Unmanned aerial vehicle cluster collaborative task allocation method and system based on cluster optimization

Abstract

The invention relates to the technical field of collaborative optimization task allocation, in particular to an unmanned aerial vehicle cluster collaborative task allocation method and system based on cluster optimization, and the method comprises the following steps: comparing and calculating the matching degree of a task and an unmanned aerial vehicle based on the task emergency degree, the resource demand and the task time limit in combination with the electric quantity, the flight distance and the current position of the unmanned aerial vehicle; analyzing the relevance of the unmanned aerial vehicle and the task through the matching degree, and generating an initial adaptation degree parameter of the task and the unmanned aerial vehicle; according to the method, task execution and path planning are integrated by matching task resource requirements and unmanned aerial vehicle loading capacity, combining resource sharing and time sequence constraint to optimize resource allocation, analyzing and determining task relevance according to task area coupling strength, optimizing resource competition and dynamically adjusting path time consumption and a task sequence; through path reconstruction and state adjustment, resource waste is reduced, task allocation continuity and resource utilization rate are improved, and adaptability and collaboration of an unmanned aerial vehicle cluster in a complex environment are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative optimization task allocation, and particularly to a method and system for collaborative task allocation of an unmanned aerial vehicle (UAV) cluster based on cluster optimization. Background Art

[0002] The technical field of collaborative optimization task allocation includes methods and theories for task allocation and resource optimization in multi-agent systems, and is widely applied in fields such as UAV clusters, intelligent transportation, and industrial production. The core content of this technical field is to achieve the efficient operation of complex systems by coordinating and optimizing the behaviors of multiple individuals. The research directions of collaborative optimization task allocation mainly include task decomposition, resource matching, path planning, and collaborative execution, etc. Its technical implementation methods usually adopt mathematical modeling, optimization algorithms, and distributed control methods, with the focus on solving the problems of resource competition and collaboration efficiency among multiple agents, while ensuring the robustness and stability of the overall system.

[0003] Among them, the method for collaborative task allocation of a UAV cluster based on cluster optimization refers to a specific method for designing the task allocation and execution process by using cluster optimization technology for the task collaboration problem in a UAV cluster. The technical matters of this patent theme cover the decomposition of task requirements, the design of task allocation rules among UAVs, and the construction of an allocation model based on cluster optimization. Specifically, based on the construction of a multi-objective optimization model, a task allocation scheme is designed in combination with the task characteristics of the UAV cluster, and the task allocation result is achieved through iterative solution by a specific optimization algorithm. The task allocation process involves the quantitative modeling of task priorities, UAV performance, and flight constraint conditions, etc., and the allocation relationship between tasks and UAVs is determined through model solution.

[0004] The prior art is difficult to effectively handle the coupling strength problem between tasks in task allocation, and often lacks a systematic analysis of resource sharing requirements, resulting in conflicts or resource waste easily occurring during task execution. In the path planning link, most technologies do not consider the dynamic influence of flight speed and path duration on the task execution order, and the path node sorting is not fully adapted to task requirements, which may cause problems such as time delay and a decrease in task execution efficiency. At the same time, when dealing with the dynamic changes of task states, most of the prior art lacks an effective path reconstruction mechanism and lacks the real-time response ability to the path deviation problem of uncompleted tasks, resulting in the interruption of some task executions, further affecting the overall scheduling efficiency of UAV resources. These deficiencies limit the practicality of the prior art in dealing with multi-task complex scenarios, and also lead to a significant reduction in the collaboration and stability of task allocation in a dynamic environment. Summary of the Invention

[0005] The object of the present invention is to solve the deficiencies existing in the prior art, and to propose a method and system for collaborative task allocation of a UAV cluster based on cluster optimization.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A method for collaborative task allocation of an unmanned aerial vehicle (UAV) cluster based on cluster optimization, comprising the following steps: S1: Based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the UAV, compare and calculate the matching degree between the task and the UAV, analyze the relevance between the UAV and the task through the matching degree, and generate the initial matching degree parameters between the task and the UAV; S2: Based on the initial matching degree parameters between the task and the UAV, analyze the coverage range of the UAV position and the task center position, evaluate the UAV coverage ability using the endurance and flight time limit, compare and analyze the number of UAVs and the number of tasks, perform task allocation processing, and generate the UAV distribution ratio data in the task area; S3: Based on the UAV distribution ratio data in the task area, calculate the matching between the task resource requirements and the UAV load capacity, analyze the task resource sharing requirements and timing constraints, analyze the coupling strength of the task area through resource competition and coupling relationships, and generate the resource coupling strength parameters in the task area; S4: Based on the resource coupling strength parameters in the task area, combined with the analysis of the UAV flight speed and path time consumption, adjust the execution order of the UAV tasks, optimize the task time distribution through the relationship between timing and path time consumption, and generate the UAV task time distribution path data; S5: Based on the UAV task time distribution path data, combined with the analysis of the task execution status and path deviation, adjust the execution path of the unfinished tasks, update the UAV flight plan, identify the task requirements, and generate the UAV task path reconstruction data.

[0007] As a further solution of the present invention, the initial matching degree parameters between the task and the UAV include task priority parameters, UAV remaining battery power parameters, and UAV task matching coefficients. The UAV distribution ratio data in the task area includes UAV coverage radius, task distribution density parameters, and UAV-task ratio coefficients. The resource coupling strength parameters in the task area include task-inter resource competition indicators, task coupling strength coefficients, and timing relevance parameters. The UAV task time distribution path data includes path node time distribution, UAV task sorting parameters, and path time optimization indices. The UAV task path reconstruction data includes task execution path node adjustment results, path deviation correction coefficients, and flight plan update data.

