Civil heterogeneous unmanned cluster control method and system based on ant colony algorithm

Through the ant colony algorithm, the control parameters of the drone swarm are optimized, and the adaptability problem of the drone swarm under mission and environmental changes is solved, and the control accuracy and collaborative execution efficiency are improved.

CN118915559APending Publication Date: 2024-11-08AIR FORCE UNIV PLA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411045509.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the prior art, drone groups are difficult to perform adaptive control based on tasks to be performed and environmental changes, resulting in poor control accuracy.

Method used

Using civil heterogeneous unmanned cluster control methods and systems based on ant colony algorithm, optimize the flight control parameters of the unmanned aircraft by determining the target unmanned cluster, obtaining initialization parameters and task queues to be executed, controlling step by step optimization, and feedback adjustment. .

Benefits of technology

It improves the accuracy of collaborative control and environmental adaptability of the drone, achieving more accurate task execution and environmental adaptation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118915559A_ABST
    Figure CN118915559A_ABST
Patent Text Reader

Abstract

The invention provides a civil heterogeneous unmanned cluster control method and system based on an ant colony algorithm, and relates to the technical field of unmanned aerial vehicle control, and the method comprises the steps: obtaining an initialized group parameter set; obtaining a to-be-executed task queue of the target unmanned cluster; step-by-step control optimization is carried out on the to-be-executed task queue based on the optimization objective function and the initialized group parameter set, and group task execution control parameters are generated; task execution environment information is collected, group task execution control parameters are subjected to feedback adjustment, and optimal control parameters are generated; and controlling the target unmanned cluster according to the optimal control parameter. Through the method and the device, the technical problem of poor control accuracy caused by difficulty in adaptive control based on the to-be-executed task and environment change in the prior art can be solved, task execution optimization is performed on the target unmanned cluster, feedback optimization is performed in combination with the execution environment, and the control accuracy is improved. The technical effect of improving the cooperative control accuracy and environment adaptability of the unmanned aerial vehicle is achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of drone control technology, and in particular to a civilian heterogeneous unmanned aerial vehicle cluster control method and system based on an ant colony algorithm. Background Art

[0002] Due to its low overall cost and flexible use, drones are widely used in civil fields such as agricultural and forestry plant protection, power line inspection, geological surveying and mapping, disaster assessment, aerial photography and entertainment, etc. As the application demand grows, the limited flight capability and mission load of single-platform drones are difficult to meet the application demand, and unmanned swarms have emerged.

[0003] Drone swarms are a system where multiple drones work together to perform tasks. In traditional technology, multiple drones generally perform tasks in a unified formation, which makes it difficult to perform adaptive control based on the tasks to be performed and environmental changes.

[0004] In summary, the prior art has a technical problem of poor control accuracy due to the difficulty in performing adaptive control based on the tasks to be performed and environmental changes. Summary of the invention

[0005] The purpose of this application is to provide a civilian heterogeneous unmanned cluster control method and system based on ant colony algorithm to solve the technical problem in the prior art that it is difficult to perform adaptive control based on the tasks to be performed and environmental changes, resulting in poor control accuracy.

[0006] In view of the above problems, the present application provides a civilian heterogeneous unmanned cluster control method and system based on ant colony algorithm.

[0007] In the first aspect, the present application provides a civilian heterogeneous unmanned cluster control method based on an ant colony algorithm, and the method is implemented by a civilian heterogeneous unmanned cluster control system based on an ant colony algorithm, wherein the method includes: determining a target unmanned cluster and performing group initialization, obtaining an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and drone initialization status information; obtaining a queue of pending tasks of the target unmanned cluster, wherein the queue of pending tasks has a priority identifier; according to the priority identifier, performing step-by-step control optimization on the queue of pending tasks based on an optimization objective function and an initialization group parameter set, and generating group task execution control parameters; collecting task execution environment information, performing feedback adjustment on the group task execution control parameters, and generating optimal control parameters; and controlling the target unmanned cluster according to the optimal control parameters.

