Cooperative performance analysis method, system, medium and electronic equipment of drone swarm

By collecting and analyzing the flight data of drone bee colonies, building a coordinated performance level analysis model, the problem of low accuracy in the collaborative performance evaluation of drone bee colonies in the existing technology is solved, and more accurate collaborative performance evaluation is achieved.

CN118584979BInactive Publication Date: 2024-11-15JOINT SERVICE COLLEGE OF THE NAT DEFENSE UNIV OF THE CHINESE PEOPLES LIBERATION ARMY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411037186.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing drone swarm synergistic performance evaluation relies on expert experience, has low accuracy, and is difficult to effectively reflect the flight details and synergistic performance of drone swarms.

Method used

By receiving mission instructions and track planning parameters, generating flight control information, collecting flight data, including mission qualitative and track quantitative indicators, building a flight parameter matrix, and using neural network and hierarchical analysis methods to build a coordinated performance level analysis model, and outputting no The synergistic performance level of human-machine bee colonies.

Benefits of technology

It improves the accuracy of drone swarm collaborative performance analysis and can truly reflect multi-dimensional flight parameters, thereby improving the accuracy and reliability of evaluation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118584979B_ABST
    Figure CN118584979B_ABST
Patent Text Reader

Abstract

The present application discloses a method, system, medium and electronic device for analyzing the collaborative performance of a drone swarm, the method comprising: receiving a task instruction, the task instruction carrying the task allocation parameters and track planning parameters of the drone swarm; generating flight control information according to the task allocation parameters and track planning parameters, and sending it to the drone swarm to control the drone swarm to fly; collecting flight data during the flight of the drone swarm, the flight data including qualitative task indicators and quantitative track indicators; analyzing the collaborative performance of the drone swarm based on the qualitative task indicators and quantitative track indicators, and obtaining the collaborative performance level of the drone swarm. