Unmanned aerial vehicle cluster collaborative operation method and system

Abstract

The invention relates to the technical field of intelligent control, in particular to an unmanned aerial vehicle cluster collaborative operation method and system, and the method comprises the following steps: collecting geometric distribution data and task density information of an unmanned aerial vehicle cluster operation region, carrying out the point set coordinate screening of the geometric distribution data, calculating the distance and spatial relevance between point set distributions, and calculating the task density information of the unmanned aerial vehicle cluster operation region; and obtaining a task density distribution set. According to the method, through comprehensive extraction of task completion time, priorities and position sequences, task windows are divided in combination with time periods and priorities, ordered execution and real-time optimization of tasks are achieved, the flexibility and collaboration of task scheduling are improved, and the task scheduling efficiency is improved based on sequence allocation and time interval optimization of the priorities. Reasonable allocation of time and resources in the task execution process is further ensured, non-critical delay and conflicts are avoided, the operation state and the residual electric quantity of the unmanned aerial vehicle are monitored in real time, and the efficiency, the flexibility and the stability of unmanned aerial vehicle cluster collaborative operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to a method and system for collaborative operation of an unmanned aerial vehicle (UAV) cluster. Background Art

[0002] The technical field of intelligent control includes technologies that take dynamic systems as objects and achieve the regulation and optimization of their behaviors through the design of algorithms and controllers. The core content of this technical field includes various aspects such as dynamic system modeling, control strategy design, controller implementation, and real-time control during operation. Based on the theory of automatic control and combined with artificial intelligence methods, intelligent control technology is widely applied to the optimization and control of complex systems in multiple fields. Specific applications include fields such as unmanned driving, robot systems, industrial process control, energy scheduling and management, etc., focusing on solving problems such as multi-variable coupling in dynamic environments, control difficulties of non-linear systems, and automation of decision-making processes.

[0003] Among them, the method for collaborative operation of a UAV cluster refers to a technical solution that realizes task division and coordinated completion by controlling the cooperative actions of multiple unmanned aerial vehicles. This technology mainly focuses on the synchronization problems of collaborative task planning, path planning, and task execution among multiple UAVs. The UAV cluster achieves the collaborative work of individuals in the cluster through methods based on geometric formation, topological control, and task allocation. In terms of task planning, the specific responsibilities of each UAV are clarified through the decomposition of cluster tasks and the allocation of subtasks. In terms of path planning, by clarifying the starting point, target point, and environmental constraints, combined with methods based on dynamic programming or constraint optimization, the flight paths of the UAVs are generated. During task execution, communication protocols and real-time position control technologies are used to achieve information interaction and collaborative execution among UAVs, and the orderly implementation of the overall task is completed.

[0004] The existing technologies lack accuracy and flexibility in task allocation and path planning for the collaborative operation of multiple UAVs in a dynamic environment, resulting in difficult resource allocation to fully match task requirements. Task planning mainly relies on static parameters and does not fully consider the task density distribution and resource state changes in the real-time environment, resulting in phenomena such as overloading or idling of UAV resources. During task execution, due to the lack of real-time monitoring and dynamic adjustment mechanisms, the probability of task execution interruption or failure is relatively high, affecting the completion efficiency and stability of the overall task. The methods for priority sorting and time window division in the task allocation process are relatively rough, resulting in delays in key tasks or waste of resources. The cooperation among UAVs mainly relies on pre-set paths and task divisions, and fails to fully adapt to sudden changes in the dynamic environment. The task adjustment ability is weak, resulting in reduced efficiency or even task failure in complex environments. For example, when the battery power of a UAV is insufficient, the lack of a mechanism for dynamically adjusting tasks leads to the inability to replace tasks in time, affecting the progress and effect of the overall operation. Summary of the Invention

[0005] To address the technical problems in the prior art, such as the lack of precision and flexibility in task allocation and path planning for multi-UAV collaborative operations in a dynamic environment, which leads to difficulties in fully matching resource allocation with task requirements. Task planning mainly relies on static parameters and does not fully consider the task density distribution and resource status changes in the real-time environment, resulting in overloaded or idle UAV resources. During the task execution process, due to the lack of real-time monitoring and dynamic adjustment mechanisms, the probability of task execution interruption or failure is relatively high, affecting the overall task completion efficiency and stability. In the task allocation process, the methods for priority ranking and time window division are relatively rough, leading to delays in critical tasks or resource waste. The cooperation between UAVs mainly relies on pre-set paths and task divisions, and fails to fully adapt to sudden changes in the dynamic environment. The task adjustment ability is weak, resulting in reduced efficiency or even task failure in complex environments. For example, when the UAV's battery power is insufficient, the lack of a mechanism for dynamically adjusting tasks leads to the inability to take over tasks in a timely manner, affecting the overall operation progress and effect. Embodiments of the present invention provide a method and system for UAV cluster collaborative operations. The technical solutions are as follows: On the one hand, a method for UAV cluster collaborative operations is provided, which includes: S1: Collect the geometric distribution data and task density information of the UAV cluster operation area, screen the point set coordinates of the geometric distribution data, calculate the distances and spatial correlations between point set distributions, and obtain the task density distribution set; S2: Use the task density distribution set to record the speed, power, and payload parameters of the UAV cluster, calculate the task matching degree based on the total task requirements and UAV cluster parameters, and perform zoning adjustment on the UAVs that do not meet the conditions in the matching degree data to obtain the UAV cluster allocation result; S3: According to the UAV cluster allocation result, extract the task completion time, sequence priority, and position sequence parameters of the UAV cluster collaborative operation allocation area, divide the collaborative operation task window according to the time period and priority, and adjust the task sequence and allocation range to obtain the time window division record; S4: Based on the time window division record, extract the priority parameters for the task execution sequence, perform parallel allocation on the task position sequence and UAV power parameters according to the priority, and optimize the adjustment of the time intervals in the allocation sequence to obtain the task execution sequence adjustment result; S5: Use the task execution sequence adjustment result to monitor the task completion status and remaining power parameters of the UAV cluster collaborative operation, extract the data of unfinished tasks and compare the task and UAV status parameters, and adjust the task window size and sequence allocation according to the real-time task status to generate the UAV cluster collaborative operation task allocation result.

[0006] As a further solution of the present invention, the task density distribution set includes the coordinate matrix of the point set within the region, the task density value, and the point set association relationship table. The UAV cluster allocation result includes the task matching table, the allocation number list of UAVs, and the task area division grid. The time window division record includes the task time interval table, the priority sorting list, and the location sequence allocation map. The task execution order adjustment result includes the optimized task sequence diagram, the UAV power allocation table, and the adjusted time interval parameter set. The UAV cluster collaborative operation task allocation result includes the unfinished task list, the task window record adjusted in real time, and the UAV status matching table.

[0007] As a further solution of the present invention, the steps of collecting the geometric distribution data and task density information of the UAV cluster operation area, screening the point set coordinates from the geometric distribution data, calculating the distance and spatial correlation between the point set distributions, and obtaining the task density distribution set are specifically as follows: S101: Collect the geometric distribution data and task density information of the UAV cluster operation area, extract and classify the point set coordinates using the geometric distribution data, calculate the classification marker value of the point set, and generate the point set screening result; S102: Using the point set screening result, extract the screened point set data, calculate the Euclidean distance between multiple points, summarize the adjacent distribution relationship of multiple points, and through the sorting and classification marking of the distances between points within the region, extract the spatial correlation index of the point set to obtain the point set spatial correlation recognition result; S103: According to the point set spatial correlation recognition result, extract the correlation index and task density information of the point set within the UAV cluster collaborative operation area, calculate the task density value of the point set within the operation area, and obtain the task density distribution set by normalizing the correlation and task distribution data.

[0008] As a further solution of the present invention, the formula for calculating the classification marker value of the point set is as follows: ; Where, is the classification marker value of the point set, represents the th coordinate point of the UAV cluster, represents the th coordinate point of the UAV cluster, represents the coordinate center of the th type of point set, represents the th number of coordinate points in the type of point set, represents the weight of the distance between the coordinate point and the center point, represents the normalization coefficient of the number of points within the class, represents the adjustment coefficient of the point density influence, is the number of coordinate points.

[0009] As a further solution of the present invention, using the task density distribution set, recording the speed, power, and payload parameters of the UAV cluster, calculating the task matching degree based on the total task requirements and the UAV cluster parameters, and performing zonal adjustment on the UAVs that do not meet the conditions in the matching degree data to obtain the UAV cluster allocation result specifically includes the following steps: S201: Through the task density distribution set, extract the density values of the task points in the collaborative operation area of the UAV cluster, call the speed, power, and payload parameters of the UAV cluster, perform parameter classification and screening, and group the parameters according to the requirements of the task points to generate the UAV cluster parameter extraction result; S202: Using the UAV cluster parameter extraction result, calculate the matching degree between the total task requirements and the UAV parameters. By comparing each item of the UAV payload, power, and task point requirements and classifying the matching degrees, summarize the task allocation items to obtain the task matching degree data; S203: Based on the task matching degree data, screen the UAVs with a matching degree lower than the threshold, re-adjust the zonal positions, and allocate the UAVs with a matching degree lower than the threshold to adjacent areas to generate the UAV cluster allocation result.

[0010] As a further solution of the present invention, according to the UAV cluster allocation result, extract the task completion time, order priority, and position sequence parameters of the collaborative operation allocation area of the UAV cluster. Divide the collaborative operation task window according to the time period and priority, and adjust the task order and allocation range to obtain the time window division record specifically includes the following steps: S301: Through the UAV cluster allocation result, extract the task completion time, priority order, and position sequence parameters in the collaborative operation allocation area of the UAV cluster, group and statistically analyze the task completion time, sort and number the order priorities to generate the task allocation parameter set; S302: Based on the task allocation parameter set, combine the task completion time and priority order to divide the collaborative operation task window. Through the interval grouping of the task time and the rearrangement of the priority order, merge and adjust the tasks within the task window to obtain the collaborative operation task window division data; S303: Using the collaborative operation task window division data, adjust the task order according to the divided task windows. By correcting the task allocation range and optimizing the priority of the task position sequence, update the collaborative operation task allocation order and range of the UAV cluster to obtain the time window division record.

[0011] As a further solution of the present invention, based on the time window division record, priority parameters are extracted for the task execution order, and the task location sequence and the UAV power parameter are allocated in parallel according to the priority. The specific steps for optimizing and adjusting the time interval in the allocation order to obtain the adjusted result of the task execution order are as follows: S401: Based on the time window division record, extract the priority parameters of the task execution order, group and classify the priority parameters, and mark the UAV cluster collaborative operation tasks according to the priority partition to obtain a task allocation priority list; S402: Use the task allocation priority list to segment the task location sequence of the UAV cluster collaborative operation task, and compare and allocate tasks item by item by combining the power parameters of the UAVs to perform the initial parallel matching of the task location and the UAVs to obtain the task location and UAV allocation result; S403: Use the task location and UAV allocation result to adjust the time interval of the task allocation order. By correcting the time deviation between tasks, optimize the uniformity of the time interval, update the task execution order, and obtain the adjusted result of the task execution order.