[0008] In the second aspect, the present application also provides a civil heterogeneous unmanned cluster control system based on an ant colony algorithm, which is used to execute the civil heterogeneous unmanned cluster control method based on an ant colony algorithm as described in the first aspect, wherein the system includes: a group initialization unit, the group initialization unit is used to determine the target unmanned cluster and perform group initialization, and obtain an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and drone initialization status information; a task queue acquisition unit, the task queue acquisition unit is used to obtain the to-be-executed task queue of the target unmanned cluster, wherein the to-be-executed task queue has a priority identifier; a control optimization unit, the control optimization unit is used to perform step-by-step control optimization on the to-be-executed task queue based on the optimization objective function and the initialization group parameter set according to the priority identifier, and generate group task execution control parameters; a feedback adjustment unit, the feedback adjustment unit is used to collect task execution environment information, perform feedback adjustment on the group task execution control parameters, and generate optimal control parameters; a control unit, the control unit is used to control the target unmanned cluster according to the optimal control parameters.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Determine the target unmanned cluster and perform group initialization, obtain the initialization group parameter set, wherein the initialization group parameter set includes the initialization formation information and the drone initialization state information; obtain the pending task queue of the target unmanned cluster, wherein the pending task queue has a priority identifier; according to the priority identifier, perform step-by-step control optimization on the pending task queue based on the optimization objective function and the initialization group parameter set to generate group task execution control parameters; collect task execution environment information, perform feedback adjustment on the group task execution control parameters, and generate optimal control parameters; control the target unmanned cluster according to the optimal control parameters. By optimizing the task execution of the target unmanned cluster and performing feedback optimization in combination with the execution environment, the technical effect of improving the collaborative control accuracy and environmental adaptability of drones is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 This is a flow chart of the civilian heterogeneous unmanned cluster control method based on the ant colony algorithm of this application;

[0014] Figure 2 This is a schematic diagram of the structure of a civilian heterogeneous unmanned cluster control system based on the ant colony algorithm in this application.

[0015] Explanation of the reference numerals: group initialization unit 11 , task queue acquisition unit 12 , control optimization unit 13 , feedback adjustment unit 14 , control unit 15 . DETAILED DESCRIPTION

[0016] This application provides a civilian heterogeneous unmanned swarm control method and system based on ant colony algorithm, which solves the technical problem of poor control accuracy in the prior art due to the difficulty in adaptive control based on the tasks to be executed and environmental changes. By optimizing the task execution of the target unmanned swarm and performing feedback optimization in combination with the execution environment, the technical effect of improving the coordinated control accuracy and environmental adaptability of the UAV is achieved.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] Embodiment 1

[0019] Please refer to the attached Figure 1 The present application provides a civilian heterogeneous unmanned cluster control method based on an ant colony algorithm, wherein the method is applied to a civilian heterogeneous unmanned cluster control system based on an ant colony algorithm, and the method specifically comprises the following steps:

[0020] Step 1: determine the target unmanned swarm and perform group initialization to obtain an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and UAV initialization state information;

[0021] Specifically, the target unmanned cluster refers to a set of unmanned aerial vehicles to be controlled, which is composed of multiple unmanned aerial vehicles for civilian use, such as unmanned aerial vehicles used for surveying and mapping, aerial photography, etc. The group initialization is to collect the current information of all unmanned aerial vehicles in the target unmanned cluster, that is, the unmanned aerial vehicles may have performed the task in a certain formation, and now to continue to control, it is necessary to obtain the current formation, unmanned aerial vehicle payload and other information for subsequent control. The initialization group parameter set includes the initialization formation information and the unmanned aerial vehicle initialization state information, wherein the initialization formation information is the current formation information of the unmanned aerial vehicles in the target unmanned cluster, and the unmanned aerial vehicle initialization state information refers to the current payload information of the unmanned aerial vehicle, for example, some unmanned aerial vehicles are equipped with various sensors, such as cameras, environmental monitoring equipment, etc., and different payloads can be used to perform different tasks.

[0022] Step 2: Obtain a queue of tasks to be executed of the target unmanned cluster, wherein the queue of tasks to be executed has a priority identifier;

[0023] Specifically, the pending task queue is the tasks waiting to be executed, such as image acquisition of a certain location. The specific needs need to be obtained based on the actual situation. The pending task queue can contain multiple pending tasks. Different tasks have different priorities. The user can mark the task priority by himself based on actual needs through the user terminal to obtain the priority identifier, so that when the drone cannot execute all tasks at the same time, it can give priority to the execution of higher-level tasks.

[0024] Step 3: According to the priority identifier, based on the optimization objective function and the initialization group parameter set, the queue of tasks to be executed is controlled and optimized step by step to generate group task execution control parameters;

[0025] Specifically, according to the priority identifier, the UAV planning is first performed for the task with the highest priority based on the initialization group parameter set, and then the UAV planning is performed for the tasks in the task queue to be executed in order from high to low priority identifiers, and then the UAV planning results are analyzed according to the optimization objective function. The optimization objective function can be understood as a fitness evaluation function, which is used to analyze the UAV planning results, that is, a weighted calculation of the complexity of the adjustment of the UAV queue and the path length in the UAV planning results. The smaller the value of the optimization objective function, the better the optimization effect. By minimizing the optimization objective function, the corresponding group task execution control parameters are obtained. The group task execution control parameters are the control parameters for controlling the flight of the UAVs in the target unmanned cluster, including the control parameters for the flight direction and speed of each UAV.

[0026] Step 4: Collecting task execution environment information, performing feedback adjustment on the group task execution control parameters, and generating optimal control parameters;

[0027] Specifically, the mission execution environment information includes at least weather information and terrain information. Simply put, weather and terrain will affect the flight of the drone. For example, in windy weather, the drone needs to resist wind resistance, so the group mission execution control parameters need to be adjusted, otherwise it will lead to deviations in the control of the drone. Different terrains will cause the drone to fly at different altitudes. For example, when flying in mountainous areas, the drone needs to overcome greater air resistance, so the corresponding group mission execution control parameters also need to be adjusted and optimized. Specifically, the degree of influence of the mission execution environment information on the drone control can be analyzed, so as to conduct feedback adjustment of the group mission execution control parameters and obtain the adjusted optimal control parameters.

[0028] Step 5: Control the target unmanned cluster according to the optimal control parameters.

[0029] Specifically, the optimal control parameters can be input into the control center of the target unmanned cluster for control, thereby achieving precise control of the unmanned cluster and improving task collaborative execution efficiency and control accuracy.

[0030] Furthermore, step one of this application also includes:

[0031] Acquire the data communication module of the target unmanned cluster; activate the data communication module to collect the initialization position information and initialization load information of multiple drones in the target unmanned cluster; initialize the drone queue based on the initialization position information and generate the initialization formation information; perform drone load status analysis based on the initialization load information and generate the drone initialization status information.

[0032] Specifically, the method of determining the target unmanned cluster and initializing the group and obtaining the initialized group parameter set is as follows: the drones in the target unmanned cluster can communicate data, such as through wireless connection, radio frequency transmission, etc., which is a common technical means used by technicians in this field. The data communication module of the target unmanned cluster is a communication module for data transmission and exchange between existing drones, which can transmit its own position to other drones in real time, and finally transmit the information of all drones to the control center. The data communication module is activated to collect the initialization position information and initialization load information of multiple drones in the target unmanned cluster. The initialization load information is the usage of the equipment carried by the drone for performing tasks, such as the remaining power of the camera.

[0033] Initializing the drone queue based on the initialization position information means obtaining the positions and distances of different drones according to the initialization position information, and using this as the initialization formation information. Analyzing the drone load status based on the initialization load information means analyzing the usable time of the device based on its usage and using this as the initialization load information. Generally, the usage time of the device when fully charged is fixed and can be obtained based on actual experience. Then, the initialization load information is subtracted, and the result is the drone initialization status information. This achieves the initialization of the target unmanned cluster and provides a basis for subsequent unmanned cluster control.