[0008] As a further solution of the present invention, the specific steps for generating the initial matching degree parameters between the task and the UAV based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the UAV, comparing and calculating the matching degree between the task and the UAV, and analyzing the relevance between the UAV and the task through the matching degree are as follows: S101: Based on the task urgency, resource requirements, and task time limit, perform priority sorting according to the task criticality in terms of time limit urgency and resource requirements, classify and label task numbers based on the sorting results, and integrate and analyze the parameters of the tasks to generate a task parameter table; S102: Based on the task parameter table, calculate the reachable range according to the battery power and flight distance of the drone, perform spatial distance matching between the current position of the drone and the geographical location coordinates of the task, screen the task range based on the resource carrying capacity of the drone, integrate and analyze the drone parameter and task parameter data, and generate a task matching parameter table; S103: Based on the task matching parameter table, sort the drones and tasks from high to low according to the task priority, analyze the matching between the remaining battery power and flight distance of the drone and the task requirements, calculate the adaptability score, and perform screening and allocation in combination with the task number and drone parameters to generate the initial adaptability parameters of the task and the drone.

[0009] As a further solution of the present invention, based on the initial adaptability parameters of the task and the drone, analyze the coverage range between the drone position and the task center position, evaluate the coverage ability of the drone using the endurance and flight time limit, compare and analyze the number of drones and the number of tasks, and the specific steps for performing task allocation processing and generating the drone distribution ratio data in the task area are as follows: S201: Based on the initial adaptability parameters of the task and the drone, calculate the distance between the current position of the drone and the geographical coordinates of the task center position, calculate and mark the reachable position range of the drone flight radius for the task area, and perform matching and classification on the task number in combination with the coverage range data to generate the drone coverage range data; S202: Based on the drone coverage range data, analyze the coverage effectiveness in combination with the drone endurance time and the geographical distribution distance of the task, evaluate the time and position coverage ability of the task area based on the flight time limit and the flight radius, and generate the drone coverage ability data; S203: Based on the drone coverage ability data, perform comparison and allocation processing on the number of drones and the number of tasks according to the drone coverage ability and task requirements, match the coverage ratio according to the effective coverage range of the drone and the task number distribution, integrate the drone number and the task area coverage data, and generate the drone distribution ratio data in the task area.

[0010] As a further solution of the present invention, based on the drone distribution ratio data in the task area, calculate the matching between the task resource requirements and the load capacity of the drone, analyze the task resource sharing requirements and timing constraints, analyze the coupling strength of the task area through resource competition and coupling relationships, and the specific steps for generating the resource coupling strength parameters in the task area are as follows: S301: Based on the UAV distribution ratio data in the task area, calculate the matching ratio of the UAV load capacity and the task resource requirements item by item according to the corresponding relationship between the task resource demand parameters and the UAV load capacity, and analyze the UAV load capacity range and the task resource requirements pair by pair to generate the task-UAV load matching data; S302: Based on the task-UAV load matching data, conduct a classification analysis of the types and quantities of resources for the task resource sharing requirements, compare the distribution of resource requirements according to the task time nodes, associate the sharing resource allocation with the time constraints, and analyze the resource usage time conflicts to generate the task resource sharing and timing data; S303: Based on the task resource sharing and timing data, analyze the resource competition relationship and coupling relationship item by item according to the cross relationship and time allocation constraints of the task resource sharing, and calculate the resource coupling intensity value in the task area based on the resource distribution data to generate the resource coupling intensity parameter in the task area.

[0011] As a further solution of the present invention, the specific formula for calculating the resource coupling intensity value is: ; Wherein, represents the resource coupling intensity value, represents the initial allocation value of the resource with the task number , represents the adjusted allocation value of the resource with the task number , represents the total time allocation of the task with the task number , represents the total number of tasks.

[0012] As a further solution of the present invention, based on the resource coupling intensity parameter in the task area, combined with the analysis of the flight speed and path time consumption of the UAV, adjust the execution order of the UAV tasks, optimize the task time distribution through the relationship between the time sequence and the path time consumption, and the specific steps for generating the UAV task time distribution path data are: S401: Based on the resource coupling intensity parameter in the task area, extract the UAV flight speed and the task geographical location, calculate the path time consumption of the UAV from the current position to the task point in segments, and conduct allocation and sorting analysis on the path time consumption data in combination with the task priority to generate the UAV task path time consumption data; S402: Based on the UAV task path time consumption data, analyze and adjust the UAV task execution order according to the path time consumption and the task geographical location, compare the path time distribution of the task with the task time nodes, adjust and analyze the task time interval and the task allocation order to generate the UAV task time sequence adjustment data; S403: Based on the UAV mission timing adjustment data, extract the mission adjustment sequence and path time distribution, combine and analyze the path information and time distribution of the UAV mission, integrate the path time data and mission sequence information, process the time interval allocation and path optimization, and generate the UAV mission time distribution path data.

[0013] As a further solution of the present invention, the calculation formula of the path time-consuming parameter is specifically: ; Wherein, represents the path time-consuming parameter, represents the path distance of the UAV on the horizontal axis of the geographical coordinates, represents the path distance of the UAV on the vertical axis of the geographical coordinates, represents the flight speed of the UAV in the horizontal axis direction, represents the flight speed of the UAV in the vertical axis direction, represents the weight of the resources required for the mission, represents the current load of the UAV, represents the maximum load capacity of the UAV.

