Unmanned aerial vehicle group self-organizing task cooperation method and device, electronic equipment and storage medium

Abstract

The invention provides an unmanned aerial vehicle group self-organizing task collaboration method and device, electronic equipment and a storage medium, and the method comprises the steps: building a distributed service list based on capability services based on respective capability services shared by each unmanned aerial vehicle in real time; determining a group leader unmanned aerial vehicle based on a task request message of the ground station, and screening task group members according to capability service quality provided by the group leader unmanned aerial vehicle; processing the task request message based on a task allocation algorithm to obtain a plurality of sub-tasks, unmanned aerial vehicle groups corresponding to the sub-tasks and a task allocation table; according to the unmanned aerial vehicle group self-organizing task coordination method, unmanned aerial vehicle group self-organizing task coordination is completed by executing the corresponding sub-tasks through the unmanned aerial vehicle groups receiving the task allocation table, and compared with direct control of the unmanned aerial vehicle group through a ground station, task-oriented unmanned aerial vehicle group command control can be achieved, the unmanned aerial vehicle group task autonomy capability is improved, and the unmanned aerial vehicle group self-organizing task coordination efficiency is improved. The unmanned aerial vehicle group task efficiency is enhanced; and the burden of control personnel is reduced.

Description

Technical Field

[0001] The present application belongs to the technical field of unmanned aerial vehicle mission control, and in particular relates to a method, device, electronic device and storage medium for self-organizing mission collaboration of a group of unmanned aerial vehicles. Background Art

[0002] Drones have been widely used in battlefield reconnaissance, target monitoring and strikes and other combat missions. Compared with a single drone, a drone swarm consisting of multiple drones has stronger detection and strike capabilities. In recent years, domestic institutions have carried out research on the task coordination of drone swarms, but most of them use drone ground stations as control centers to coordinate the control of drone swarms. This collaborative method has brought a heavy burden to the drone ground station operators. In addition, the reliability of the entire system is also relatively low. Once the drone ground station communication is disturbed or fails to operate, the drone swarm will not be able to coordinate tasks and lose its combat capability. Summary of the invention

[0003] In view of this, the embodiments of the present application propose a method, device, electronic device and storage medium for self-organizing task collaboration of drone swarms, aiming to realize task-oriented command and control of drone swarms, improve the autonomous task capabilities of drone swarms, enhance the mission efficiency of drone swarms, and reduce the burden on control personnel.

[0004] To achieve the above-mentioned objectives, an embodiment of the present application provides a method for self-organizing task collaboration of a drone swarm, including: obtaining the respective capability services and drone platform information shared by each drone in real time, and constructing a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of participating in the task; determining a leader drone based on a task request message from a ground station, and screening task team members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; processing the task request message and the drone platform information based on a task allocation algorithm to obtain multiple subtasks and drone teams corresponding to each of the subtasks and a task scheduling table; using each of the drone teams that have received the task scheduling table to execute the corresponding subtasks to complete self-organizing task collaboration of the drone swarm.

[0005] Optionally, the constructing of a distributed service list based on the capability service includes: determining the capability service of the drone based on the service ID, capability name, capability indicator, service status and service time of the drone, wherein the service ID is determined based on the drone number, the capability name is determined based on the capability of the drone to perform a task, the capability indicator is determined based on the equipment parameters of the drone to perform the task, the service status is determined based on the service availability of the drone, and the service time is determined based on the duration of service provided by the drone; obtaining a capability service list of the drone based on each capability service of the drone; and constructing a distributed service list of each drone based on the capability service list of all the drones.

[0006] Optionally, the constructing of a distributed service list of each drone based on the capability service lists of all the drones includes: sharing the capability service lists of each drone according to a preset refresh cycle; and constructing a distributed service list of each drone based on the capability service list of each drone and the capability service lists of other drones.

[0007] Optionally, after constructing a distributed service list of each drone based on the capability service list of each drone and the capability service lists of other drones, the drone group self-organizing task collaboration method also includes: if the capability service list sent by any drone is not received within a first preset time, the drone is determined to be a lost drone, and the capability service list of the drone is removed from the distributed service list.