[0034] Furthermore, step three of this application also includes:

[0035] The queue of tasks to be executed is serialized and reconstructed according to the priority identifier to generate a task priority queue; the task priority queue has a task type identifier, and the task type identifier includes a single-machine independent task identifier, a multi-machine collaborative task identifier and a task requirement load identifier; based on the task type identifier, a candidate drone group sequence of the queue of tasks to be executed is generated; based on the initialized group parameter set, the candidate drone group sequence and the optimization objective function, the drone task execution path is optimized to generate the group task execution control parameter.

[0036] Furthermore, the present application also includes the following steps:

[0037] Based on the mission requirement load identifier and the drone initialization state information, drone load matching is performed to generate a first candidate drone group sequence; drone combination is performed on the first candidate drone group sequence according to the single-machine independent task identifier and the multi-machine collaborative task identifier to generate the candidate drone group sequence.

[0038] Furthermore, the present application also includes the following steps:

[0039] Based on the initialization formation information and the candidate drone group sequence, drone task path planning is performed to generate a candidate task queue adjustment timing and a candidate drone path sequence; based on the candidate task queue adjustment timing, unmanned cluster queue complexity identification is performed to generate a first candidate complexity index; based on the candidate drone path sequence, total path length identification is performed to generate a first candidate path length index; based on the optimization objective function, the first candidate complexity index and the first candidate path length index are normalized and weightedly calculated to obtain a first fitness; based on the first fitness, fitness minimization is performed to obtain the target candidate task queue adjustment timing and target candidate drone path sequence corresponding to the minimum fitness, and the group task execution control parameters are generated.

[0040] Specifically, the method for performing step-by-step control optimization on the to-be-executed task queue based on the optimization objective function and the initialization group parameter set is as follows:

[0041] First, the tasks in the to-be-executed task queue are reordered according to the priority identifier, and the ordering result is used as the task priority queue. The task priority queue has a task type identifier, and the task type identifier includes a single-machine independent task identifier, a multi-machine collaborative task identifier, and a task requirement load identifier. A single-machine independent task refers to a task that only requires one drone to perform, such as taking an image of a flat position. A multi-machine collaborative task is a task that requires two or more drones, such as a certain position that requires multi-angle images, or the need to take images and collect the environment at the same time. The task requirement load identifier is the type of equipment required and the time the equipment can continuously execute the task. The task type identifier is generally identified by the user through the user terminal.

[0042] Further based on the task type identifier, the candidate drone group sequence of the to-be-executed task queue is generated, that is, the drone matching the task type identifier is obtained, the drone corresponding to each task that can be used to execute the task is obtained, and the candidate drone group sequence is obtained. The specific method is: based on the task requirement load identifier and the drone initialization state information, the drone load is matched, and the drone group that meets the task requirement load identifier corresponding to each task is obtained as the first candidate drone group sequence. Further, the first candidate drone group sequence is combined with drones according to the single-machine independent task identifier and the multi-machine collaborative task identifier, that is, according to the single-machine independent task identifier and the multi-machine collaborative task identifier, the number of drones required for the task is determined, and the drones are randomly combined in the unmanned cluster corresponding to the first candidate drone group sequence according to the number of drones required for the task, to obtain a variety of combination results, one task corresponds to a variety of combination results, and the combination results of multiple tasks are arranged as the candidate drone group sequence. In this way, the preliminary combination of drones is achieved, which is convenient for subsequent control optimization.

[0043] Based on the initialization group parameter set, the candidate drone group sequence and the optimization objective function, the drone task execution path is optimized to generate the group task execution control parameters, and the specific method is as follows:

[0044] First, based on the initialization formation information and the candidate drone group sequence, the drone task path planning is performed, that is, based on the initialization formation information, the drones in the candidate drone group sequence are adjusted in the direction of the task destination, and the drone queue in the adjustment process is used as the candidate task queue adjustment timing, and the flight path of the drone in the adjustment process is used as the candidate drone path sequence. Based on the candidate task queue adjustment timing, the unmanned cluster queue complexity identification is performed. In simple terms, it is to compare the difference between the candidate task queue adjustment timing and the initialization formation information, and use the difference as the first candidate complexity index. Then, based on the candidate drone path sequence, the total path length calculation is performed, and the calculation result is used as the first candidate path length index. Then, based on the optimization objective function, the first candidate complexity index and the first candidate path length index are normalized and weighted. Normalization is to limit the first candidate complexity index and the first candidate path length index to a certain range, so that the data has a unified dimension and evaluation standard, and prevent small data from being swallowed by big data. It is a common technical means for those skilled in the art and will not be expanded here. In simple terms, the optimization objective function is a formula for performing weighted average calculation on the first candidate complexity index and the first candidate path length index, thereby calculating the first fitness.

[0045] Fitness minimization based on the first fitness is to iteratively adjust the candidate task queue adjustment timing and candidate drone path sequence of different drones according to the candidate drone group sequence until a preset number of iterations, such as 50 times, is reached, and then the target candidate task queue adjustment timing and target candidate drone path sequence corresponding to the minimum fitness are obtained, and the target candidate task queue adjustment timing and target candidate drone path sequence are used as control targets, and the control center generates control parameters for controlling the flight of drones in the target unmanned cluster, such as flight direction, flight distance, etc. as the group task execution control parameters. In this way, the optimization of the task execution path is achieved, and the efficiency of drone task collaborative execution is improved.

[0046] Furthermore, step 4 of this application also includes:

[0047] The task execution environment information includes at least weather information and terrain information; based on the weather information and the terrain information, the UAV control offset analysis is performed to generate an offset impact index; according to the offset impact index, the group task execution control parameters are feedback optimized to generate the optimal control parameters.

[0048] Specifically, the task execution environment information is collected, the group task execution control parameters are adjusted for feedback, and the optimal control parameters are generated. The specific method is: weather information can be collected through environmental sensors carried by drones, such as wind sensors, and the terrain information of the location of the target unmanned cluster, such as altitude, can be further collected based on the existing geographic information system. The drone control offset analysis is performed based on the weather information and the terrain information. That is, the weather information and the terrain information will cause errors in the control of the drone, such as errors in flight distance and direction. Specifically, the offset impact index samples of the drones in the target unmanned cluster under historical weather information and historical terrain information can be collected, wherein the offset impact index samples are the degree of deviation between the control parameters issued by the control center to the drone and the actual control results of the drone. Based on the existing machine learning model, an offset impact analysis model is constructed, and historical weather information, historical terrain information and corresponding offset impact index samples are used as training data for training. The offset impact analysis model trained to convergence is used to analyze the task execution environment information and output the offset impact index. Finally, the offset impact index is multiplied by the group task execution control parameter to generate the optimal control parameter. This will enable control optimization combined with the environment, improve the environmental adaptability of unmanned cluster control, and enhance control accuracy.

[0049] Furthermore, the present application also includes the following steps:

[0050] Read the drone specification information set of the target unmanned cluster; perform clustering based on the drone specification information set to generate a drone type set; collect electromagnetic environment information of the environment in which the target unmanned cluster is located; extract a first drone type from the drone type set, perform control safety impact identification based on the electromagnetic environment information and the first drone type, and generate a first risk adaptation index; when the first risk adaptation index exceeds a predetermined index threshold, generate a reminder message.

