-agent systems have received increasing attention in the field of logistics and delivery. These systems can improve delivery efficiency through the collaboration of multiple automated entities (such as delivery robots). However, existing multi-agent delivery systems often face problems such as unreasonable task allocation, low resource utilization, and poor adaptability in dynamic environments. Traditional task allocation algorithms are usually based on static planning and are difficult to adjust in real time, resulting in low delivery efficiency, especially when environmental factors such as traffic and weather change, the system lacks a flexible response mechanism.

[0003] In the prior art, the publication number CN108009012B discloses a multi-agent dynamic task allocation method based on a task model. By collecting the state information of the tasks in the environment and combining the ability parameters of the agents, a task state quantity model is established; the agents are quickly initially deployed, and the agents communicate with other agents in the environment during execution, sharing information in real time, so as to dynamically fine-tune the agents and collaborate to complete all tasks. However, sharing information during the allocation process cannot guarantee the completion of the task. Task allocation also requires overall decision-making. It is difficult to guarantee the efficiency of task completion with just preliminary deployment. Therefore, it is difficult to guarantee the effectiveness of resource allocation and the flexibility of task execution in a complex environment with only preliminary deployment and dynamic fine-tuning of shared information.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide an efficient task allocation method for a multi-agent system based on reinforcement learning to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: An efficient task allocation method for a multi-agent system based on reinforcement learning, the specific steps include: S1: Obtain the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, wherein the demand data includes the target delivery location of each task and the remaining time data for task execution, and the environmental data includes the traffic condition coefficient and weather environment data of the total area; S2: Determine the priority of the delivery task according to the demand data corresponding to the delivery task, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; S3: Obtain the total number of transport agents that can perform delivery tasks in the total area and the distance information between the center point of each sub-area and the delivery point of the total area, and combine the environmental data of the total area and the number of delivery tasks in each sub-area to generate the maximum delivery volume of each sub-area; S4: Arrange the transport agent to deliver the tasks according to the task priority and maximum delivery volume of each area.

[0007] Furthermore, the step S1 includes the following steps: S11, the method for obtaining the delivery location of each task target is: establish a plane coordinate system based on the total area of ​​the delivery task to be assigned, randomly select a point in the plane of the total area of ​​the delivery task to be assigned as the origin, and at the selected origin, take the north direction as Axis positive direction, perpendicular to The axis direction is Axis, according to the established plane coordinate system, determine the target delivery location coordinates of each task, denoted as ,in is the index of the delivery task, ,in The total number of tasks in the total area to be assigned delivery tasks; S12, the method for determining the remaining time data for task execution is: obtaining the timestamp of the current moment and the timestamp of the task deadline , based on the current timestamp and The timestamp of the task deadline Calculate the remaining time data for task execution, where the remaining time data is based on the formula: ; In the formula, To execute the remaining time data; S13, the The target delivery distance for each delivery task The calculation is based on the formula: ; in, is the current position coordinate; S14, the formula for calculating the traffic condition coefficient is: ; In the formula, is the traffic condition coefficient, is the agent flow, represents the average speed of the agent, and are the weight coefficients of agent flow and agent average speed respectively, where and are greater than 0, and ; S15, obtaining weather environment data in the total area to be assigned delivery tasks, using label encoding for the weather environment data, mapping sunny days, cloudy days and rainy days to integer form, where sunny days are mapped to 0, cloudy days are mapped to 1, and rainy days are mapped to 2.

[0008] Furthermore, the formula for determining the priority of the delivery task is: ; In the formula, For the The priority of each delivery task, Indicates The target delivery distance for a delivery task, For the The remaining execution time data of each delivery task.

[0009] Furthermore, the logic for determining the number of delivery tasks within each sub-region is: Divide the total area into sub-regions of the same area, and the area of ​​each sub-region is , determine the sub-region The vertex coordinates are represented by rectangles, and the sub-areas The lower left corner coordinates are , sub-area The upper right corner coordinates are , when Delivery location of tasks In sub-area If it is in the sub-area, it returns 1, and if it is not in the sub-area, it returns 0. The specific formula is: ; in, For the The number of delivery tasks within a sub-area.

[0010] Furthermore, the logic of the distance information between each sub-region center point and the total regional distribution point is: Sub-area The center coordinates of The calculation formula is: ; The calculation formula for the distance from the sub-region center point to the total regional distribution point is: ; in, For the The distance from the center point of each sub-region to the distribution point of the total region.

[0011] Furthermore, the maximum delivery volume formula for each sub-area is: ; in, For the The maximum delivery volume for each sub-region, is the total number of transport agents that can perform delivery tasks in the total area, For the The number of delivery tasks within each sub-region, Weather environment data.

[0012] Furthermore, the number of delivery tasks within each sub-region is sorted in ascending order according to the priority of the delivery tasks to form a task priority delivery cluster sequence. , ; in, For each task after sorting.

[0013] Furthermore, the task priority delivery cluster sequence is further modified by the maximum delivery quantity to be modified into the task sequence , the revised logic is: No. The number of delivery tasks within a sub-region is , for each task in the task priority distribution cluster sequence , if In the sub-area ,Task Assign to sub-regions and update ; If In the sub-area , task skipping, corrected task sequence for: ; in, Indicates that the The sub-region tasks and meet .

[0014] The present invention also provides a multi-agent system efficient task allocation system based on reinforcement learning, the allocation system is used to execute the above-mentioned multi-agent system efficient task allocation method, comprising: Acquisition module: obtains the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, the demand data includes the target delivery location of each task and the remaining time data of the task execution, and the environmental data includes the traffic condition coefficient and weather environment data of the total area; Data processing module: Determine the priority of the delivery task according to the demand data corresponding to the delivery task, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; Distribution decision module: obtain the total number of transport agents that can perform distribution tasks in the total area and the distance information between the center point of each sub-area and the distribution point of the total area, and combine the environmental data of the total area and the number of distribution tasks in each sub-area to generate the maximum distribution volume of each sub-area; Task allocation module: Arranges the transport agent to deliver tasks according to the task priority and maximum delivery volume of each area.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention significantly improves the distribution efficiency and resource utilization by introducing a multi-agent logistics distribution system based on reinforcement learning. Specifically, the system first reasonably divides the total area into multiple sub-areas based on the demand data and environmental factors of each distribution task, and accurately counts the number of distribution tasks in each sub-area. This refined task management strategy enables the transportation agent to efficiently respond to distribution needs in the shortest time. By comprehensively considering the number of transportation agents, the distance from the sub-area center to the distribution point, traffic conditions and weather environment data, the system generates the maximum distribution volume for each sub-area, thereby optimizing the allocation of transportation capacity. This method can effectively balance task priorities and resource constraints, ensuring that the transportation agent can efficiently complete the task during the execution process. During the task execution stage, the agent can make rapid adjustments based on real-time environmental changes, which improves the flexibility and adaptability of the overall distribution. Through this intelligent task allocation and resource management mechanism, the present invention not only improves the operating efficiency of the system, but also significantly enhances the ability to cope with complex environments, providing an innovative solution for modern logistics distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1It is a schematic diagram of the overall method flow of the present invention; Figure 2 It is a schematic diagram of the overall system design of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Example: See also Figure 1 , the present invention provides a technical solution: An efficient task allocation method for a multi-agent system based on reinforcement learning, the specific steps include: S1: Obtain the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, wherein the demand data includes the target delivery location of each task and the remaining time data for task execution, and the environmental data includes the traffic condition coefficient and weather environment data of the total area; The method for obtaining the delivery location of each task target is as follows: a plane coordinate system is established based on the total area of ​​the delivery task to be assigned, a point is randomly selected in the plane of the total area of ​​the delivery task to be assigned as the origin, and the north direction is taken as the origin at the selected origin. Axis positive direction, perpendicular to The axis direction is Axis, according to the established plane coordinate system, determine the target delivery location coordinates of each task, denoted as ,in is the index of the delivery task, ,in The total number of tasks in the total area to be assigned delivery tasks; The method to determine the remaining time data for task execution is: Get the timestamp of the current moment as and the timestamp of the task deadline , based on the current timestamp and The timestamp of the task deadline Calculate the remaining time data for task execution, where the remaining time data is based on the formula: ; In the formula, To execute the remaining time data; The said The target delivery distance for each delivery task The calculation is based on the formula: ; in, is the current position coordinate; The formula for calculating the traffic situation coefficient is: ; In the formula, is the traffic condition coefficient, is the agent flow, represents the average speed of the agent, and are the weight coefficients of agent flow and agent average speed respectively, where and are greater than 0, and ; Weight The influence of the corresponding intelligent agent flow, weight The relative size of the weights determines the relative importance of these two factors in the priority calculation, corresponding to the influence of the average speed of the agent. and The setting ensures that the average speed of the agent has a greater impact on the priority, because the delivery speed of the agent is usually a more critical factor. Even if the agent flow is sufficient during a task, if the average speed is too slow, its priority may not be high. Although the average speed of the agent is more critical, the agent flow cannot be ignored. A large enough agent flow can improve the overall efficiency. Therefore, There is also a certain weight, but it is relatively Smaller, The value of can be set to 0.1-0.5, indicating that the importance of agent traffic is limited but not negligible. The setting of is 0.5-1.0, indicating that the average speed of the agent is more important. This range is chosen based on experience and practical operational needs to ensure that in most cases, the formula can reflect a reasonable priority order.