[0008] Optionally, the task request message based on the ground station determines the leader drone, and screens the task team members according to the capability service quality provided by the leader drone, including: obtaining task requirements based on the task request message; obtaining the minimum number of drones and the optimal number of drones required to complete the task based on the team leader drone processing the task requirements; judging whether the task collaboration fails based on the minimum number of drones and the optimal number of drones; if the task collaboration is successful, the team leader drone calculates the capability service quality of each drone according to the distributed service list, and determines temporary task team members based on the capability service quality of each drone.

[0009] Optionally, after determining the task group members based on the service quality of each capability of each drone, the drone group self-organizing task collaboration method also includes: using the group leader drone to send collaboration request messages to the temporary task group members at a second preset time interval; and determining the task group based on the reply messages of each temporary task group.

[0010] Optionally, the task allocation algorithm includes: Hungarian algorithm and / or genetic algorithm.

[0011] To achieve the above-mentioned purpose, an embodiment of the present application also provides a self-organizing task collaboration device for a drone swarm, including: a list determination module, used to obtain the respective capability services and drone platform information shared by each drone in real time, and to construct a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of the participating tasks; a member determination module, used to determine the leader drone based on the task request message of the ground station, and to screen the task team members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; a task allocation module, used to process the task request message and the drone platform information based on a task allocation algorithm, to obtain multiple subtasks and drone teams corresponding to each subtask, and a task allocation table; an execution module, used to use each drone team that has received the task allocation table to execute the corresponding subtask, and complete the self-organizing task collaboration of the drone swarm.

[0012] To achieve the above-mentioned objectives, an embodiment of the present application also provides a server, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the drone swarm self-organizing task collaboration method provided in any one of the above-mentioned embodiments.

[0013] To achieve the above objectives, an embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the drone swarm self-organizing task collaboration method provided in any of the above embodiments.

[0014] The embodiment of the present application proposes a method, device, electronic device and storage medium for self-organizing task coordination of a drone swarm, which obtains the respective capability services and drone platform information shared by each drone in real time, and constructs a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of participating in the task; determines the leader drone based on the task request message of the ground station, and screens the task group members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; processes the task request message and the drone platform information based on a task allocation algorithm to obtain multiple subtasks and drone groups corresponding to each of the subtasks and a task allocation table; uses each of the drone groups that receive the task allocation table to perform the corresponding subtasks to complete the self-organizing task coordination of the drone swarm. Compared with directly controlling the drone swarm through a ground station, the self-organizing task coordination method of the drone swarm is a universal task coordination method, which is independent of the unmanned machine configuration and size, is applicable to fixed-wing, rotary-wing and other isomorphic / heterogeneous drone swarms, and is applicable to large, medium, small and micro drone platforms, and can realize task-oriented drone swarm command and control, improve the autonomous capability of drone swarm tasks, enhance the mission efficiency of drone swarms, and reduce the burden on control personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a process of a drone group self-organizing task collaboration method provided in an embodiment of the present application Figure 1 ;

[0016] Figure 2 This is a process of a drone group self-organizing task collaboration method provided in an embodiment of the present application Figure 2 ;

[0017] Figure 3 It is a structural block diagram of a drone swarm self-organizing task coordination device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0019] An embodiment of the present application proposes a method for self-organizing task collaboration of a drone group, which is applied to an electronic device, wherein the electronic device can be a control terminal set in a drone, and this embodiment and the following embodiments are all described by taking the control terminal as an example. The following is a specific description of the implementation details of the method for self-organizing task collaboration of a drone group proposed in this embodiment, and the following content is only provided for the convenience of understanding and is not necessary for the implementation of this solution.

[0020] Before introducing the drone swarm self-organizing task coordination method, it can be assumed that the drone swarm is composed of M drones, and the drones can communicate with each other and with the ground station through data links. The types of tasks that the drone swarm can perform include regional reconnaissance, target monitoring, target interference, target attack, etc. The specific process of the drone swarm self-organizing task coordination method proposed in this embodiment can be as follows: Figure 1 and Figure 2 As shown, the method can be executed by a control terminal in any drone in the drone group.