[0051] Specifically, the drone specification information set includes information such as the model, size, and communication frequency band of the drone, which can be directly read through the user manual of the drone in the target unmanned cluster. Further use the existing clustering algorithm, such as the k-means algorithm, to cluster based on the drone specification information set, that is, to group objects with similar drone specification information into a group to generate a drone type set. Electromagnetic environment information refers to the electromagnetic signal characteristics of the area where the target drone cluster is located, including the intensity of electromagnetic waves, frequency band occupancy, interference sources, etc., which can be directly collected through existing electromagnetic environment monitoring equipment. Extract any drone type from the drone type set as the first drone type, identify the control safety impact based on the electromagnetic environment information and the first drone type, and generate the first risk adaptation index, that is, analyze the control safety risk of the first drone type in the current environment. The first risk adaptation index reflects the degree of existing safety risk. For example, if the electromagnetic environment has a certain degree of control impact on the drone, it will make it difficult for the drone control center to control the flight of the drone, resulting in the risk of collision, falling, etc., and its first risk adaptation index is higher. Specifically, the historical control records of the same drone as the first drone type under different historical electromagnetic environments can be obtained, and the proportion of control loss records is calculated based on the historical control records, and the proportion calculation result is used as a risk adaptation index sample. A risk database is established with historical electromagnetic environment and risk adaptation index samples, and then a comparison is performed in the risk database based on the electromagnetic environment information to obtain the risk adaptation index sample corresponding to the electromagnetic environment information as the first risk adaptation index. When the first risk adaptation index exceeds the predetermined index threshold, a reminder message is generated. The predetermined index threshold is set by professional and technical personnel in this field based on actual experience. That is to say, if the first risk adaptation index exceeds the predetermined index threshold, it means that the electromagnetic environment has too much influence on the control of the drone. At this time, a reminder message is generated to remind the staff to intervene in time, such as setting anti-interference equipment on the drone to prevent the drone from losing control.

[0052] In summary, the civilian heterogeneous unmanned swarm control method based on ant colony algorithm provided in this application has the following technical effects:

[0053] Determine the target unmanned cluster and perform group initialization, obtain the initialization group parameter set, wherein the initialization group parameter set includes the initialization formation information and the drone initialization state information; obtain the pending task queue of the target unmanned cluster, wherein the pending task queue has a priority identifier; according to the priority identifier, perform step-by-step control optimization on the pending task queue based on the optimization objective function and the initialization group parameter set to generate group task execution control parameters; collect task execution environment information, perform feedback adjustment on the group task execution control parameters, and generate optimal control parameters; control the target unmanned cluster according to the optimal control parameters. By optimizing the task execution of the target unmanned cluster and performing feedback optimization in combination with the execution environment, the technical effect of improving the collaborative control accuracy and environmental adaptability of drones is achieved.

[0054] Embodiment 2

[0055] Based on the same inventive concept as the civilian heterogeneous unmanned cluster control method based on the ant colony algorithm in the aforementioned embodiment, the present application also provides a civilian heterogeneous unmanned cluster control system based on the ant colony algorithm, please refer to the attached Figure 2 , the system comprising:

[0056] A group initialization unit 11, the group initialization unit 11 is used to determine the target unmanned cluster and perform group initialization, and obtain an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and UAV initialization state information;

[0057] A task queue acquisition unit 12, wherein the task queue acquisition unit 12 is used to acquire a to-be-executed task queue of the target unmanned cluster, wherein the to-be-executed task queue has a priority identifier;

[0058] A control optimization unit 13, the control optimization unit 13 is used to perform step-by-step control optimization on the to-be-executed task queue according to the priority identifier based on an optimization objective function and an initialization group parameter set, and generate a group task execution control parameter;

[0059] A feedback adjustment unit 14, the feedback adjustment unit 14 is used to collect task execution environment information, perform feedback adjustment on the group task execution control parameters, and generate optimal control parameters;

[0060] A control unit 15 is used to control the target unmanned cluster according to the optimal control parameters.

[0061] Furthermore, the group initialization unit 11 in the system is also used for:

[0062] Acquire a data communication module of the target unmanned cluster;

[0063] Activate the data communication module to collect initialization position information and initialization load information of multiple drones in the target unmanned cluster;

[0064] Initialize the UAV queue based on the initialization position information to generate the initialization formation information;

[0065] The UAV load status analysis is performed based on the initialization load information to generate the UAV initialization status information.

[0066] Furthermore, the control optimization unit 13 in the system is also used for:

[0067] Serializing and reconstructing the to-be-executed task queue according to the priority identifier to generate a task priority queue;

[0068] The task priority queue has a task type identifier, and the task type identifier includes a single-machine independent task identifier, a multi-machine collaborative task identifier, and a task demand load identifier;

[0069] Generate a candidate drone group sequence for the to-be-executed task queue based on the task type identifier;

[0070] Based on the initialization group parameter set, the candidate drone group sequence and the optimization objective function, the drone task execution path is optimized to generate the group task execution control parameters.

[0071] Furthermore, the control optimization unit 13 in the system is also used for:

[0072] Performing drone load matching based on the mission requirement load identifier and the drone initialization state information to generate a first candidate drone group sequence;

[0073] The first candidate drone group sequence is combined with drones according to the single-machine independent task identifier and the multi-machine collaborative task identifier to generate the candidate drone group sequence.

[0074] Furthermore, the control optimization unit 13 in the system is also used for:

[0075] Perform UAV task path planning based on the initialization formation information and the candidate UAV group sequence, and generate a candidate task queue adjustment timing and a candidate UAV path sequence;

[0076] Based on the candidate task queue adjustment timing, the complexity of the unmanned cluster queue is identified to generate a first candidate complexity index;

[0077] Performing path total length identification based on the candidate UAV path sequence to generate a first candidate path length indicator;

[0078] Based on the optimization objective function, performing normalized weighted calculation on the first candidate complexity index and the first candidate path length index to obtain a first fitness;

[0079] The fitness is minimized based on the first fitness, the target candidate task queue adjustment timing and the target candidate UAV path sequence corresponding to the minimum fitness are obtained, and the group task execution control parameters are generated.

[0080] Furthermore, the feedback adjustment unit 14 in the system is also used for:

[0081] The task execution environment information includes at least weather information and terrain information;

[0082] Performing a UAV control deviation analysis based on the weather information and the terrain information to generate a deviation impact index;

[0083] Feedback optimization is performed on the group task execution control parameters according to the offset impact index to generate the optimal control parameters.

[0084] Furthermore, the system further includes a risk reminder unit, which is used to:

[0085] Read the drone specification information set of the target unmanned cluster;

[0086] Perform clustering based on the drone specification information set to generate a drone type set;

[0087] Collecting electromagnetic environment information of the environment in which the target unmanned cluster is located;

[0088] Extracting a first drone type from the drone type set, identifying control safety impact based on the electromagnetic environment information and the first drone type, and generating a first risk adaptation indicator;

[0089] When the first risk adaptation indicator exceeds a predetermined indicator threshold, a reminder message is generated.

[0090] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The civilian heterogeneous unmanned cluster control method based on ant colony algorithm and the specific examples in the first embodiment are also applicable to the civilian heterogeneous unmanned cluster control system based on ant colony algorithm in this embodiment. Through the above detailed description of the civilian heterogeneous unmanned cluster control method based on ant colony algorithm, those skilled in the art can clearly know the civilian heterogeneous unmanned cluster control system based on ant colony algorithm in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0091] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0092] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A civil heterogeneous unmanned cluster control method based on ant colony algorithm, characterized in that: include: Determine the target unmanned cluster and perform group initialization to obtain an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and initialization state information of unmanned aerial vehicles; Obtaining a to-be-executed task queue of the target unmanned cluster, wherein the to-be-executed task queue has a priority identifier; According to the priority identifier, based on the optimization objective function and the initialization group parameter set, the queue of tasks to be executed is controlled and optimized step by step to generate group task execution control parameters; Collecting task execution environment information, performing feedback adjustment on the group task execution control parameters, and generating optimal control parameters; The target unmanned cluster is controlled according to the optimal control parameters.

2. The method according to claim 1, characterized in that The step of determining the target unmanned cluster and initializing the cluster to obtain the initialization cluster parameter set includes: Acquire a data communication module of the target unmanned cluster; Activate the data communication module to collect initialization position information and initialization load information of multiple drones in the target unmanned cluster; Initialize the UAV queue based on the initialization position information to generate the initialization formation information; The UAV load status analysis is performed based on the initialization load information to generate the UAV initialization status information.