[0014] As a further solution of the present invention, based on the UAV mission time distribution path data, combined with the mission execution status and path deviation analysis, the specific steps for adjusting the execution path of the unfinished mission, updating the flight plan of the UAV, identifying the mission requirements, and generating the UAV mission path reconstruction data are as follows: S501: Based on the UAV mission time distribution path data, extract the mission execution status and the current position of the UAV, calculate the path deviation of the unfinished mission, associate and analyze the path deviation and the mission geographical location, classify and sort the path deviation and mission execution status, and generate the UAV mission path deviation data; S502: Based on the UAV mission path deviation data, extract the flight speed of the UAV and the remaining mission time, calculate the path adjustment value, compare and analyze the path adjustment result and the remaining mission time node, and generate the UAV mission adjusted path data; S503: Based on the UAV mission adjusted path data, analyze the adjusted path and mission time distribution, update the time node data after path optimization and the flight plan of the UAV, identify and integrate the path adjustment and time distribution data, and generate the UAV mission path reconstruction data.

[0015] The UAV swarm cooperative mission allocation system based on cluster optimization includes: The initial adaptation module, based on the mission urgency, resource requirements and mission time limit, combines the battery power, flight distance and current position of the UAV, compares and calculates the matching degree between the mission and the UAV, and generates the initial adaptation degree parameter of the mission and the UAV; Based on the initial adaptation degree parameter of the task and the UAV, the coverage ability module analyzes the coverage ranges of the UAV position and the task center position, evaluates the coverage ability of the UAV by using the endurance and the upper limit of flight time, conducts task assignment processing, and generates data on the distribution ratio of UAVs in the task area; Based on the data on the distribution ratio of UAVs in the task area, the resource matching module calculates the matching between the task resource requirements and the payload capacity of the UAV, analyzes the coupling strength of the task area through resource competition and coupling relationships, and generates a resource coupling strength parameter within the task area; Based on the resource coupling strength parameter within the task area, the timing optimization module combines the flight speed of the UAV and the path time consumption analysis, optimizes the task time distribution through the relationship between timing and path time consumption, and generates UAV task time distribution path data; Based on the UAV task time distribution path data, the path reconstruction module combines the task execution status and path deviation analysis, adjusts the execution paths of unfinished tasks, updates the flight plan of the UAV, and generates UAV task path reconstruction data.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by matching the task resource requirements with the payload capacity of the UAV, optimizing resource allocation by combining resource sharing and timing constraints, analyzing the coupling strength of the task area to clarify task relevance, optimizing resource competition, dynamically adjusting path time consumption and task order, integrating task execution and path planning is realized. Through path reconstruction and status adjustment, resource waste is reduced, the continuity of task assignment and resource utilization rate are improved, and the adaptability and cooperation of the UAV cluster in complex environments are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of the step flow of the present invention; Figure 2 is a flowchart of step S1 of the present invention; Figure 3 is a flowchart of step S2 of the present invention; Figure 4 is a flowchart of step S3 of the present invention; Figure 5 is a flowchart of step S4 of the present invention; Figure 6 is a flowchart of step S5 of the present invention; Figure 7 is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0019] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically defined.

[0020] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily construed as being more preferred or having more advantages than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those skilled in the art can realize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present application.

[0021] Please refer to Figure 1 , a method for collaborative task allocation of an unmanned aerial vehicle (UAV) cluster based on cluster optimization, comprising the following steps: S1: Based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the UAV, compare and calculate the matching degree between the task and the UAV, analyze the relevance between the UAV and the task through the matching degree, and generate the initial adaptation degree parameters of the task and the UAV; S2: Based on the initial adaptation degree parameters of the task and the UAV, analyze the coverage range of the UAV position and the task center position, evaluate the coverage ability of the UAV using the endurance and flight time limit, compare and analyze the number of UAVs and the number of tasks, perform task allocation processing, and generate the UAV distribution ratio data in the task area; S3: Based on the UAV distribution ratio data in the task area, calculate the matching between the task resource requirements and the UAV load capacity, analyze the task resource sharing requirements and timing constraints, analyze the coupling strength of the task area through resource competition and coupling relationships, and generate the resource coupling strength parameters in the task area; S4: Based on the resource coupling intensity parameters within the task area, combined with the analysis of the flight speed and path time consumption of the UAV, adjust the execution order of the UAV tasks, optimize the task time distribution through the relationship between time sequence and path time consumption, and generate the UAV task time distribution path data; S5: Based on the UAV task time distribution path data, combined with the analysis of the task execution status and path deviation, adjust the execution paths of the unfinished tasks, update the flight plan of the UAV, identify the task requirements, and generate the UAV task path reconstruction data.

[0022] The initial adaptation degree parameters between the task and the UAV include task priority parameters, remaining battery power parameters of the UAV, and UAV task matching coefficients. The UAV distribution ratio data in the task area includes UAV coverage radius, task distribution density parameters, and UAV-task ratio coefficients. The resource coupling intensity parameters within the task area include task-inter resource competition indicators, task coupling intensity coefficients, and time sequence correlation parameters. The UAV task time distribution path data includes path node time distribution, UAV task sorting parameters, and path time optimization index. The UAV task path reconstruction data includes task execution path node adjustment results, path deviation correction coefficients, and flight plan update data.

[0023] Please refer to Figure 2 , the specific steps of S1 are as follows: S101: Based on the task urgency, resource requirements, and task time limit, perform priority sorting according to the task criticality in terms of time limit urgency and resource requirements, classify and label the task numbers according to the sorting results, and integrate and analyze the task parameters to generate a task parameter table; By extracting and sorting out the parameters of the tasks, using the priority sorting of the tasks as the basis, first extract the time limit values and resource requirement parameters of each task, quantify the task time limit urgency, set the time classification interval, screen and classify the resource requirements by analyzing the types and quantities of resources required for the tasks, then calculate the criticality sorting value according to the weight ratio of the task urgency and resource requirement parameters, evaluate the matching relationship between the urgency and resource requirements through the calculation formula, and finally classify and label the tasks in combination with the task numbers and generate the corresponding task parameter table.

[0024] S102: Based on the task parameter table, calculate its reachable range according to the battery power and flight distance of the UAV, perform spatial distance matching between the current position of the UAV and the geographical location coordinates of the tasks, screen the task range according to the resource carrying capacity of the UAV, integrate and analyze the UAV parameter and task parameter data, and generate a task matching parameter table; Analyze the remaining battery level value at the current position of the drone and obtain the available flight distance in combination with the battery parameters. Calculate the spatial distance between the geographical location coordinates of the task and the current position coordinates of the drone. Extract the matching task range according to the formula, screen the task list suitable for the drone's carrying capacity, compare item by item through the drone's load capacity parameters and task resource requirements, eliminate tasks whose resource requirements exceed the drone's carrying capacity, conduct a comprehensive analysis of the parameter relationship between the task and the drone and record it, and generate a task matching parameter table after integrating the results.

[0025] S103: Based on the task matching parameter table, sort the drones and tasks from high to low according to the task priority, analyze the matching of the remaining battery level and flight distance of the drone with the task requirements, calculate the adaptability score, and conduct screening and allocation in combination with the task number and drone parameters to generate the initial adaptability parameters of the task and the drone; Sort the drones and tasks from high to low according to the task priority, analyze the matching of the remaining battery level and flight distance of the drone with the task requirements, calculate the adaptability score, according to the formula ; Calculate the adaptability score.

[0026] In the formula, represents the adaptability score between the drone and the task, represents the remaining flight distance of the drone, represents the spatial distance of the task location, represents the remaining battery level of the drone, represents the maximum capacity of the drone's battery.

[0027] The flight distance and remaining battery level of the drone are obtained through the real-time monitoring module of the drone. The spatial distance of the task is calculated by the Euclidean distance formula between the task geographical coordinates and the current position coordinates of the drone. Assuming that the remaining flight distance of the drone is 5000 meters, the distance of the task location is 4000 meters, the remaining battery level is 60 watt-hours, and the maximum battery capacity is 100 watt-hours, the formula calculation is as follows: Calculation of the ratio of the remaining flight distance to the task distance: ; Calculation of the ratio of the remaining battery level to the maximum battery level: ; Calculation of the comprehensive adaptability score: ; The result shows that the current remaining battery level and flight distance of the drone can meet the task requirements, and its adaptability score is 0.75, indicating a relatively high task adaptability. Combined with the priority sorting value, the matching tasks can be further screened.

[0028] Please refer to Figure 3 , the specific steps of S2 are as follows: S201: Based on the initial adaptation degree parameters of the task and the drone, calculate the distance between the current position of the drone and the geographical coordinates of the task center position, calculate and mark the range of positions that the flight radius of the drone can cover in the task area, match and classify the task numbers in combination with the coverage range data, and generate the drone coverage range data; By extracting the geographical coordinates of the current position of the drone and the task center position, calculate the spatial distance between the current position of the drone and the task center position, convert and mark the flight radius using the earth's radius as a geographical reference parameter, deduce the flight radius according to the remaining power and battery capacity of the drone, convert the flight radius into the polygon area coordinate data of the coverage range, judge whether the target task area is covered by matching with the task area position, and classify and mark item by item in combination with the task number, and generate the task number and classification information corresponding to the drone coverage range, so as to generate the drone coverage range data.

[0029] S202: Based on the drone coverage range data, analyze the coverage effectiveness in combination with the drone endurance time and the task geographical distribution distance, evaluate the time and position coverage capabilities of the task area according to the flight time limit and the flight radius, and generate the drone coverage capability data; Calculate the coverage effectiveness through the parameters of the drone flight time limit and the task geographical distribution distance, extract the battery endurance time parameter of the drone and verify the flight ability in combination with the flight distance, screen and locate the task numbers within the coverage range in combination with the coordinate data of the task area, analyze whether the flight time limit meets the coverage requirements of all task points in the task area, calculate the effective coverage radius according to the drone flight speed and time parameters, and evaluate the coverage effectiveness through the spatial relationship between the geographical coordinate data within the coverage range and the flight radius, and finally generate the drone coverage capability data.

[0030] S203: Based on the drone coverage capability data, compare and allocate the number of drones and the number of tasks according to the drone coverage capability and the task requirements, match the coverage ratio according to the effective coverage range of the drone and the task number distribution, integrate the drone number and the task area coverage data, and generate the task area drone distribution ratio data; Compare and allocate the number of drones and the number of tasks according to the drone coverage capability and the task requirements, match the coverage ratio according to the effective coverage range of the drone and the task number distribution, and according to the formula ; Calculate the drone coverage ratio data of the task area.

[0031] In the formula, The drone coverage ratio representing the task area, represents the total area covered by the drones, represents the total area of the task area, represents the number of drones within the task area, represents the total number of tasks.

[0032] The area covered by the drones is calculated based on the flight radius, and the total area of the task area is extracted from the task coordinate points and the area range. Assuming the area covered by the drones is 100 square kilometers, the area of the task area is 200 square kilometers, the number of drones within the task area is 10, and the total number of tasks is 20, the formula calculation is as follows: Calculate the ratio of the area covered by the drones to the area of the task area: ; Calculate the ratio of the number of drones in the task area to the total number of tasks: ; Comprehensive coverage ratio calculation: ; The result shows that the drone coverage ratio is 0.25, that is, the current distribution matching of drones with the number of tasks and the task area range is 25%, which can be used for further allocation and adjustment of task and drone resources.

[0033] Please refer to Figure 4 , the specific steps of S3 are as follows: S301: Based on the drone distribution ratio data in the task area, according to the corresponding relationship between the task resource demand parameters and the drone load capacity, calculate the matching ratio of the drone load capacity to the task required resources item by item, and analyze the drone load capacity range and the task resource demand pair by pair to generate task and drone load matching data; Extract the task resource demand parameters and the drone load capacity parameters, standardize the basic data of the drone load capacity, calculate the matching degree of the drone through the ratio of the load capacity to the weight of the task required resources, establish a matrix using the load capacity and resource demand corresponding to the drone number and the task number respectively, map the initial matching result of the drone and the task through the matrix, analyze the difference between the drone load capacity range and the task resource demand item by item, mark the relationship between the mismatched task number and the drone number, and generate task and drone load matching data.

[0034] S302: Based on the task and UAV load matching data, conduct a classification analysis of the types and quantities of resources for the task resource sharing requirements. Compare the distribution of resource requirements according to the task time nodes, associate the sharing resource allocation with time constraints, and analyze the resource usage time conflicts to generate task resource sharing and timing data. Classify and analyze the types and quantities of resources required for the task in combination with the task resource sharing requirements, extract the task time node data and resource distribution quantities, match them according to the time priority and spatial distribution order of resource requirements, associate the sharing resource allocation with time constraints, compare the resource demand quantities in different task time periods, analyze the conflicts in resource usage time between different tasks within the same time period, mark the resource numbers of conflicting tasks through an allocation matrix, and finally integrate the task resource allocation situation to generate task resource sharing and timing data.

[0035] S303: Based on the task resource sharing and timing data, analyze the resource competition relationship and coupling relationship item by item according to the cross relationship and time allocation constraints of task resource sharing. Calculate the resource coupling strength value within the task area based on the resource distribution data to generate the resource coupling strength parameter within the task area. The specific formula for the resource coupling strength value is: ; Among them, represents the resource coupling strength value, represents the initial allocation value of the resource with task number , represents the adjusted allocation value of the resource with task number , represents the total time allocation of the task with task number , represents the total number of tasks.

[0036] The resource coupling strength value represents a comprehensive measure of the resource allocation difference and time constraint within the task area. It is obtained by calculating the difference value before and after the adjustment of the task resource distribution, normalizing the time constraint and then finding the sum of squares, and finally performing a square root operation. The formula contains the following parameters: is the initial allocation value of the resource with task number , in tons, taken from the initial resource allocation value in the task allocation table and monitored through the task demand acquisition module. For example, it is obtained by statistically analyzing the actual demand for materials at each task point and the capacity of the transportation vehicle.

[0037] is the task number The resource adjustment and allocation value, in tons, reflects the final allocation status of task resources and is obtained through the resource dynamic adjustment plan. For example, the resource value reallocated in combination with task priorities.

[0038] is the task number The total time allocation, in hours, is obtained from the task time allocation value recorded by the task scheduling system. For example, the time difference between the start time and end time of the task.

[0039] is the total number of tasks, taken from the total number of tasks counted in the task allocation table.

[0040] The specific calculation process is as follows: Assume the total number of tasks is , and the parameter values for each task are as follows: tons, tons, hours tons, tons, hours tons, tons, hours Calculation steps: Calculate the absolute value normalized time allocation of the resource allocation difference for each task: ; ; ; Square the results and sum them up: ; ; Calculate the square root to obtain the resource coupling strength value: ; This result shows that the resource coupling strength value in the task area is 0.6418, reflecting the comprehensive relationship between the difference in resource allocation among different tasks and time constraints during the resource adjustment process. This value provides a measurement basis for resource optimal allocation and can be used to further analyze the resource scheduling efficiency and rationality in the task area.

[0041] Please refer to Figure 5 , and the specific steps of S4 are as follows: S401: Based on the resource coupling intensity parameters within the task area, extract the UAV flight speed and task geographical location, calculate the path time-consuming parameters for the UAV from the current position to the task point in segments, and perform allocation and sorting analysis on the path time-consuming data in combination with the task priority to generate the UAV task path time-consuming data; The specific calculation formula for the path time-consuming parameters is as follows: ; Among them, represents the path time-consuming parameter, represents the path distance of the UAV on the horizontal axis of the geographical coordinates, represents the path distance of the UAV on the vertical axis of the geographical coordinates, represents the flight speed of the UAV in the horizontal axis direction, represents the flight speed of the UAV in the vertical axis direction, represents the weight of the resources required for the task, represents the current load of the UAV, represents the maximum load capacity of the UAV.

[0042] The path time-consuming parameter represents the flight time of the UAV on the path from the current position to the task point, and is comprehensively calculated in combination with the flight speed, path distance of the UAV in different axial directions and the load impact of the task resource requirements. The meanings of the parameters in the formula are as follows: : The path distance of the UAV on the horizontal axis of the geographical coordinates, in meters, is obtained by calculating the difference between the horizontal axis coordinates of the UAV's current position and the task point through GPS positioning.