[0021] The method may include:

[0022] S10, acquiring the respective capability services and UAV platform information shared by each UAV in real time, and constructing a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of participating tasks;

[0023] In an embodiment of the present application, step S10 may include the following execution steps:

[0024] S101, determining the capability service of the drone based on the service ID, capability name, capability index, service status and service time of the drone, wherein the service ID is determined based on the drone number, the capability name is determined based on the capability of the drone to perform tasks, the capability index is determined based on the equipment parameters of the drone to perform tasks, the service status is determined based on the service availability of the drone, and the service time is determined based on the duration of the drone providing services;

[0025] In the specific implementation process, the mission payload carried by a drone, such as optoelectronic ball, radar, electronic warfare, warhead, etc., determines the ability of the drone to participate in the mission. This capability is abstractly expressed according to certain rules, which is a capability service. A capability service s can be described as s{service ID, capability name, capability indicator, service status, service time}. The service ID is unique in the drone group and is derived from the number of the drone; the capability name is the specific capability that can be provided, such as TV reconnaissance, infrared reconnaissance, laser ranging, radar interference, target damage, etc.; the capability indicator corresponds to the capability name, such as the indicator of reconnaissance capability is spatial resolution, and the target damage capability is the killing radius, etc.; the service status is the current availability of this service, such as idle, busy, invalid, etc.; the service time is the length of time that this capability service can be provided.

[0026] S102, obtaining a capability service list of the drone based on each capability service of the drone;

[0027] In the specific real-time process, suppose the ath drone in the drone group can provide β a capability services, then a capability service of this drone can be expressed as s a,j (1≤j≤β a ). Each drone in the drone swarm uses its full capabilities to serve s a,j (1≤j≤β) Build a list of capability services.

[0028] S103: construct a distributed service list for each drone based on the capability service lists of all the drones.

[0029] In an embodiment of the present application, step S103 may include the following execution steps:

[0030] S1031, sharing the capability service list of each drone according to a preset refresh cycle;

[0031] In the specific implementation process, each drone in the drone swarm will use its full capabilities to serve s a,j (1≤j≤β) and drone platform information (position, attitude, endurance, etc.) are shared with other drones in real time at a certain refresh period (typical value is 50ms-1000ms).

[0032] S1032: construct a distributed service list for each drone based on the capability service list of each drone and the capability service lists of other drones.

[0033] In the specific implementation process, each drone in the drone group receives the capability service sharing of other drones, plus its own capability service, to form a distributed service list.

[0034]

[0035] In an embodiment of the present application, after step S103, the drone group self-organizing task coordination method further includes:

[0036] S1033: If the capability service list sent by any of the drones is not received within the first preset time, the drone is determined to be a lost drone, and the capability service list of the drone is removed from the distributed service list.

[0037] In the specific implementation process, if a drone does not share its capability service within the first preset time (typical value is 3s-10s), the drone is considered to be out of connection and its capability service is removed from the distributed service list.

[0038] S20, determining a leader drone based on the task request message of the ground station, and screening task team members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list;

[0039] In an embodiment of the present application, step S20 may include the following execution steps:

[0040] S201, obtaining task requirements based on the task request message;

[0041] S202, obtaining a minimum number of drones and an optimal number of drones required to complete the task based on the team leader drone processing the task requirement;

[0042] S203, judging whether task coordination fails based on the minimum number of drones and the optimal number of drones;

[0043] S204: If the task collaboration is successful, the team leader drone calculates the service quality of each capability of each drone according to the distributed service list, and determines temporary task team members based on the service quality of each capability of each drone.

[0044] In the specific implementation process, if UAV γ in the UAV group receives the task T from the ground station, then UAV γ automatically becomes the temporary team leader and is responsible for the formation of the task team.

[0045] In response to the capability service requirements of task T, drone γ preliminarily screens the task team members by evaluating the capability service quality provided by each drone. Drone γ calculates the minimum number of drones N required to complete task T based on the requirements of task T and business domain expertise. min , optimal number of drones N op , N op≥N min If M <N min , the collaboration fails and will not proceed; otherwise, continue.

[0046] Assume that the jth capability service s of the ath drone in the drone swarm a,j The quality is q a,j

[0047]

[0048] where θ k is the kth capability service quality evaluation index. General indicators can select relevant parameters such as service time and mission distance (flight distance from the current position to the executable mission). Special indicators correspond to the capability indicators in the capability service and should meet the requirements of the mission T. For example, for reconnaissance missions, relevant parameters such as spatial resolution can be selected. The larger the value, the higher the quality. k is the k-capability service quality evaluation index θ k The weight coefficient satisfies

[0049] According to formula 2, drone γ evaluates the service quality of each capability in the distributed service list in turn, sorts them from large to small, removes duplicate drones, selects δ drones, forms a temporary group, and determines the temporary group members based on the temporary group. Take δ = ceil (1.1N op ), ceil means rounding up.

[0050] In an embodiment of the present application, after step S204, the drone group self-organizing task coordination method further includes:

[0051] S205, using the team leader drone to send a collaboration request message to the temporary task team members at a second preset time interval;

[0052] S206. Determine the task group based on the reply messages of each temporary task group.

[0053] In the specific implementation process, the drone γ continuously sends the first N in the temporary group at a certain time interval (typical value 80ms-400ms). op The collaborative request format is {task group ID, task T}, where the task group ID is unique in the drone group. The drone that receives the collaborative request evaluates whether it can participate in the collaborative task based on its own task load. If it agrees to join, it replies {task group ID, agree}, otherwise it replies {task group ID, reject}. Within the second preset time (typical value 3s-10s), if drone γ receives all N opIf the number of drones responding “yes” is N, the task force is successfully formed, and the number of drones in the task force is N = N op .

[0054] If the number of drones that receive an "agree" response is N re <N op , then UAV γ continues to send cooperation requests to the remaining UAVs in the temporary group. Assume that within a certain period of time (typical value 3s-10s), UAV γ receives N sy The drones responded “yes”. If N re +N sy ≥N min , then the task group is successfully formed, and the number of drones in the task group N = N re +N sy ; Otherwise, the task force will fail to be formed, coordination will fail, and it will no longer proceed.

[0055] S30, processing the task request message and the drone platform information based on a task allocation algorithm to obtain a plurality of subtasks and drone groups corresponding to each of the subtasks and a task allocation table;

[0056] In the specific implementation process, UAV γ is the leader of the collaborative task group and is responsible for cluster task allocation and distribution.

[0057] According to the requirements of task T, such as the area to be reconnaissance, the list of targets to be monitored, the list of targets to be attacked or interfered, etc., combined with the characteristics of the task group, such as the location distribution of drones, task capabilities, etc., call the task allocation algorithm (such as the Hungarian algorithm, genetic algorithm, etc.) to decompose task T into several subtasks T i (1≤i≤N) to complete the task allocation. The subtask may be a task sub-area to be reconnaissance, a target to be monitored, a target to be attacked or interfered with, etc. The subtask has a one-to-one correspondence with the drones in the task group, forming a task allocation table in the form of: {(1,T1),(2,T2)...(i,T i )...(N,T N )}. Since the task allocation is completed on the UAV γ, it is a centralized decision-making with high efficiency and good real-time performance. Through the data link, the UAV γ distributes each subtask to the corresponding UAV according to the task allocation table and transmits it to the ground station at the same time.

[0058] S40, using each drone group that has received the task allocation table to execute the corresponding subtask to complete the self-organized task coordination of the drone group.

[0059] After receiving their respective subtasks, the UAVs in the task group carry out single-machine mission planning based on the subtask requirements and related constraints (such as UAV maneuverability, mission payload performance, etc.), including mission parameter decisions (such as reconnaissance altitude, strike entry angle, interference frequency band, etc.), route planning, etc.

[0060] During the specific implementation process, the UAVs will transmit their respective mission planning results to the ground station, and perform their respective subtasks according to the mission planning results, thereby realizing collaborative execution of tasks.

[0061] In a specific embodiment:

[0062] A drone swarm consists of 4 drones, which are numbered 1, 2, 3, and 4. Drone 1 carries a visible light / laser ranging sensor and has reconnaissance capabilities; drone 2 carries a visible light / infrared sensor and has reconnaissance capabilities; drone 3 carries a visible light sensor and warhead and has reconnaissance and strike capabilities; drone 4 carries an electronic warfare payload and has jamming capabilities. Drones 1-4 share their available capabilities and services in a 100ms cycle, as shown in the following table.

[0063] Table 1 List of drone swarm services

[0064]

[0065]

[0066] The UAV operator issues a combat mission, which requires monitoring armored targets 1 and 2 at an altitude of no less than 500 meters. The size of targets 1 and 2 is 4m×6m, the longitude and latitude of target 1 is (114.01°, 34.08°), and the longitude and latitude of target 2 is (114.05°, 34.08°). At this time, the longitude and latitude of UAV 1 is (114.02°, 34.07°), the longitude and latitude of UAV 2 is (114.04°, 34.07°), the longitude and latitude of UAV 3 is (114.02°, 34.06°), and the longitude and latitude of UAV 4 is (114.02°, 34.06°).

[0067] After receiving the combat mission, the drone automatically becomes the temporary team leader and is responsible for forming the task force. The minimum number of drones N is calculated. min =2, the optimal number of drones N op =2. Then the reconnaissance capability service is evaluated. In the capability service quality evaluation, the reciprocal of the task distance (normalized) is selected as the general indicator with a weight of 0.5; the reciprocal of the spatial resolution (normalized) is selected as the special indicator with a weight of 0.5. The capability service quality evaluation indicators are shown in Table 2, and the capability service quality evaluation results are shown in Table 3.

[0068] Table 2 Capability service quality evaluation indicators

[0069]

[0070] Table 3 Capability service quality evaluation results

[0071]

[0072] Therefore, drones 1, 2, and 3 are selected to form a temporary team. Drone 1 sends a collaboration request {task team ID = 1, task T = target monitoring} to drone 2 at an interval of 100ms. Drone 2 replies {task team ID = 1, agree} within 1s. The task team is successfully formed, with members being drones 1 and 2, and the number of drones being 2. According to the distribution relationship between drones and targets, drone 1 performs task allocation, forming a task allocation table as shown in Table 4, that is, drone 1 is assigned to target 1, and drone 2 is assigned to target 2.

[0073] Table 4 Task Allocation Table

[0074]

[0075] UAV 1 distributes the task allocation table to UAV 2 and transmits it to the ground station at the same time. After receiving the task allocation table, UAV 2 performs single-machine task planning and generates a surveillance route for target 2.

[0076] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0077] The present invention proposes a self-organizing task coordination method for drone swarms based on capability services, which belongs to the technical field of drone task control and is used to solve the problems of low automation degree of drone swarm task coordination and heavy burden on control personnel. In the task coordination method proposed by the present invention, each drone in the drone swarm shares the capability services that can be provided in real time through the network to form a distributed service list; for the tasks that need to be performed, service quality evaluation and task coordination are performed, and a task group is formed; the task group performs cluster task allocation, decomposes the task into subtasks, and distributes it to each task group member; the task group members perform single-machine task planning, form a task plan and execute it. Compared with directly controlling the drone swarm through the ground station, the present invention combines the advantages of distributed and centralized control, has the characteristics of good real-time performance and high reliability, and is easy to apply in engineering. The present invention is a universal task coordination method, which is independent of the unmanned machine configuration and size, and is suitable for fixed-wing, rotary-wing and other isomorphic / heterogeneous drone swarms, and is suitable for large, medium, small and micro drone platforms. It can realize task-oriented drone swarm command and control, improve the autonomous capability of drone swarm tasks, enhance the effectiveness of drone swarm tasks, and reduce the burden on control personnel.

[0078] From August to September 2023, two test flights were conducted using a drone swarm consisting of eight small fixed-wing drones to verify the method proposed in the invention. Under the command of an operator at the drone ground station, self-organizing task coordination for combat tasks such as regional reconnaissance, target monitoring, and coordinated attack was achieved. The test flight results show that this method has high computational efficiency and good real-time performance. The drone swarm can achieve coordination within 5 seconds of receiving the task command, with a coordination success rate of 100%.

[0079] Based on the above embodiments, the present application also provides a drone group self-organizing task coordination device, referring to Figure 3 The collaboration device 200 includes a list determination module 201, a member determination module 202, a task allocation module 203 and an execution module 204, wherein the list determination module 201 is used to obtain the respective capability services and drone platform information shared by each drone in real time, and to construct a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of the participating tasks; the member determination module 202 is used to determine the leader drone based on the task request message of the ground station, and to screen the task team members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; the task allocation module 203 is used to process the task request message and the drone platform information based on the task allocation algorithm, and obtain multiple subtasks and drone groups corresponding to each subtask and a task allocation table; the execution module 204 is used to use each drone group that has received the task allocation table to execute the corresponding subtask to complete the self-organized task collaboration of the drone group.

[0080] It is not difficult to find that this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in conjunction with the above method embodiment. The relevant technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the above embodiments.