[0012] As a further solution of the present invention, using the adjusted result of the task execution order, monitor the completion status of the UAV cluster collaborative operation task and the remaining power parameter, extract the data of the unfinished task and compare the parameters of the task and the UAV status, and adjust the task window size and order allocation according to the real-time task status to generate the steps of the UAV cluster collaborative operation task allocation result are as follows: S501: Based on the adjusted result of the task execution order, monitor the task execution status and power consumption of the UAV cluster in real time, classify and record the completed tasks and unfinished tasks, and calculate the task priority value of the UAVs to obtain the unfinished task status record; S502: According to the unfinished task status record, extract the time window and task allocation range of the unfinished task, combine the UAV status parameters, compare the remaining task amount and the remaining UAV power value item by item, adjust the allocation range of the time window, and update the task allocation window to obtain the real-time task allocation adjustment result; S503: Use the real-time task allocation adjustment result to re-divide the time window and order of the unfinished tasks. Through the matching optimization of the collaborative operation tasks and the UAV cluster, update the task order and UAV allocation status, and generate the UAV cluster collaborative operation task allocation result.

[0013] As a further solution of the present invention, the formula for calculating the task priority value of the UAV is as follows: ; Wherein, is the task priority value of the drone, represents the total number of unfinished tasks, represents the remaining battery power of the real-time drone, represents the weight coefficient of battery power and task urgency, represents the variability of task allocation and power consumption, represents the remaining task volume of the drone in real time, represents the estimated minimum battery power required to execute the remaining tasks, is the natural constant.

[0014] On the other hand, an electric vehicle status monitoring system is provided. The electric vehicle status monitoring system is used to execute the above-mentioned electric vehicle status monitoring method. The system includes: The distribution analysis module collects the geometric distribution data and task density information of the drone cluster operation area, extracts the point set coordinates, calculates the spatial distance and correlation between the point sets, and combines the task density information to generate a task density distribution data set; The task allocation module uses the task density distribution data set, extracts the drone speed, battery power and payload information, calculates the matching degree between the task requirements and the drone parameters, filters out the drones that do not meet the conditions, adjusts the task partition allocation, and obtains the drone task allocation data; The collaborative task division module uses the drone task allocation data, extracts the task completion time, sequence priority and position sequence information, combines the allocation range and priority of the task time period, divides the collaborative operation time window, and obtains the time window division result; The sequence adjustment module extracts the priority of the task execution sequence through the time window division result, allocates the task position sequence and the drone battery power, optimizes the time interval allocation sequence, and obtains the optimized task execution sequence; The dynamic monitoring module monitors the drone task completion status and remaining battery power according to the optimized task execution sequence, extracts the unfinished task data, compares the task and the drone status, adjusts the task allocation range and sequence, and generates the drone cluster collaborative operation task allocation result.

[0015] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include: By collecting and analyzing the geometric distribution data and task density information of the operation area, the task density distribution is reasonably divided to ensure the efficient coverage and precise matching of the UAV cluster in the task area. Based on the speed, power, and payload parameters of the UAVs, the task matching degree is calculated and the partition is adjusted, significantly improving the resource utilization rate of the UAVs and effectively avoiding the uneven distribution of resources. By comprehensively extracting the task completion time, priority, and position sequence, and combining the time period and priority to divide the task window, the orderly execution and real-time optimization of tasks are realized, enhancing the flexibility and coordination of task scheduling. Based on the sequential allocation based on priority and the optimization of time intervals, it further ensures the reasonable allocation of time and resources during the task execution process, avoiding non-critical delays and conflicts. Real-time monitoring of the operation status and remaining power of the UAVs, and dynamically adjusting the task window and sequential allocation, helps reduce the risk of interruptions and failures during task execution, improve the overall task completion rate, enhance the efficiency, flexibility, and stability of the UAV cluster collaborative operation, and significantly enhance the ability to adapt to complex environments and dynamic task requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a detailed flowchart of S1 of the present invention; Figure 3 It is a detailed flowchart of S2 of the present invention; Figure 4 It is a detailed flowchart of S3 of the present invention; Figure 5 It is a detailed flowchart of S4 of the present invention; Figure 6 It is a detailed flowchart of S5 of the present invention; Figure 7 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with 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 belong to the scope of protection of the present application.

[0018] In the description of the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood 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" means two or more, unless otherwise specifically defined.

[0019] 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 advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with non-essential details. 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.

[0020] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0021] Please refer to Figure 1 , an embodiment of the present invention provides a method for collaborative operation of an unmanned aerial vehicle (UAV) cluster. The processing flow of this method may include the following steps: S1: Collect the geometric distribution data and task density information of the operation area of the UAV cluster, screen the point set coordinates of the geometric distribution data, calculate the distances and spatial correlations between the point set distributions, and obtain the task density distribution set; S2: Use the task density distribution set to record the speed, power, and payload parameters of the UAV cluster, calculate the task matching degree based on the total task requirements and the UAV cluster parameters, and perform partition adjustment on the UAVs that do not meet the conditions in the matching degree data to obtain the UAV cluster allocation result; S3: According to the UAV cluster allocation result, extract the parameters of the task completion time, order priority, and position sequence of the collaborative operation allocation area of the UAV cluster, divide the collaborative operation task window according to the time period and priority, and adjust the task order and allocation range to obtain the time window division record; S4: Based on the time window division record, extract the priority parameters for the task execution order, perform parallel allocation on the task position sequence and the UAV power parameters according to the priority, and optimize and adjust the time intervals in the allocation order to obtain the task execution order adjustment result; S5: Utilize the task execution order adjustment result to monitor the task completion status and remaining power parameters of the UAV cluster collaborative operation, extract the data of the uncompleted tasks and compare the task and UAV status parameters, and adjust the task window size and order allocation according to the real-time task status to generate the UAV cluster collaborative operation task allocation result.

[0022] The task density distribution set includes the coordinate matrix of the point set within the area, the task density value, and the point set association relation table. The UAV cluster allocation result includes the task matching table, the allocation number list of UAVs, and the task area division grid. The time window division record includes the task time interval table, the priority sorting list, and the position sequence allocation diagram. The task execution order adjustment result includes the optimized task sequence diagram, the UAV power allocation table, and the adjusted time interval parameter set. The UAV cluster collaborative operation task allocation result includes the unfinished task list, the task window record adjusted in real time, and the UAV status matching table.