[0043] : The path distance of the UAV on the vertical axis of the geographical coordinates, in meters, is obtained by calculating the difference between the vertical axis coordinates of the UAV's current position and the task point through GPS positioning.

[0044] : The flight speed of the UAV in the horizontal axis direction, in meters per second, is obtained from the monitoring data of the UAV speed sensor.

[0045] : The flight speed of the UAV in the vertical axis direction, in meters per second, is obtained from the monitoring data of the UAV speed sensor.

[0046] : The weight of the resources required for the task, in kilograms, is obtained from the resource requirement data in the task allocation table.

[0047] : The current load of the UAV, in kilograms, is obtained through the UAV load sensor.

[0048] : The maximum load capacity of the drone, in kilograms, is obtained from the drone technical parameter table.

[0049] The specific calculation process is as follows: Assume that the current position coordinates of the drone are meters, and the coordinates of the task point are meters. The flight speed of the drone in the horizontal axis direction is meters per second, and the flight speed in the vertical axis direction is meters per second. The weight of the resources required for the task is kilograms, the current load of the drone is kilograms, and the maximum load capacity of the drone is kilograms.

[0050] Calculate the path distances in the horizontal and vertical axes: ; Calculate the path time components: ; Calculate the comprehensive path time component: ; Calculate the resource load impact component: ; Comprehensive path time-consuming parameter: ; This result indicates that the path time-consuming parameter for the drone to fly from the current position to the task point considering the resource load difference is 28.288 seconds. This value synthesizes the path distance, flight speed, and load impact, providing an important basis for the allocation and sorting of the task path time-consuming, and can be further used to optimize task scheduling and drone resource allocation.

[0051] S402: Based on the drone task path time-consuming data, analyze and adjust the path time-consuming and task geographical location for the drone task execution order. Compare the path time distribution of the tasks with the task time nodes, adjust and analyze the task time interval and task allocation order, and generate drone task timing adjustment data; Extract the path time distribution and task geographical location data, compare the path time of the tasks with the task node time, adjust the path time-consuming and task execution time according to the drone task execution order, analyze the time interval between different task paths, optimize the path order for the tasks with insufficient time intervals through the reordering method, calculate the adjustment result through the time difference between the task node and the path time, and reallocate the task execution order according to the adjusted path time, and finally generate drone task timing adjustment data.

[0052] S403: Based on the adjusted data of the UAV mission time sequence, extract the mission adjustment order and path time distribution, combine and analyze the path information and time distribution of the UAV mission, integrate the path time data and mission order information, process the time interval allocation and path optimization, and generate the UAV mission time distribution path data; Combined with the path time distribution and mission order data, by extracting the UAV flight path coordinates and task point location coordinates, optimize the path time distribution, match the UAV path time with the mission time interval, analyze the relationship between time interval allocation and path intersection, optimize the UAV mission time distribution through the shortest path calculation method, adjust the relationship between the mission time node and the path time sequence, and integrate the optimized path time and mission order information to generate the UAV mission time distribution path data.

[0053] Please refer to Figure 6 , the specific steps of S5 are as follows: S501: Based on the UAV mission time distribution path data, extract the mission execution status and the current UAV position, calculate the path offset of the uncompleted mission, associate and analyze the path offset and the mission geographical location, classify and organize the path offset and mission execution status, and generate the UAV mission path offset data; Through the UAV path offset calculation model, calculate the difference between the current UAV position and the standard path of the task point, record and quantify the magnitude of the path offset, associate and analyze the path offset with the geographical location coordinates of the task point, classify and organize the path offset data by calculating the relationship between the offset and the mission execution time, and organize and label the classification results of the path offset of the task point path and the mission execution status to generate the UAV mission path offset data.

[0054] S502: Based on the UAV mission path offset data, extract the UAV flight speed and the remaining mission time, calculate the path adjustment value, compare and analyze the path adjustment result and the remaining mission time node, and generate the UAV mission adjusted path data; Calculate the path adjustment value according to the formula ; Calculate the path adjustment data.

[0055] In the formula, represents the path adjustment value, represents the offset path length from the current UAV position to the task point, represents the original path length of the task point, represents the flight speed of the UAV, represents the remaining time required for path adjustment, represents the total time of the mission.

[0056] The offset path length between the current position of the UAV and the task point is calculated through coordinate offset. The original path length of the task point is the reference data for the planned path. The flight speed of the UAV is obtained through the real-time monitoring module of the aircraft. The time required for path adjustment and the total task time are extracted from the task assignment table. Assume that the offset path length from the current position of the UAV to the task point is 1500 meters, the original path length of the task point is 1000 meters, the flight speed of the UAV is 25 meters per second, the remaining time for path adjustment is 120 seconds, and the total task time is 360 seconds. Then the calculation process is as follows: Calculate the path offset adjustment time: ; Calculate the ratio of the remaining path time: ; Comprehensive path adjustment value: ; This result indicates that the adjustment value of the UAV path is 20.3333 units, indicating that the current path needs to be adjusted appropriately, and the path and task assignment order can be further optimized according to the adjustment value.

[0057] S503: Based on the UAV task adjustment path data, analyze the adjusted path and task time distribution, update the time node data after path optimization and the flight plan of the UAV, identify and integrate the path adjustment and time distribution data, and generate the UAV task path reconstruction data; By extracting the task adjustment order and path time distribution, match the adjusted path coordinates with the task time nodes, update the time information after path optimization through the time node data in the UAV task assignment table, analyze the relationship between path adjustment and task time distribution, integrate the optimized path time data and the flight plan of the UAV task, re-label the optimized time nodes and path data, and finally generate the UAV task path reconstruction data.

