Cooperative cluster control method, device and equipment for unmanned aerial vehicles, and storage medium

Abstract

The invention provides a cooperative cluster control method, device and equipment for unmanned aerial vehicles, and a storage medium, in an initial stage, initial information of N unmanned aerial vehicles in a cluster is acquired, and a pilot weight value of each unmanned aerial vehicle is calculated based on the initial information, and the initial information comprises a missile loading amount, a combat radius and endurance time; then, determining a piloting unmanned aerial vehicle according to the piloting weight value of each unmanned aerial vehicle, and calculating communication delay between the piloting unmanned aerial vehicle and other unmanned aerial vehicles in the cluster; and finally, clustering and grouping other unmanned aerial vehicles in the cluster according to the communication delay, randomly selecting one unmanned aerial vehicle from each group as a secondary piloting unmanned aerial vehicle, generating a communication routing table, and synchronizing the communication routing table to each unmanned aerial vehicle in the cluster, and the secondary pilot unmanned aerial vehicle is used for communicating with the unmanned aerial vehicles in the group and the pilot unmanned aerial vehicle. The problem that the cluster is easy to be out of control in the existing communication mode of the piloting unmanned aerial vehicle and the cluster is solved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicles, and in particular to a cooperative cluster control method, device, equipment and storage medium for unmanned aerial vehicles. Background Art

[0002] The pilot-follower method is commonly used in the coordinated control of drone swarms. It has the advantages of simplicity, high efficiency, and high formation accuracy. However, the traditional pilot-follower method requires all drones in the swarm to communicate directly with the pilot drone, which results in excessive communication volume and increases the system burden. Moreover, when the pilot drone fails, it is easy to cause the entire drone swarm to lose control.

[0003] In view of this, this application is filed. Summary of the invention

[0004] The present invention discloses a cooperative cluster control method, device, equipment and storage medium of unmanned aerial vehicles, aiming to solve the problem that the existing communication mode between pilot unmanned aerial vehicles and clusters is prone to cluster out of control.

[0005] A first embodiment of the present invention provides a collaborative cluster control method for unmanned aerial vehicles, comprising: In the initial stage, the initial information of N drones in the cluster is obtained, and the pilot weight value of each drone is calculated based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; Determine a pilot drone according to the pilot weight value of each drone, and calculate the communication delay between the pilot drone and other drones in the cluster; The other drones in the cluster are clustered and grouped according to the communication delay, a drone is randomly selected from each group as a secondary pilot drone, and a communication routing table is generated and synchronized to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone.

[0006] Preferably, the determining of the pilot drone according to the pilot weight value of each drone is specifically: Create a voting box for each drone, control each drone in the cluster to vote for itself at the beginning, and make each drone pass its own vote to other drones and receive votes from other drones at the same time; Compare the received voting weights, and if the received voting weight is higher than its own weight, modify the vote to point to the drone with a higher weight; The voting status is continuously counted, and when more than half of the drones vote for the same drone, the drone is set as the pilot drone.

[0007] Preferably, clustering and grouping other drones in the cluster according to the communication delay is specifically as follows: The communication delay time is fused with the drone navigation weight value to generate a weight array. Based on the weight array, a clustering grouping algorithm is executed to divide the drone cluster into k=(N-1) / t groups. The distance between drones is calculated using the Euclidean distance formula, and clustering is completed through an iterative optimization process, where t represents the expected number of drones in each group.

[0008] Preferably, the execution process of the clustering grouping algorithm is: S21 randomly selects k initial centroid vectors , where each centroid vector Represents the coordinates of the drone weight combination data in the multidimensional feature space; S22 will be each drone's weight array The Euclidean distance formula is used to calculate the distance between the centroid vectors The distance between , and its calculation formula is:

[0009] in, represents the value of drone i on the lth feature, Represents the centroid vector The value of the lth feature, and Assign to make The smallest cluster ; S23 For each cluster , update the cluster center according to the following formula :

[0010] in, Represents the jth cluster, which contains several data points , Representation clustering The total number of data points in , , which means clustering All data points in are accumulated, Represents the new cluster center; Repeat steps S22 and S23 until all centroid vectors no longer change and output the clustering grouping results.

[0011] Preferably, it also includes: The communication routing table is used to guide the drone cluster to perform intermittent heartbeat monitoring and detect the status of the pilot drone. When the pilot drone is detected to be out of control or offline, the whole cluster is immediately triggered to re-elect the pilot drone.

[0012] A second embodiment of the present invention provides a coordinated cluster control device for unmanned aerial vehicles, comprising: A weight calculation unit, used to obtain initial information of N drones in the cluster at the start stage, and calculate the navigation weight value of each drone based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; a communication delay calculation unit, configured to determine a pilot UAV according to the pilot weight value of each UAV, and calculate the communication delay between the pilot UAV and other UAVs in the cluster; A communication routing table generating unit is used to cluster and group other drones in the cluster according to the communication delay, randomly select a drone from each group as a secondary pilot drone, and generate a communication routing table to synchronize to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone.

[0013] The third embodiment of the present invention provides a collaborative cluster control device for drones, characterized in that it includes a memory and a processor, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement a collaborative cluster control method for drones as described in any one of the above items.

[0014] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a collaborative cluster control method for drones as described in any one of the above items.

[0015] Based on the cooperative cluster control method, device, equipment and storage medium of drones provided by the present invention, in the initial stage, the initial information of N drones in the cluster is obtained, and the pilot weight value of each drone is calculated based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; then, the pilot drone is determined according to the pilot weight value of each drone, and the communication delay between the pilot drone and other drones in the cluster is calculated; finally, the other drones in the cluster are clustered and grouped according to the communication delay, and a drone is randomly selected from each group as a secondary pilot drone, and a communication routing table is generated and synchronized to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone. The problem that the existing communication method between the pilot drone and the cluster is prone to cluster out of control is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a cooperative cluster control method of unmanned aerial vehicles provided by the first embodiment of the present invention; Figure 2It is a schematic diagram of the drone election process provided by the present invention; Figure 3 It is a schematic diagram of cluster routing communication provided by the present invention; Figure 4 It is a module schematic diagram of a cooperative cluster control device for unmanned aerial vehicles provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0019] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0021] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0022] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0023] The "first\second" mentioned in the embodiments is only to distinguish similar objects, and does not represent a specific order for the objects. It is understandable that the "first\second" can be interchanged with the specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] The present invention discloses a cooperative cluster control method, device, equipment and storage medium of unmanned aerial vehicles, aiming to solve the problem that the existing communication mode between pilot unmanned aerial vehicles and clusters is prone to cluster out of control.

[0026] See also Figure 1 The first embodiment of the present invention provides a cooperative cluster control method for UAVs, which can be executed by a cooperative cluster control device for UAVs (hereinafter referred to as a control device), and in particular, by one or more processors in the control device, to implement at least the following steps: S101, in the initial stage, obtaining initial information of N drones in the cluster, and calculating the navigation weight value of each drone based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; In this embodiment, the control device can be a terminal with data processing capabilities such as a server, a desktop computer, a laptop computer, etc., which can communicate with each drone in the cluster. The control device can be installed with a corresponding operating system and application software, and the functions required by this embodiment can be implemented through the combination of the operating system and application software.

[0027] It should be noted that in this embodiment, when the mission is initiated, the control device first establishes a stable connection with each drone in the cluster through a pre-configured communication network, so as to collect the initial status data of each drone in real time. These data may include but are not limited to payload, combat radius and endurance time.

[0028] The control device adds up the payload, combat radius and endurance of the drone according to the predetermined weight coefficient, and can use the formula uav_i_leader_weight=uav_payload_am×0.4+uav_radius×0.3+uav_endurance×0.3 to calculate the leader weight value of each drone, so that the control device can quickly and accurately quantify the comprehensive combat capability of each drone.

[0029] In a possible implementation of the present invention, a dynamic adjustment mechanism is introduced into the initial weight calculation formula so that the weight coefficients of the payload, combat radius and endurance of the drone can be adaptively changed under different mission scenarios or environmental conditions. For example, in long-distance reconnaissance or high-intensity missions, the endurance of the drone may appear to be more critical. At this time, the control device can increase the weight coefficient of the endurance from the original 0.3 to 0.5 or higher by real-time monitoring of mission requirements and environmental parameters, and correspondingly reduce the weight of the payload or combat radius to more accurately reflect the actual requirements of the current mission for the combat capability of the drone. On the other hand, if the mission requires a higher strike capability, the importance of the payload may increase. At this time, the control device can dynamically increase the weight of the payload, and in specific environments, such as complex terrain or crowded war zones, the impact of the combat radius may also need to be further amplified, thereby adjusting to a higher weight coefficient.

[0030] S102, determining a pilot drone according to the pilot weight value of each drone, and calculating the communication delay between the pilot drone and other drones in the cluster; Please combine Figure 2 In the specific implementation, the control device first requires each drone to create an independent voting box when it starts up, and vote for itself during initialization, that is, each drone records its own pilot weight as the basis for voting in the voting box. Subsequently, each drone transmits its own voting information to all other drones in the cluster according to the predetermined communication protocol, and receives voting data from other drones at the same time. Each drone continuously compares its own pilot weight with the voting weights obtained from other drones to detect in real time whether there is a candidate with a higher weight; once it finds that the weight of a drone in the received voting information is higher than its own, it will automatically adjust the voting direction and turn its vote to the drone with a higher weight.

[0031] It should be noted that the dynamic vote transfer mechanism enables each drone to always maintain its recognition of the best pilot candidate in the cluster, thus forming a self-organizing voting network. The control device continuously counts and monitors the voting status of all drones in the background, and when it detects that more than half of the drones have voted for the same drone, it immediately confirms that the drone is the pilot drone and triggers the subsequent communication route construction and task allocation process. This allows the cluster to quickly and accurately elect the pilot drone with the most comprehensive combat capability without a central node, effectively reducing the risk caused by single point failures.

[0032] Furthermore, when the pilot drone is elected, the drone immediately enters the calculation stage of the communication link routing table. First, the pilot drone establishes a real-time connection with each drone in the cluster through a preset communication protocol, and uses multiple round-trip data transmissions to accurately measure the communication delay of each link, thereby obtaining the delay time between each drone. Subsequently, the pilot drone fuses these real-time measured communication delay data with the pilot weight values ​​previously calculated by each drone to form a new weight array, which is expressed in the form of uva_cluster_list=[(time(Ei_j),uav_i_leader_weight),(time(Ei_k),uav_k_leader_weight)], where time(Ei_j) represents the communication delay between drone i and drone j, and uav_i_leader_weight represents the comprehensive combat capability of drone i. This fusion accurately reflects the real-time communication status of each link.

[0033] S103, clustering and grouping other drones in the cluster according to the communication delay, randomly selecting a drone from each group as a secondary pilot drone, and generating a communication routing table and synchronizing it to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone.

[0034] It should be noted that by calculating the communication delay between drones, the actual communication quality and distance between nodes can be intuitively reflected, thereby providing an important basis for optimizing the communication architecture of the entire cluster. In practical applications, drone clusters are often distributed in a wide area, and the communication links between different nodes may be affected by factors such as physical distance, environmental interference or signal shielding, resulting in different delays. After these delay data are integrated with the pilot weights of the drones, they are clustered and grouped, which can effectively divide drones with better communication conditions and faster response speeds into the same group, so that the nodes within each group can achieve information exchange and coordinated operations in a shorter time, while reducing the long-distance and high-delay communication load in the entire cluster. After grouping, a secondary pilot drone can also be selected in each group to centrally process the data within the group, realizing hierarchical management and distributed control, thereby reducing the overall communication burden while enhancing the robustness of the system in the face of single point failures or link interruptions.

[0035] Specifically, please combine Figure 3In practical applications, after the control device obtains the communication delay data of each drone, it first integrates these delay data with the pre-calculated pilot weight values ​​of each drone to generate a weight array that comprehensively reflects the communication status and combat capability. This weight array not only reflects the actual communication delay between drones, but also integrates their respective performance indicators; next, the control device calculates the number of clustering groups k based on the total number of drones N in the cluster and the expected number of each group t, where k=(N-1) / t, which can be determined by appropriate rounding.

[0036] In the clustering process, the control device first randomly selects k initial centroid vectors in the multidimensional feature space. Each centroid vector represents an initial center position of the drone weight combination data. Then, the Euclidean distance between the weight array of each drone and each centroid vector is calculated. The calculation formula is: ,in, represents the value of drone i on the lth feature, Represents the value of the centroid vector uⱼ on the lth feature, and Assign to make The smallest cluster , The control device assigns each drone to the cluster with the closest centroid. Then, for each drone in each cluster, the update formula is used To recalculate the cluster centers, Represents the jth cluster, which contains several data points , Representation clustering The total number of data points in , , which means clustering All data points in are accumulated, Represents the new cluster center; The control device continuously repeats the iterative process of calculating the Euclidean distance and updating the centroid until all centroid vectors become stable and no longer change, and finally outputs the clustering grouping results. The drones can be accurately divided into groups under different communication conditions.