[0020] Obtain the weather and environmental data in the total area to be assigned the delivery task, use label encoding for the weather and environmental data, and map sunny days, cloudy days, and rainy days into integer form, where sunny days are mapped to 0, cloudy days are mapped to 1, and rainy days are mapped to 2.

[0021] An efficient task allocation method for multi-agent systems based on reinforcement learning divides the total area into multiple sub-areas based on the demand data and environmental factors of each delivery task, and counts the number of delivery tasks in each sub-area. By comprehensively considering the number of transport agents, the distance from the sub-area center to the delivery point, traffic conditions, and weather and environmental data, the system generates the maximum delivery volume for each sub-area and optimizes the allocation of transportation capacity. It effectively balances task priorities and resource constraints to ensure that transport agents can efficiently complete tasks during execution.

[0022] S2: Determine the priority of the delivery task according to the demand data corresponding to the delivery task, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; The formula for determining the priority of delivery tasks is: ; In the formula, For the The priority of each delivery task, Indicates The target delivery distance for a delivery task, For the The remaining execution time data of the delivery tasks, and are greater than 0, and ; Weight The impact of the corresponding target delivery distance, weight The relative size of the weights determines the relative importance of these two factors in the priority calculation, corresponding to the impact of the remaining execution time. and The setting ensures that the remaining execution time has a greater impact on the priority, because time urgency is usually a more critical factor. Even if a task is short, if there is ample time, its priority may not be high. Although time urgency is more critical, the target delivery distance cannot be ignored. Short-distance tasks can be completed more quickly, improving overall efficiency. Therefore, There is also a certain weight, but it is relatively Smaller, The value of can be set to 0.1-0.5, indicating that the importance of distance is limited but not negligible. The setting of is 0.5-1.0, indicating that time urgency is more important. This range is chosen based on experience and actual operational needs to ensure that in most cases, the formula can reflect reasonable priority ranking.

[0023] S3: Obtain the total number of transport agents that can perform delivery tasks in the total area and the distance information between the center point of each sub-area and the delivery point of the total area, and combine the environmental data of the total area and the number of delivery tasks in each sub-area to generate the maximum delivery volume of each sub-area; The logic for determining the number of delivery tasks within each sub-region is: Divide the total area into sub-regions of the same area, and the area of ​​each sub-region is , determine the sub-region The vertex coordinates are represented by rectangles, and the sub-areas The lower left corner coordinates are , sub-area The upper right corner coordinates are , when Delivery location of tasks In sub-area If it is in the sub-area, it returns 1, and if it is not in the sub-area, it returns 0. The specific formula is: ; in, For the The number of delivery tasks within a sub-area.

[0024] The logic of the distance information between each sub-region center point and the total regional distribution point is: Sub-area The center coordinates of The calculation formula is: ; The calculation formula for the distance from the sub-region center point to the total regional distribution point is: ; in, For the The distance from the center point of each sub-region to the distribution point of the total region.