[0058] Please refer to Figure 7 , the UAV swarm collaborative task assignment system based on cluster optimization, including: The initial adaptation module, based on the task urgency, resource requirements, and task time limit, combines the battery power, flight distance, and current position of the UAV, compares and calculates the matching degree between the task and the UAV, and generates the initial adaptation degree parameters of the task and the UAV; The coverage ability module, based on the initial adaptation degree parameters of the task and the UAV, analyzes the coverage range between the UAV position and the task center position, evaluates the UAV coverage ability using the endurance and flight time upper limit, performs task assignment processing, and generates the UAV distribution ratio data in the task area; The resource matching module calculates the matching between the task resource requirements and the drone load capacity based on the drone distribution ratio data in the task area, analyzes the coupling strength of the task area through resource competition and coupling relationships, and generates the resource coupling strength parameters within the task area; The timing optimization module optimizes the task time distribution based on the resource coupling strength parameters in the task area, combined with the flight speed and path time consumption analysis of the drones, and generates the drone task time distribution path data through the relationship between timing and path time consumption; The path reconstruction module adjusts the execution paths of the unfinished tasks based on the drone task time distribution path data, combined with the task execution status and path deviation analysis, updates the flight plans of the drones, and generates the drone task path reconstruction data.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. A method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization, characterized in that, It includes the following steps: S1: Based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the drone, compare and calculate the matching degree between the task and the drone, analyze the relevance between the drone and the task through the matching degree, and generate the initial matching degree parameters of the task and the drone; S2: Based on the initial matching degree parameters of the task and the drone, analyze the coverage range of the drone position and the task center position, evaluate the coverage ability of the drone using the endurance and flight time limit, compare and analyze the number of drones and the number of tasks, perform task allocation processing, and generate the drone distribution ratio data in the task area; S3: Based on the drone distribution ratio data in the task area, calculate the matching between the task resource requirements and the drone load capacity, analyze the task resource sharing requirements and timing constraints, analyze the coupling strength of the task area through resource competition and coupling relationships, and generate the resource coupling strength parameters in the task area; S4: Based on the resource coupling strength parameters in the task area, combined with the analysis of the flight speed and path time consumption of the drone, adjust the execution order of the drone tasks, optimize the task time distribution through the relationship between timing and path time consumption, and generate the drone task time distribution path data; S5: Based on the drone task time distribution path data, combined with the analysis of the task execution status and path deviation, adjust the execution path of the unfinished tasks, update the flight plan of the drone, identify the task requirements, and generate the drone task path reconstruction data.

2. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, wherein The initial matching degree parameters of the task and the drone include task priority parameters, drone remaining battery parameters, and drone task matching coefficients. The drone distribution ratio data in the task area includes drone coverage radius, task distribution density parameters, and drone-task ratio coefficients. The resource coupling strength parameters in the task area include inter-task resource competition indicators, task coupling strength coefficients, and timing relevance parameters. The drone task time distribution path data includes path node time distribution, drone task sorting parameters, and path time optimization indices. The drone task path reconstruction data includes task execution path node adjustment results, path deviation correction coefficients, and flight plan update data.

3. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, wherein The specific steps for generating the initial matching degree parameters of the task and the drone based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the drone, comparing and calculating the matching degree between the task and the drone, and analyzing the relevance between the drone and the task through the matching degree are as follows: S101: Based on the task urgency, resource requirements, and task time limit, perform priority sorting according to the task criticality in terms of time limit urgency and resource requirements, classify and label the task numbers according to the sorting results, and integrate and analyze the task parameters to generate a task parameter table; S102: Based on the task parameter table, calculate its reachable range according to the battery power and flight distance of the drone, perform spatial distance matching between the current position of the drone and the geographical location coordinates of the task, screen the task range according to the resource carrying capacity of the drone, and integrate and analyze the drone parameter and task parameter data to generate a task matching parameter table; S103: Based on the task matching parameter table, sort the drones and tasks in descending order according to the task priority, analyze the remaining power of the drones and the matching between the flight distance and the task requirements, calculate the adaptability score, and perform screening and allocation by combining the task number and the drone parameters to generate the initial adaptability parameters of the tasks and drones.

4. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, characterized in that Based on the initial adaptability parameters of the tasks and drones, analyze the coverage range of the drone positions and the task center positions, evaluate the coverage ability of the drones using the endurance and the upper limit of the flight time, compare and analyze the number of drones and the number of tasks, and perform the task allocation process. The specific steps for generating the drone distribution ratio data in the task area are as follows: S201: Based on the initial adaptability parameters of the tasks and drones, calculate the distance between the current position of the drone and the geographical coordinates of the task center position, calculate and mark the range of positions that can be covered by the drone flight radius in the task area, and match and classify the task numbers by combining the coverage range data to generate the drone coverage range data; S202: Based on the drone coverage range data, analyze the coverage effectiveness by combining the drone endurance time and the geographical distribution distance of the tasks, and evaluate the time and position coverage ability of the task area according to the upper limit of the flight time and the flight radius to generate the drone coverage ability data; S203: Based on the drone coverage ability data, compare and allocate the number of drones and the number of tasks according to the drone coverage ability and the task requirements, match the coverage ratio according to the effective coverage range of the drones and the distribution of the task numbers, and integrate the drone numbers and the task area coverage data to generate the drone distribution ratio data in the task area.