[0037] It should be noted that after the clustering is completed, a UAV is randomly selected from each group as the secondary pilot aircraft, aiming to simplify the selection mechanism and balance the load within each group. Since the clustering process has divided the UAVs into several subsets with similar communication quality and combat capability based on multi-dimensional features such as communication delay and pilot weight, the overall performance of each UAV in each subset has a certain homogeneity. At this time, the random selection method can avoid introducing additional computational complexity or additional selection criteria, while ensuring that each group is representative, without the need for more complex sorting or comparison of the specific details of each UAV in the group. In addition, this random selection method also helps to prevent excessive concentration of communication load on a specific UAV, because in a dynamic environment, if a group's secondary pilot aircraft fails due to a malfunction or other reasons, it is relatively simple and quick to randomly select a new representative.

[0038] Furthermore, the pilot drone synchronizes the routing table to each drone in the cluster through a pre-set reliable data transmission protocol. In this way, each drone can obtain the latest communication path information and link status, so as to clarify the best path and method for communicating with other nodes. The practice of synchronizing communication routing tables can not only eliminate the problem of local communication interruption caused by the failure of a single node or link, but also enable each drone to autonomously select the optimal transmission path according to a unified and global routing strategy when receiving mission instructions or sensor data, thereby minimizing transmission delays and improving the reliability of information transmission. In addition, this global synchronization mechanism also provides a rapid response and self-repair capability for the drone cluster. When communication anomalies occur or the pilot drone fails, other drones can quickly adjust the communication path according to the locally stored routing table to ensure the overall stable operation of the cluster.

[0039] In a possible implementation of the present invention, the present invention further includes: The communication routing table is used to guide the drone cluster to perform intermittent heartbeat monitoring and detect the status of the pilot drone. When the pilot drone is detected to be out of control or offline, the whole cluster is immediately triggered to re-elect the pilot drone.

[0040] It should be noted that all drones form a real-time updated network through synchronized communication routing tables, and each drone sends and receives heartbeat information at preset time intervals to monitor the operating status of the pilot drone in real time. Specifically, the current pilot drone needs to broadcast its own status information, including control indicators and communication quality parameters, within a fixed period, and transmit these heartbeat data to the entire cluster through a predetermined communication route. When other drones fail to receive the heartbeat data from the pilot drone within the specified time window, or find abnormal conditions in the received heartbeat data (such as control failure, data abnormality or obvious signal attenuation), these drones will immediately report abnormal information to neighboring nodes through the network and cross-verify the situations detected by each. After global information sharing, when a certain proportion of drones in the cluster confirm that the pilot drone is out of control or offline, the system will automatically trigger the re-election process. At this time, all drones quickly complete the re-election of the pilot drone according to the pre-defined voting rules, and update the new communication routing table at the same time to ensure that the entire cluster can restore normal communication and command and control in the shortest time.

[0041] See also Figure 4 The second embodiment of the present invention provides a cooperative cluster control device for unmanned aerial vehicles, comprising: The weight calculation unit 201 is used to obtain the initial information of the N drones in the cluster at the start stage, and calculate the navigation weight value of each drone based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; The communication delay calculation unit 202 is used to determine the pilot UAV according to the pilot weight value of each UAV, and calculate the communication delay between the pilot UAV and other UAVs in the cluster; The communication routing table generating unit 203 is used to cluster and group other UAVs in the cluster according to the communication delay, randomly select a UAV from each group as a secondary pilot UAV, and generate a communication routing table and synchronize it to each UAV in the cluster, wherein the secondary pilot UAV is used to communicate with the UAVs in the group and the pilot UAV.

[0042] The third embodiment of the present invention provides a collaborative cluster control device for drones, characterized in that it includes a memory and a processor, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement a collaborative cluster control method for drones as described in any one of the above items.

[0043] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a collaborative cluster control method for drones as described in any one of the above items.

[0044] Based on the cooperative cluster control method, device, equipment and storage medium of drones provided by the present invention, in the initial stage, the initial information of N drones in the cluster is obtained, and the pilot weight value of each drone is calculated based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; then, the pilot drone is determined according to the pilot weight value of each drone, and the communication delay between the pilot drone and other drones in the cluster is calculated; finally, the other drones in the cluster are clustered and grouped according to the communication delay, and a drone is randomly selected from each group as a secondary pilot drone, and a communication routing table is generated and synchronized to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone. The problem that the existing communication method between the pilot drone and the cluster is prone to cluster out of control is solved.