[0023] Please refer to Figure 2 , for collecting the geometric distribution data and task density information of the UAV cluster operation area, screening the point set coordinates from the geometric distribution data, calculating the distance and spatial correlation between point set distributions, the steps for obtaining the task density distribution set are specifically as follows: S101: Collect the geometric distribution data and task density information of the UAV cluster operation area, extract and classify the point set coordinates using the geometric distribution data, calculate the classification marker value of the point set, and the execution process for generating the point set screening result is as follows; The formula for calculating the classification marker value of the point set is as follows: ; Where, is the classification marker value of the point set, represents the th coordinate point of the UAV cluster, represents the th coordinate point of the UAV cluster, represents the coordinate center of the th type of point set, represents the th number of coordinate points in the type of point set, represents the weight of the distance between the coordinate point and the center point, represents the normalization coefficient of the number of points within the class, represents the adjustment coefficient of the point density influence, is the number of coordinate points; Parameter meaning and setting value: represents the position value of the jth coordinate point in the point set, and the data is collected from the GPS coordinate data within the UAV cluster operation area. The point set sample is ; represents the centroid position value of the point set, and the calculation method is the centroid formula, that is , and the average value of the point set coordinates is used as the centroid, and the calculated value is ; Indicates the number of coordinate points included in the point set, and the directly monitored value is ; Indicates the weight of the distance between a point and the centroid, and is optimized according to the classification accuracy to be , and this value is adjusted according to the classification requirements; Indicates the normalization coefficient of the number of points within a class, and is set according to the distribution characteristics of the number of points to be , and this value fluctuates and adjusts according to the range of the number of points; Indicates the adjustment coefficient affected by point density, and is optimized according to density sensitivity to be , and this value is adjusted according to the density distribution range; Substitute the parameters into the formula for calculation: Calculate the numerator part: ; ; Calculate the denominator part: ; ; ; ; Calculate the classification marker value: ; The result shows the distribution characteristics and density characteristics of the point set relative to the centroid. This value is used in the subsequent steps of the classification algorithm to screen and optimize the classification of the point set, and can effectively distinguish the characteristics of the point sets in different regions.

[0024] S102: Adopt the point set screening result, extract the screened point set data, calculate the Euclidean distance between multiple points, summarize the adjacent distribution relationship of multiple points, and through the sorting and classification annotation of the distances between points within the region, extract the spatial correlation index of the point set, and the execution process for obtaining the spatial correlation recognition result of the point set is as follows; After extracting the filtered point set data, it is necessary to comprehensively analyze the spatial coordinates of each point in the point set. By calculating the Euclidean distance between points, the distribution characteristics of the point set are evaluated. The calculation formula of the Euclidean distance is the square root of the sum of the squares of the coordinate differences between two points. For the relationship between multiple points, it is necessary to construct a point-to-point distance matrix, and through this matrix, the adjacent distribution relationship of multiple points in the point set is summarized. Further, combined with the spatial characteristics of the region, the distances between points are sorted in ascending order. By setting a distance threshold, the distances between points are classified as adjacent points or non-adjacent points, and at the same time, the spatial connection relationships of each point are marked, and the spatial characteristic indicators between points in the region are summarized, providing data support for subsequent task density analysis and point set optimization, and obtaining the recognition result of the spatial correlation of the point set.

[0025] S103: According to the recognition result of the spatial correlation of the point set, extract the correlation index and task density information of the point set in the collaborative operation area of the UAV cluster, calculate the task density value of the point set in the operation area, and the execution process of obtaining the task density distribution set by normalizing the correlation and task distribution data is as follows; After extracting the correlation index and task density information of the point set in the collaborative operation area of the UAV cluster, it is necessary to clarify the task attributes and regional coverage of each point, analyze the distribution pattern between points based on the spatial correlation index, use the strength of the correlation between task points as an important basis for dividing regions, calculate the task density value of the point set in each region. The calculation of task density is carried out by dividing the total task amount of the point set by the area of the region, and combined with the distribution characteristics of the points in the region, the task density values of each point are grouped and summarized. By normalizing the correlation data and task distribution information, the inter-point correlation data and task density data are standardized to the same dimension range, further optimizing the spatial layout and resource scheduling strategy of UAV task allocation, and obtaining the task density distribution set.

[0026] Please refer to Figure 3 , adopt the task density distribution set, record the speed, power and payload parameters of the UAV cluster, calculate the task matching degree according to the total task requirements and the parameters of the UAV cluster, and perform partition adjustment on the UAVs that do not meet the conditions in the matching degree data. The specific steps to obtain the UAV cluster allocation result are as follows: S201: Through the task density distribution set, extract the density values of the task points in the collaborative operation area of the UAV cluster, call the speed, power and payload parameters of the UAV cluster, perform parameter classification and screening, and group the parameters according to the requirements of the task points. The execution process of generating the UAV cluster parameter extraction result is as follows; To extract the density value of task points within the collaborative operation area of a drone swarm, it is necessary to clarify the coordinates and attribute information of all task points within the task area. The entire operation area is divided into cells of a fixed size, and each cell serves as the basic calculation unit for task density. The number of task points in each cell is counted. The density value is calculated as the number of task points in each cell divided by the cell area. Further analyze the distribution pattern of task points. While counting the density, specific requirement parameters are marked for each task point, such as the complexity of task requirements, time requirements, etc. At the same time, the speed, power, and payload parameters of the drones are invoked, and a three-dimensional matrix is constructed based on the parameter performance range for classification and screening. Drones with similar performances are grouped into the same group. Combining the density distribution of task points, a preliminary correspondence between task points and drone parameters is established, and the optimal parameter combination is selected to generate the result of drone swarm parameter extraction.