5. The method for collaborative mission allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, wherein Based on the drone distribution ratio data in the task area, calculate the matching between the task resource requirements and the drone load capacity, analyze the task resource sharing requirements and the timing constraints, analyze the coupling strength of the task area through the resource competition and coupling relationship, and the specific steps for generating the resource coupling strength parameters in the task area are as follows: S301: Based on the drone distribution ratio data in the task area, calculate the matching ratio between the drone load capacity and the task required resources item by item according to the corresponding relationship between the task resource requirement parameters and the drone load capacity, and analyze the drone load capacity range and the task resource requirements one by one to generate the task and drone load matching data; S302: Based on the task and drone load matching data, conduct a classification analysis of the resource types and quantities for the task resource sharing requirements, compare the distribution of the resource requirements according to the task time nodes, associate the allocation of the shared resources with the time constraints, and analyze the resource usage time conflicts to generate the task resource sharing and timing data; S303: Based on the task resource sharing and timing data, analyze the resource competition relationship and the coupling relationship item by item according to the cross relationship of the task resource sharing and the time allocation constraints, and calculate the resource coupling strength value in the task area according to the resource distribution data to generate the resource coupling strength parameters in the task area.

6. The method for collaborative mission assignment of an unmanned aerial vehicle cluster based on cluster optimization according to claim 5, wherein The specific formula for the resource coupling strength value is as follows: ； Among them, represents the resource coupling strength value, represents that the task number is the initial resource allocation value, represents that the task number is the adjusted resource allocation value, represents that the task number is the total time allocation amount, represents the total number of tasks.

7. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, characterized in that, Based on the resource coupling strength parameters within the task area, combined with the flight speed and path time consumption analysis of the unmanned aerial vehicle (UAV), the execution order of the UAV tasks is adjusted, and the task time distribution is optimized through the relationship between time sequence and path time consumption. The specific steps for generating the UAV task time distribution path data are as follows: S401: Based on the resource coupling strength parameters within the task area, extract the UAV flight speed and task geographical location, calculate the path time consumption of the UAV from the current position to the task point in segments, and perform allocation and sorting analysis on the path time consumption data in combination with the task priority to generate the UAV task path time consumption data; S402: Based on the UAV task path time consumption data, analyze and adjust the execution order of the UAV tasks according to the path time consumption and task geographical location, compare the path time distribution of the tasks with the task time nodes, adjust and analyze the task time interval and task allocation order to generate the UAV task time sequence adjustment data; S403: Based on the UAV task time sequence adjustment data, extract the task adjustment order and path time distribution, combine and analyze the path information and time distribution of the UAV tasks, integrate the path time data and task order information, and process the time interval allocation and path optimization to generate the UAV task time distribution path data.

8. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 7, wherein The specific formula for the path time consumption parameter is as follows: ； Among them, represents the path time-consuming parameter, represents the path distance of the drone on the horizontal axis of the geographical coordinates, represents the path distance of the drone on the vertical axis of the geographical coordinates, represents the flight speed of the drone in the horizontal axis direction, represents the flight speed of the drone in the vertical axis direction, represents the weight of resources required for the mission, represents the current load capacity of the drone, represents the maximum load capacity of the drone.

9. The method for collaborative task allocation of an unmanned aerial vehicle cluster based on cluster optimization according to claim 1, wherein Based on the UAV task time distribution path data, combined with the task execution status and path deviation analysis, adjust the execution path of the unfinished tasks, update the flight plan of the UAV, identify the task requirements, and the specific steps for generating the UAV task path reconstruction data are as follows: S501: Based on the UAV task time distribution path data, extract the task execution status and the current position of the UAV, calculate the path deviation of the unfinished tasks, correlate and analyze the path deviation and task geographical location, and classify and organize the path deviation and task execution status to generate the UAV task path deviation data; S502: Based on the UAV task path deviation data, extract the UAV flight speed and the remaining task time, calculate the path adjustment value, compare and analyze the path adjustment result with the remaining task time node to generate the UAV task adjusted path data; S503: Based on the UAV task adjusted path data, analyze the adjusted path and task time distribution, update the time node data after path optimization and the flight plan of the UAV, identify and integrate the path adjustment and time distribution data to generate the UAV task path reconstruction data.

10. A UAV swarm cooperative mission allocation system based on cluster optimization, characterized in that, According to the method for collaborative task allocation of UAV clusters based on cluster optimization described in any one of claims 1-9, the system includes: The initial adaptation module, based on the task urgency, resource requirements, and task time limit, combined with the battery power, flight distance, and current position of the UAV, compares and calculates the matching degree between the task and the UAV to generate the initial adaptation degree parameter of the task and the UAV; The coverage ability module, based on the initial adaptation degree parameter of the task and the UAV, analyzes the coverage range of the UAV position and the task center position, evaluates the UAV coverage ability using the endurance and flight time upper limit, performs task allocation processing, and generates the UAV distribution ratio data in the task area; Based on the drone distribution ratio data in the task area, the resource matching module calculates the matching between the task resource requirements and the drone payload capacity, analyzes the coupling strength of the task area through resource competition and coupling relationships, and generates resource coupling strength parameters within the task area; Based on the resource coupling strength parameters in the task area, the timing optimization module combines the flight speed of the drone and the path time consumption analysis, optimizes the task time distribution through the relationship between timing and path time consumption, and generates drone task time distribution path data; Based on the drone task time distribution path data, the path reconstruction module combines the task execution status and path deviation analysis, adjusts the execution paths of unfinished tasks, updates the flight plan of the drone, and generates drone task path reconstruction data.

Images