[0045] Exemplarily, the computer program described in the third and fourth embodiments of the present invention may be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the collaborative cluster control device for implementing a drone. For example, the device described in the second embodiment of the present invention.

[0046] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the cooperative cluster control method of a UAV, and uses various interfaces and lines to connect the various parts of the entire method for implementing the cooperative cluster control of a UAV.

[0047] The memory can be used to store the computer program and / or module, and the processor realizes various functions of a cooperative cluster control method of a drone by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0048] Wherein, if the implemented module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0049] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0050] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A collaborative cluster control method for unmanned aerial vehicles, characterized in that: include: In the initial stage, the initial information of N drones in the cluster is obtained, and the pilot weight value of each drone is calculated based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; Determine a pilot drone according to the pilot weight value of each drone, and calculate the communication delay between the pilot drone and other drones in the cluster; The other drones in the cluster are clustered and grouped according to the communication delay, a drone is randomly selected from each group as a secondary pilot drone, and a communication routing table is generated and synchronized to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone.

2. The cooperative cluster control method of UAVs according to claim 1, characterized in that: The specific method of determining the pilot drone according to the pilot weight value of each drone is as follows: Create a voting box for each drone, control each drone in the cluster to vote for itself at the beginning, and make each drone pass its own vote to other drones and receive votes from other drones at the same time; Compare the received voting weights, and if the received voting weight is higher than its own weight, modify the vote to point to the drone with a higher weight; The voting status is continuously counted, and when more than half of the drones vote for the same drone, the drone is set as the pilot drone.

3. The cooperative cluster control method of UAVs according to claim 1, characterized in that: The clustering and grouping of other drones in the cluster according to the communication delay is specifically as follows: The communication delay time is fused with the drone navigation weight value to generate a weight array. Based on the weight array, a clustering grouping algorithm is executed to divide the drone cluster into k=(N-1) / t groups. The distance between drones is calculated using the Euclidean distance formula, and clustering is completed through an iterative optimization process, where t represents the expected number of drones in each group.

4. The cooperative cluster control method of UAVs according to claim 3, characterized in that: The execution process of the clustering grouping algorithm is as follows: S21 randomly selects k initial centroid vectors , where each centroid vector Represents the coordinates of the drone weight combination data in the multidimensional feature space; S22 will be each drone's weight array The Euclidean distance formula is used to calculate the distance between the centroid vectors The distance between , and its calculation formula is: in, represents the value of drone i on the lth feature, Represents the centroid vector The value of the lth feature, and Assign to make The smallest cluster ; S23 For each cluster , update the cluster center according to the following formula : in, Represents the jth cluster, which contains several data points , Representation clustering The total number of data points in , which means clustering All data points in are accumulated, Represents the new cluster center; Repeat steps S22 and S23 until all centroid vectors no longer change and output the clustering grouping results.

5. The cooperative cluster control method of UAVs according to claim 1, characterized in that: Also includes: The communication routing table is used to guide the drone cluster to perform intermittent heartbeat monitoring and detect the status of the pilot drone. When the pilot drone is detected to be out of control or offline, the whole cluster is immediately triggered to re-elect the pilot drone.

6. A cooperative cluster control device for unmanned aerial vehicles, characterized in that: include: A weight calculation unit, used to obtain initial information of N drones in the cluster at the start stage, and calculate the navigation weight value of each drone based on the initial information, wherein the initial information includes the payload, combat radius and endurance time; a communication delay calculation unit, configured to determine a pilot UAV according to the pilot weight value of each UAV, and calculate the communication delay between the pilot UAV and other UAVs in the cluster; A communication routing table generating unit is used to cluster and group other drones in the cluster according to the communication delay, randomly select a drone from each group as a secondary pilot drone, and generate a communication routing table to synchronize to each drone in the cluster, wherein the secondary pilot drone is used to communicate with the drones in the group and the pilot drone.

7. A cooperative cluster control device for unmanned aerial vehicles, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a collaborative cluster control method for unmanned aerial vehicles as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a collaborative cluster control method for drones as described in any one of claims 1 to 5.

Images