[0081] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0082] Another embodiment of the present application proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the drone swarm self-organizing task collaboration method in the above-mentioned method embodiments.

[0083] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripheral devices, voltage regulators and power management circuits together, which are all well known in the art, so this article will not describe them further. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor.

[0084] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0085] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0086] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM (Read-Only Memory), RAM (Random Access Memory), disk or optical disk and other media that can store program codes.

[0087] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. A method for self-organizing task coordination of a drone swarm, characterized in that: include: Acquire the respective capability services and UAV platform information shared by each UAV in real time, and construct a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of participating tasks; Determine a leader drone based on a task request message from a ground station, and select task team members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; Process the task request message and the drone platform information based on a task allocation algorithm to obtain a plurality of subtasks and drone teams corresponding to each of the subtasks and a task allocation table; Each drone group in the received task allocation table executes the corresponding subtask to complete the self-organized task coordination of the drone group.

2. The method for self-organizing task coordination of a drone group according to claim 1, characterized in that: The constructing a distributed service list based on the capability service includes: Based on each of the capability services of the drone, a capability service list of the drone is obtained, wherein the capability service of the drone is determined by the service ID, capability name, capability index, service status and service time of the drone, wherein the service ID is determined based on the drone number, the capability name is determined based on the capability of the drone to perform a task, the capability index is determined based on the device parameters of the drone to perform the task, the service status is determined based on the service availability of the drone, and the service time is determined based on the duration of the service provided by the drone; The distributed service list of each drone is constructed based on the capability service lists of all the drones.

3. The method for self-organizing task coordination of a drone group according to claim 2, characterized in that: The step of constructing a distributed service list of each drone based on the capability service list of all the drones includes: Sharing the capability service list of each drone according to a preset refresh cycle; The distributed service list of each drone is constructed based on the capability service list of each drone and the capability service lists of other drones.

4. The method for self-organizing task coordination of a drone group according to claim 1, characterized in that: After constructing a distributed service list of each drone based on the capability service list of each drone and the capability service lists of other drones, the drone group self-organizing task collaboration method further includes: If the capability service list sent by any of the drones is not received within the first preset time, the drone is determined to be a lost drone, and the capability service list of the lost drone is removed from the distributed service list.

5. The method for self-organizing task coordination of a drone group according to claim 4, characterized in that: The determining of the leader UAV based on the task request message of the ground station, and screening of the task team members according to the capability service quality provided by the leader UAV, include: Obtaining task requirements based on the task request message; The minimum number of drones and the optimal number of drones required to complete the task are obtained based on the team leader drone processing the task requirements; Determining whether task coordination fails based on the minimum number of drones and the optimal number of drones; If the task collaboration is successful, the team leader drone calculates the service quality of each capability of each drone according to the distributed service list, and determines temporary task team members based on the service quality of each capability of each drone.

6. The method for self-organizing task coordination of a drone group according to claim 5, characterized in that: After determining the temporary task group members based on the service quality of each capability, the drone swarm self-organizing task collaboration method further includes: Using the team leader drone to send a collaboration request message to the temporary task team members at a second preset time interval; The task group members are determined based on the reply messages of the temporary task group members.

7. The method for self-organizing task coordination of a drone group according to claim 1, characterized in that: The task allocation algorithm includes: Hungarian algorithm and / or genetic algorithm.

8. A drone swarm self-organizing task coordination device, characterized in that: include: A list determination module, used to obtain the respective capability services and UAV platform information shared by each UAV in real time, and to construct a distributed service list based on the capability services, wherein the capability services are constructed based on the capabilities of participating tasks; A member determination module, used to determine a leader drone based on a task request message from a ground station, and screen task group members according to the capability service quality provided by the leader drone, wherein the capability service quality is determined based on the distributed service list; A task allocation module, used for processing the task request message and the UAV platform information based on a task allocation algorithm to obtain a plurality of subtasks and UAV groups corresponding to each of the subtasks and a task allocation table; The execution module is used to utilize each drone group that has received the task allocation table to execute the corresponding subtask and complete the self-organized task coordination of the drone group.

9. An electronic device, characterized in that: include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the drone swarm self-organizing task collaboration method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it is capable of implementing the drone swarm self-organizing task collaboration method as described in any one of claims 1 to 7.

Images