[0025] The formula for the maximum delivery volume of each sub-region is: ; in, For the The maximum delivery volume of a sub-region reflects the upper limit of the delivery tasks that can be completed for a specific sub-region under specific logistics conditions, which affects the efficiency of the entire distribution system. The size of the warehouse can optimize resource allocation, improve the efficiency of logistics distribution, reduce costs, and ensure delivery capabilities under different weather conditions. is the total number of transport agents that can perform delivery tasks in the total area, For the The number of delivery tasks within each sub-region, is weather environment data, independent variable and and Directly related, they represent available resources and demand respectively. , and It indirectly affects the distribution efficiency ,when and The bigger, The larger the value, the positive relationship is shown, which means that the richer the resources, the stronger the distribution capacity. and , the bigger, The smaller it is, the negative correlation is shown, and the deterioration of external conditions will reduce the ability of logistics distribution.

[0026] S4: Arrange the transport agent to deliver the tasks according to the task priority and maximum delivery volume of each area.

[0027] Arrange the number of delivery tasks in each sub-region in ascending order according to the priority of the delivery tasks to form a task priority delivery cluster sequence , ; in, For each task after sorting.

[0028] The task priority delivery cluster sequence is further modified by the maximum delivery volume to be modified into the task sequence , the revised logic is: No. The number of delivery tasks within a sub-region is , for each task in the task priority distribution cluster sequence , if In the sub-area ,Task Assign to sub-regions and update ; If In the sub-area , task skipping, corrected task sequence for: ; in, Indicates that the The sub-region tasks and meet .

[0029] The final revised task sequence can be expressed as: ; in, is the total number of sub-regions, Indicates Correction task sequence for each sub-area.

[0030] Assume that there are the following task data and sub-area data: Priority , Priority , Priority ; Maximum delivery volume for sub-area 1 , the maximum delivery volume for sub-area 2 ; The initial task priority distribution cluster sequence is: ; Modify the task sequence according to the maximum delivery volume, assuming that the task target delivery location is: Belongs to sub-area 1, Belongs to sub-area 1, Belongs to sub-area 2; Corrected task sequence For: Task sequence of sub-area 1 ; Task sequence for sub-area 2 ; The final combined task sequence is: ; See also Figure 2 The present invention also provides a multi-agent system efficient distribution task allocation system based on reinforcement learning, the distribution system is used to execute the above-mentioned multi-agent system efficient distribution task allocation method, including: A collection module, used to obtain the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, the demand data including the target delivery location of each task and the remaining time data for task execution, and the environmental data including the traffic condition coefficient and weather environment data of the total area; A data processing module is used to determine the priority of the delivery tasks according to the demand data corresponding to the delivery tasks, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; The distribution decision module is used to obtain the total number of transport agents that can perform distribution tasks in the total area and the distance information between the center point of each sub-area and the distribution point of the total area, and combine the environmental data of the total area and the number of distribution tasks in each sub-area to generate the maximum distribution volume of each sub-area; The task allocation module is used to arrange the transportation agent to carry out the delivery of tasks according to the task priority and maximum delivery volume of each area.

[0031] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0032] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0033] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0034] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An efficient distribution task allocation method for a multi-agent system based on reinforcement learning, characterized by: S1: Obtain the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, wherein the demand data includes the target delivery location of each task and the remaining time data for task execution, and the environmental data includes the traffic condition coefficient and weather environment data of the total area; S2: Determine the priority of the delivery task according to the demand data corresponding to the delivery task, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; S3: Obtain the total number of transport agents that can perform delivery tasks in the total area and the distance information between the center point of each sub-area and the delivery point of the total area, and combine the environmental data of the total area and the number of delivery tasks in each sub-area to generate the maximum delivery volume of each sub-area; The logic for determining the number of delivery tasks within each sub-region is: Divide the total area into sub-regions of the same area, and the area of ​​each sub-region is , determine the sub-region The vertex coordinates are represented by rectangles, and the sub-areas The coordinates of the lower left corner are , sub-area The upper right corner coordinates are , when Delivery location of tasks In sub-area If it is in the sub-area, it returns 1, and if it is not in the sub-area, it returns 0. The specific formula is: ； in, For the The number of delivery tasks within each sub-area; The logic of the distance information between each sub-region center point and the total regional distribution point is: Sub-area The center coordinates of The calculation formula is: ； The calculation formula for the distance from the sub-region center point to the total regional distribution point is: ； in, For the The distance from the center of each sub-region to the distribution point of the total region; The formula for the maximum delivery volume of each sub-region is: ； in, For the The maximum delivery volume for each sub-region, is the total number of transport agents that can perform delivery tasks in the total area, For the The number of delivery tasks within each sub-region, Weather environment data; S4: Arrange the transport agent to deliver the tasks according to the task priority and maximum delivery volume of each area.

2. According to claim 1, a method for efficient distribution task allocation of a multi-agent system based on reinforcement learning is characterized by: The step S1 comprises the following steps: S11, the method for obtaining the delivery location of each task target is: establish a plane coordinate system based on the total area of ​​the delivery task to be assigned, randomly select a point in the plane of the total area of ​​the delivery task to be assigned as the origin, and at the selected origin, take the north direction as Axis positive direction, perpendicular to The axis direction is Axis, according to the established plane coordinate system, determine the target delivery location coordinates of each task, denoted as ,in is the index of the delivery task, ,in The total number of tasks in the total area to be assigned delivery tasks; S12, the method for determining the remaining time data for task execution is: obtaining the timestamp of the current moment and the timestamp of the task deadline , based on the current timestamp and The timestamp of the task deadline Calculate the remaining time data for task execution, where the remaining time data is based on the formula: ； In the formula, To execute the remaining time data; S13, the The target delivery distance for each delivery task The calculation is based on the formula: ； in, is the current position coordinate; S14, the formula for calculating the traffic condition coefficient is: ； In the formula, is the traffic condition coefficient, is the agent flow, represents the average speed of the agent, and are the weight coefficients of agent flow and agent average speed respectively, where and are greater than 0, and ; S15, obtaining weather environment data in the total area to be assigned delivery tasks, using label encoding for the weather environment data, mapping sunny days, cloudy days and rainy days to integer form, where sunny days are mapped to 0, cloudy days are mapped to 1, and rainy days are mapped to 2.

3. The method for efficient distribution task allocation of a multi-agent system based on reinforcement learning according to claim 1 is characterized by: The formula for determining the priority of delivery tasks is: ； In the formula, For the The priority of each delivery task, Indicates The target delivery distance for a delivery task, For the The remaining execution time data of each delivery task.

4. According to claim 1, a method for efficient distribution task allocation of a multi-agent system based on reinforcement learning is characterized by: Arrange the number of delivery tasks in each sub-region in ascending order according to the priority of the delivery tasks to form a task priority delivery cluster sequence , ； in, For each task after sorting.

5. The method for efficient distribution task allocation of a multi-agent system based on reinforcement learning according to claim 4 is characterized by: The task priority delivery cluster sequence is further modified by the maximum delivery volume to be modified into the task sequence , the revised logic is: No. The number of delivery tasks within a sub-region is , for each task in the task priority distribution cluster sequence , if In the sub-area ,Task Assign to sub-regions and update ; If In the sub-area , task skipping, corrected task sequence for: ； in, Indicates that the The sub-region tasks and meet .

6. An efficient distribution task allocation system for a multi-agent system based on reinforcement learning, characterized by: The distribution system is used to execute the multi-agent system efficient distribution task distribution method according to any one of claims 1 to 5, comprising: A collection module, used to obtain the number of tasks in the total area to be assigned, demand data and environmental data corresponding to the tasks, the demand data including the target delivery location of each task and the remaining time data for task execution, and the environmental data including the traffic condition coefficient and weather environment data of the total area; A data processing module is used to determine the priority of the delivery tasks according to the demand data corresponding to the delivery tasks, divide the total area into multiple sub-areas of equal area, and determine the number of delivery tasks in each sub-area according to the target delivery location information of each task; The distribution decision module is used to obtain the total number of transport agents that can perform distribution tasks in the total area and the distance information between the center point of each sub-area and the distribution point of the total area, and combine the environmental data of the total area and the number of distribution tasks in each sub-area to generate the maximum distribution volume of each sub-area; The task allocation module is used to arrange the transportation agent to carry out the delivery of tasks according to the task priority and maximum delivery volume of each area.

Images