[0027] S202: Using the result of drone swarm parameter extraction, calculate the matching degree between the total task requirements and drone parameters. The execution process of obtaining the task matching degree data by classifying the item-by-item comparison and matching degree of drone payload, power, and task point requirements and summarizing the task assignment items is as follows; To calculate the matching degree between the total task requirements and drone parameters, it is necessary to comprehensively consider multiple comparisons of task point requirement parameters and drone performance parameters. In the analysis of task point requirements, for the specific parameters of the task, the threshold ranges of the required payload capacity, power consumption, and expected execution speed of the task need to be listed and compared one by one with the data in the drone performance matrix. The matching degree is calculated using the item-by-item calculation method. The remaining power of the drone is converted into an operable range by percentage, and combined with the density value of task point requirements, the adaptability between the drone and the task point is calculated. By classifying and counting the matching of payload, power, and speed, the matching relationship between drone performance and task requirements is further summarized. At the same time, the task items and drones with matching degrees are preferentially grouped, and the corresponding results are used in the next task assignment process to obtain the task matching degree data.

[0028] S203: Based on the task matching degree data, screen out the drones with a matching degree lower than the threshold, re-adjust the partition positions, and assign the drones with a matching degree lower than the threshold to adjacent areas. The execution process of generating the drone swarm assignment result is as follows; When screening for drones with a matching degree lower than the threshold and reassigning tasks to adjacent areas, a comprehensive analysis of the coverage range of the drones and the requirements of the task points in the adjacent areas is required. By redefining the partition range, it is ensured that drones with a lower matching degree are prioritized to undertake the secondary requirements of the surrounding task points. When repositioning the partition, the actual performance parameters of the drones are used to simulate the allocation of task points in the allocated area one by one. At the same time, it is statistically determined whether the total requirements of the task points after allocation are met. The specific operations include relabeling all task points in the area, pairing the task point requirement density with the drone payload and battery power for testing, screening the allocable task points one by one, updating the task area of the drones, and optimizing the allocation plan in combination with the matching degree screening conditions to generate the drone cluster allocation results.

[0029] Please refer to Figure 4 , according to the drone cluster allocation results, extract the task completion time, order priority, and position sequence of the drone cluster collaborative operation allocation area. The steps for dividing the collaborative operation task window according to the time period and priority and adjusting the task order and allocation range to obtain the time window division record are as follows: S301: Through the drone cluster allocation results, extract the task completion time, priority order, and position sequence parameters in the drone cluster collaborative operation allocation area. The execution process of grouping and statistically analyzing the task completion time, sorting and numbering the order priority to generate the task allocation parameter set is as follows; To extract the task completion time, priority order, and position sequence parameters in the drone cluster collaborative operation allocation area, it is necessary to clarify the method of obtaining the task completion time, which can be obtained through real-time monitoring data during task execution or task simulation calculation. For the extraction of the priority order, a comprehensive evaluation needs to be carried out based on the urgency of the task, the resource requirements, and the preset priority criteria, and the task priority is marked as a set of ordered data. The position sequence parameter needs to be extracted in combination with the drone flight trajectory data and the geographical coordinates of the task points. After extraction, the task points are grouped and statistically analyzed according to the task completion time to generate the average completion time corresponding to each group of tasks. At the same time, the tasks are reordered and numbered according to the priority order, and the position sequence parameter is associated with the task priority to form an ordered task allocation path and generate the task allocation parameter set.

[0030] S302: Based on the task allocation parameter set, combine the task completion time and priority order to divide the collaborative operation task window. The execution process of merging and adjusting the tasks in the task window through interval grouping of the task time and reordering of the priority order to obtain the collaborative operation task window division data is as follows; When dividing the collaborative operation task window by combining the task completion time and priority order, it is necessary to conduct a multi-dimensional analysis of the task time and priority data. According to the range of task completion time, the tasks are grouped into multiple time intervals, and it is ensured that the tasks within each interval have similar execution times. Secondly, the tasks within the task time interval are rearranged according to the priority order. By adjusting the priority order, it is ensured that high-priority tasks are preferentially assigned to the front task windows. When merging and adjusting the tasks within the task window, it is necessary to combine the geographical distribution of task points and the task execution time to optimize the task merging scheme to reduce execution conflicts between tasks. At the same time, integrate the priority order and completion time within the task window to provide an accurate time and priority planning basis for the task optimization scheduling of the UAV cluster, and obtain the data for dividing the collaborative operation task window.

[0031] S303: Use the data for dividing the collaborative operation task window to adjust the task order according to the divided task windows. By correcting the task allocation range and optimizing the priority of the task position sequence, update the collaborative operation task allocation order and range of the UAV cluster, and the execution process for obtaining the time window division record is as follows; When adjusting the task order according to the divided task windows, it is necessary to correct the priority of the task position sequence and the task allocation range one by one. According to the order of the divided task windows, combine the priority optimization algorithm to reorder the task sequence to ensure that the task allocation order meets the comprehensive requirements of time and priority. Adjust the task allocation range. By optimizing the coverage radius of the UAV and the concentrated distribution of task points, merge adjacent task points into the same task window, and optimize the task trajectory of the UAV based on the task position sequence parameters to reduce the flight distance and task switching time between task points. At the same time, update the priority parameters in the task position sequence to optimize the collaborative operation task allocation order and range of the UAV cluster, and provide an optimized allocation plan for subsequent task execution to obtain the time window division record.