3. The method according to claim 1, characterized in that The step-by-step control optimization of the to-be-executed task queue based on the optimization objective function and the initialization group parameter set includes: Serializing and reconstructing the to-be-executed task queue according to the priority identifier to generate a task priority queue; The task priority queue has a task type identifier, and the task type identifier includes a single-machine independent task identifier, a multi-machine collaborative task identifier, and a task demand load identifier; Generate a candidate drone group sequence for the to-be-executed task queue based on the task type identifier; Based on the initialization group parameter set, the candidate drone group sequence and the optimization objective function, the drone task execution path is optimized to generate the group task execution control parameters.

4. The method according to claim 3, characterized in that The generating a candidate drone group sequence of the to-be-executed task queue based on the task type identifier includes: Performing drone load matching based on the mission requirement load identifier and the drone initialization state information to generate a first candidate drone group sequence; The first candidate drone group sequence is combined with drones according to the single-machine independent task identifier and the multi-machine collaborative task identifier to generate the candidate drone group sequence.

5. The method according to claim 3, characterized in that The step of optimizing the drone task execution path based on the initialized group parameter set, the candidate drone group sequence and the optimization objective function to generate the group task execution control parameter includes: Perform UAV task path planning based on the initialization formation information and the candidate UAV group sequence, and generate a candidate task queue adjustment timing and a candidate UAV path sequence; Based on the candidate task queue adjustment timing, the complexity of the unmanned cluster queue is identified to generate a first candidate complexity index; Performing path total length identification based on the candidate UAV path sequence to generate a first candidate path length indicator; Based on the optimization objective function, performing normalized weighted calculation on the first candidate complexity index and the first candidate path length index to obtain a first fitness; The fitness is minimized based on the first fitness, the target candidate task queue adjustment timing and the target candidate UAV path sequence corresponding to the minimum fitness are obtained, and the group task execution control parameters are generated.

6. The method according to claim 1, characterized in that The collecting of task execution environment information, feedback adjustment of group task execution control parameters, and generation of optimal control parameters include: The task execution environment information includes at least weather information and terrain information; Performing a UAV control deviation analysis based on the weather information and the terrain information to generate a deviation impact index; Feedback optimization is performed on the group task execution control parameters according to the offset impact index to generate the optimal control parameters.

7. The method according to claim 1, characterized in that After the target unmanned cluster is controlled according to the optimal control parameters, the method further includes: Read the drone specification information set of the target unmanned cluster; Perform clustering based on the drone specification information set to generate a drone type set; Collecting electromagnetic environment information of the environment in which the target unmanned cluster is located; Extracting a first drone type from the drone type set, identifying control safety impact based on the electromagnetic environment information and the first drone type, and generating a first risk adaptation indicator; When the first risk adaptation indicator exceeds a predetermined indicator threshold, a reminder message is generated.

8. A civil heterogeneous unmanned cluster control system based on ant colony algorithm, characterized by: For implementing the steps of the method according to any one of claims 1 to 7, the system comprises: A group initialization unit, the group initialization unit is used to determine the target unmanned cluster and perform group initialization, and obtain an initialization group parameter set, wherein the initialization group parameter set includes initialization formation information and UAV initialization state information; A task queue acquisition unit, the task queue acquisition unit is used to acquire a to-be-executed task queue of the target unmanned cluster, wherein the to-be-executed task queue has a priority identifier; A control optimization unit, the control optimization unit is used to perform step-by-step control optimization on the to-be-executed task queue according to the priority identifier based on an optimization objective function and an initialization group parameter set, and generate a group task execution control parameter; A feedback adjustment unit, the feedback adjustment unit is used to collect task execution environment information, perform feedback adjustment on the group task execution control parameters, and generate optimal control parameters; A control unit is used to control the target unmanned cluster according to the optimal control parameters.