[0032] Please refer to Figure 5 , based on the time window division record, extract the priority parameters for the task execution order, and parallelly allocate the task position sequence and the UAV battery parameters according to the priority. Optimize and adjust the time interval in the allocation order to obtain the steps of the task execution order adjustment result as follows: S401: Based on the time window division record, extract the priority parameters of the task execution order, group and classify the priority parameters, and mark the collaborative operation tasks of the UAV cluster according to the priority partition to obtain the execution process of the task allocation priority list as follows; To extract the priority parameters of the task execution order, it is necessary to comprehensively sort out the tasks within the task window, mark the priority parameters according to the execution order of the tasks in the time window, divide the priority parameters into several groups, and group the tasks into three levels: high priority, medium priority, and low priority according to the high and low distribution of the priority. For the partition marking of the priority, combined with the cooperative operation mode of the UAV, mark the tasks by region according to the priority, and adjust the execution order of the tasks within the region to ensure that the high-priority tasks can be preferentially executed within the same region. By analyzing the attribute data after task grouping, provide basic information for task allocation to the UAV, and obtain the task allocation priority list.

[0033] S402: The following is the execution process of using the task allocation priority list to segment the task location sequence of the UAV cluster cooperative operation task, and perform the initial parallel matching of the task location and the UAV by comparing and allocating tasks item by item in combination with the battery parameters of the UAV to obtain the task location and the UAV allocation result; When segmenting the task location sequence of the UAV cluster cooperative operation task, it is necessary to compare and allocate tasks item by item in combination with the battery parameters of the UAV, segment the task location sequence according to the spatial distribution, perform matching tests on each segment of the task sequence with the UAV battery parameters, and judge whether the UAV can meet all the requirements of the allocated task according to the remaining battery value. At the same time, incorporate the distance parameters of the task location into the matching rule to further optimize the task coverage range of the UAV. Ensure that each segment of the task matches the battery and performance parameters of the corresponding UAV through segmentation processing, initialize the position parameters of the UAV and the task, and complete the allocation of the UAV and the task sequence through initial matching to provide a specific allocation plan and task path plan for subsequent task execution, and obtain the task location and the UAV allocation result.

[0034] S403: The following is the execution process of using the task location and the UAV allocation result to adjust the time interval of the task allocation order, optimizing the uniformity of the time interval by correcting the time deviation between tasks, and updating the task execution order to obtain the task execution order adjustment result; When adjusting the time interval of the task allocation order, it is necessary to focus on optimizing the uniformity of the time interval between tasks. By calculating and analyzing the time interval, find out the time deviation between tasks, and correct the deviation item by item to ensure that the time interval is more uniform. When adjusting, combine the geographical distribution of the task location and the flight speed parameters of the UAV to calculate the time required for the UAV to move from one task point to the next task point, adjust the task execution order so that the movement time of the UAV is coordinated with the task interval, and at the same time dynamically optimize the time interval according to the task matching result of the UAV. Update the adjusted time interval data to the task execution order to provide an optimized time allocation plan for the UAV cluster to complete tasks efficiently, and obtain the task execution order adjustment result.

[0035] Please refer to Figure 6 , the steps of using the task execution order adjustment result to monitor the completion status of the collaborative operation task of the UAV cluster and the remaining power parameter, extracting the data of the unfinished tasks and comparing the parameters of the tasks and the UAV status, and adjusting the task window size and order allocation according to the real-time task status to generate the task allocation result of the UAV cluster collaborative operation are as follows: S501: Based on the task execution order adjustment result, monitor the task execution status and power consumption of the UAV cluster in real time, classify and record the completed tasks and unfinished tasks, calculate the task priority value of the UAV, and the execution process of obtaining the unfinished task status record is as follows; The formula for calculating the task priority value of the UAV is as follows: ; Among them, is the task priority value of the UAV, represents the total number of unfinished tasks, represents the remaining power of the real-time UAV, represents the weight coefficient of power and task urgency, represents the variability of task allocation and power consumption, represents the remaining task volume of the real-time UAV, represents the estimated minimum power required to execute the remaining tasks, is the natural constant; Parameter meaning and setting value: represents the total number of unfinished tasks as of the real-time time point, set to 12, and this number is obtained through the real-time task monitoring of the UAV; represents the remaining power (percentage) of the real-time UAV, set to 60%, and this number is obtained through the real-time monitoring of the UAV battery status; is the weight coefficient of power and task urgency, set to 0.8, and this is a proportional coefficient optimized based on task data and power consumption models; represents the variability of task allocation and power consumption, set to 50, and this parameter is the statistical standard deviation obtained by analyzing the task completion situations under different tasks and different power states; represents the remaining task volume of the real-time UAV, set to 4, and this is obtained by real-time counting of the UAV task queue; represents the estimated minimum power required to execute all remaining tasks, set to 100, and this is estimated according to the UAV energy model and the type of tasks to be executed; Substitute the parameters into the formula for calculation: ; The result shows that the current task priority of the UAV is relatively low, which reflects that the remaining power of the UAV is relatively sufficient, the number of unfinished tasks is small, and the urgency of the tasks is not high. This result can be used to decide whether to adjust the task queue of the UAV or reassign tasks to improve the operation efficiency of the entire UAV cluster.

[0036] S502: According to the record of unfinished task status, extract the time window and task assignment range of the unfinished tasks. Combine with the UAV status parameters, compare the remaining task quantity with the remaining UAV power value item by item, adjust the assignment range of the time window, update the task assignment window, and the execution process of obtaining the real-time task assignment adjustment result is as follows; When extracting the time window and task assignment range of the unfinished tasks, it is necessary to analyze the task status record, screen out the tasks marked as unfinished, and extract the corresponding time window and geographical distribution data of the task points. Establish a mapping relationship between the time window of the unfinished tasks and the task assignment range. At the same time, obtain the current power, payload and position status of the UAV. Combine with the UAV status parameters, compare the remaining demand of each unfinished task with the remaining UAV power value item by item, calculate the minimum power required for the UAV to execute the unfinished tasks and match it with the actual power. Adjust the assignment range of the time window through the comparison result. For tasks beyond the current UAV capabilities, they will be reassigned to the time window or executed by UAVs with sufficient power to provide real-time optimization support for completing the unfinished tasks and obtain the real-time task assignment adjustment result.

[0037] S503: Adopt the real-time task assignment adjustment result to re-divide the time window and order of the unfinished tasks. Through the matching optimization of the collaborative operation tasks and the UAV cluster, update the task order and UAV assignment status, and the execution process of generating the UAV cluster collaborative operation task assignment result is as follows; When re-dividing the time window and order of the unfinished tasks, it is necessary to combine the current operating status of the UAV and the priority parameters of the task points, re-divide the time window of the unfinished tasks according to the actual execution ability, re-arrange the priority order of the tasks within the time window according to the remaining quantity and urgency, and combine the flight speed, power and task distribution distance of the UAV to calculate the optimal assignment order of each task point. Adjust the matching relationship between the UAV and the task point through the optimization algorithm, re-define the task assignment status of the UAV. For tasks executed by multiple UAVs collaboratively, reduce the conflicts and resource waste between tasks through task partitioning and path optimization, and at the same time update the priority mark of the task and the UAV status data to generate the UAV cluster collaborative operation task assignment result.

[0038] Please refer to Figure 7 , on the other hand, an electric vehicle status monitoring system is provided. The electric vehicle status monitoring system is used to execute the above-mentioned electric vehicle status monitoring method. The system includes: The distribution analysis module collects the geometric distribution data and task density information of the UAV cluster operation area, extracts the point set coordinates, calculates the spatial distance and correlation between point sets, and combines the task density information to generate a task density distribution data set; The task allocation module uses the task density distribution data set, extracts the UAV speed, power, and payload information, calculates the matching degree between the task requirements and the UAV parameters, filters out the UAVs that do not meet the conditions, adjusts the task partition allocation, and obtains the UAV task allocation data; The collaborative task division module uses the UAV task allocation data, extracts the task completion time, sequence priority, and position sequence information, combines the allocation range and priority of the task time period, divides the collaborative operation time window, and obtains the time window division result; The sequence adjustment module extracts the priority of the task execution sequence through the time window division result, allocates the task position sequence and the UAV power, optimizes the time interval allocation sequence, and obtains the optimized task execution sequence; The dynamic monitoring module monitors the UAV task completion status and remaining power according to the optimized task execution sequence, extracts the uncompleted task data, compares the task and the UAV status, adjusts the task allocation range and sequence, and generates the UAV cluster collaborative operation task allocation result.

[0039] 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 the 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 the modifications and variations.

Claims

1. A method for collaborative operation of an unmanned aerial vehicle cluster, characterized in that It includes the following steps: S1: Collect the geometric distribution data and task density information of the UAV cluster operation area, screen the point set coordinates of the geometric distribution data, calculate the distance and spatial correlation between point set distributions, and obtain the task density distribution set; S2: Use the task density distribution set to record the speed, power, and payload parameters of the UAV cluster, calculate the task matching degree based on the total task requirements and UAV cluster parameters, and perform zoning adjustment on the UAVs that do not meet the conditions in the matching degree data to obtain the UAV cluster allocation result; S3: According to the UAV cluster allocation result, extract the task completion time, order priority, and position sequence of the UAV cluster collaborative operation allocation area, divide the collaborative operation task window according to the time period and priority, and adjust the task order and allocation range to obtain the time window division record; S4: Based on the time window division record, extract the priority parameters for the task execution order, parallelly allocate the task position sequence and UAV power parameters according to the priority, and optimize and adjust the time interval in the allocation order to obtain the task execution order adjustment result; S5: Use the task execution order adjustment result to monitor the task completion status and remaining power parameters of the UAV cluster collaborative operation task, extract the data of the unfinished tasks and compare the task and UAV status parameters, and adjust the task window size and order allocation according to the real-time task status to generate the UAV cluster collaborative operation task allocation result.

2. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein The task density distribution set includes the coordinate matrix of the point set in the area, the task density value, and the point set association relationship table. The UAV cluster allocation result includes the task matching table, the allocation number list of UAVs, and the task area division grid. The time window division record includes the task time interval table, the priority sorting list, and the position sequence allocation map. The task execution order adjustment result includes the optimized task sequence diagram, the UAV power allocation table, and the adjusted time interval parameter set. The UAV cluster collaborative operation task allocation result includes the unfinished task list, the real-time adjusted task window record, and the UAV status matching table.

3. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein The steps of collecting the geometric distribution data and task density information of the UAV cluster operation area, screening the point set coordinates of the geometric distribution data, calculating the distance and spatial correlation between point set distributions, and obtaining the task density distribution set are specifically as follows: S101: Collect the geometric distribution data and task density information of the UAV cluster operation area, use the geometric distribution data to extract and classify the point set coordinates, calculate the classification marker value of the point set, and generate the point set screening result; S102: Use the point set screening result to extract the screened point set data, calculate the Euclidean distance between multiple points, summarize the adjacent distribution relationship of multiple points, and extract the spatial correlation index of the point set through the sorting and classification annotation of the distances between points in the area to obtain the point set spatial correlation identification result; S103: According to the recognition result of the spatial correlation of the point set, extract the correlation index and task density information of the point set within the collaborative operation area of the UAV cluster, calculate the task density value of the point set within the operation area, and obtain the task density distribution set by normalizing the correlation and task distribution data.

4. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 3, wherein The formula for calculating the classification label value of the point set is as follows: ； Among them, is the classification marker value of the point set, represents the th coordinate point of the UAV cluster, represents the th coordinate point of the UAV cluster, represents the coordinate center of the th type of point set, represents the th number of coordinate points in the type of point set, represents the weight of the distance between the coordinate point and the center point, represents the normalization coefficient of the number of points within the class, represents the adjustment coefficient of the influence of point density, is the number of coordinate points.

5. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein The steps of using the task density distribution set to record the speed, power, and payload parameters of the UAV cluster, calculating the task matching degree based on the total task requirements and UAV cluster parameters, and performing partition adjustment on the UAVs that do not meet the conditions in the matching degree data to obtain the UAV cluster allocation result are specifically as follows: S201: Through the task density distribution set, extract the density values of the task points within the collaborative operation area of the UAV cluster, call the speed, power, and payload parameters of the UAV cluster, perform parameter classification and screening, and group the parameters according to the requirements of the task points to generate the UAV cluster parameter extraction result; S202: Using the UAV cluster parameter extraction result, calculate the matching degree between the total task requirements and the UAV parameters, and through the item-by-item comparison and matching degree classification of the UAV payload, power, and task point requirements, summarize the task assignment items to obtain the task matching degree data; S203: Based on the task matching degree data, screen the UAVs with a matching degree lower than the threshold, re-adjust the partition positions, and assign the UAVs with a matching degree lower than the threshold to adjacent areas to generate the UAV cluster allocation result.

6. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein According to the UAV cluster allocation result, extract the task completion time, order priority, and position sequence parameters of the collaborative operation allocation area of the UAV cluster, divide the collaborative operation task window according to the time period and priority, and adjust the task order and allocation range to obtain the time window division record. The specific steps are as follows: S301: Through the UAV cluster allocation result, extract the task completion time, priority order, and position sequence parameters within the collaborative operation allocation area of the UAV cluster, perform grouped statistics on the task completion time, sort and number the order priorities to generate the task allocation parameter set; S302: Based on the task allocation parameter set, combine the task completion time and priority order to divide the collaborative operation task window. Through the interval grouping of the task time and the rearrangement of the priority order, merge and adjust the tasks within the task window to obtain the collaborative operation task window division data; S303: Using the collaborative operation task window division data, adjust the task order according to the divided task windows, and update the task assignment order and range of the UAV cluster collaborative operation by correcting the task allocation range and optimizing the priority of the task position sequence to obtain the time window division record.

7. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein Based on the time window division record, extract the priority parameters for the task execution order, perform parallel allocation of the task position sequence and UAV power parameters according to the priority, and optimize and adjust the time interval in the allocation order to obtain the task execution order adjustment result. The specific steps are as follows: S401: Based on the time window division record, extract the priority parameters of the task execution order, group and classify the priority parameters, and mark the collaborative operation tasks of the drone cluster according to the priority partition to obtain the task assignment priority list; S402: Use the task assignment priority list to segment the position sequence of the collaborative operation tasks of the drone cluster. By combining the power parameters of the drones, compare and assign tasks item by item, and perform parallel initialization matching of the task positions and the drones to obtain the task position and drone assignment results; S403: Use the task position and drone assignment results to adjust the time interval of the task assignment order. By correcting the time deviation between tasks, optimize the uniformity of the time interval, update the task execution order, and obtain the task execution order adjustment results.

8. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 1, wherein The steps of using the task execution order adjustment results to monitor the completion status of the collaborative operation tasks of the drone cluster and the remaining power parameters, extract the data of the unfinished tasks and compare the parameters of the tasks and the drone status, and adjust the task window size and order assignment according to the real-time task status to generate the task assignment results of the drone cluster collaborative operation are as follows: S501: Based on the task execution order adjustment results, monitor the task execution status and power consumption of the drone cluster in real time, classify and record the completed tasks and unfinished tasks, and calculate the task priority value of the drones to obtain the unfinished task status record; S502: According to the unfinished task status record, extract the time window and task assignment range of the unfinished tasks, combine the drone status parameters, compare the remaining task quantity and the remaining power value of the drones item by item, adjust the assignment range of the time window, and update the task assignment window to obtain the real-time task assignment adjustment results; S503: Use the real-time task assignment adjustment results to re-divide the time window and order of the unfinished tasks. By optimizing the matching of the collaborative operation tasks and the drone cluster, update the task order and the drone assignment status, and generate the task assignment results of the drone cluster collaborative operation.

9. The method for collaborative operation of an unmanned aerial vehicle cluster according to claim 8, wherein The formula for calculating the task priority value of the drones is as follows: ； wherein, is the task priority value of the drone, represents the total number of unfinished tasks, represents the remaining battery power of the real-time drone, represents the weight coefficient of the battery power and task urgency, represents the variability of task allocation and power consumption, represents the remaining task volume of the drone in real time, represents the estimated minimum battery power required to execute the remaining tasks, is the natural constant.

10. An unmanned aerial vehicle cluster collaborative operation system, characterized in that, According to the drone cluster collaborative operation method according to any one of claims 1-9, the system includes: The distribution analysis module collects the geometric distribution data and task density information of the drone cluster operation area, extracts the point set coordinates, calculates the spatial distance and correlation between the point sets, and combines the task density information to generate the task density distribution data set; The task assignment module uses the task density distribution data set to extract the drone speed, power and payload information, calculates the matching degree between the task requirements and the drone parameters, filters out the drones that do not meet the conditions, adjusts the task partition assignment, and obtains the drone task assignment data; The collaborative task division module uses the drone task assignment data to extract the task completion time, order priority and position sequence information, combines the assignment range and priority of the task time period, and divides the collaborative operation time window to obtain the time window division results; The sequence adjustment module extracts the priority of the task execution sequence through the time window division result, allocates the task position sequence and the UAV power, optimizes the time interval allocation sequence, and obtains the optimized task execution sequence; The dynamic monitoring module monitors the UAV task completion status and the remaining power according to the optimized task execution sequence, extracts the unfinished task data, compares the task and the UAV status, adjusts the task allocation scope and sequence, and generates the UAV cluster cooperative operation task allocation result.

Images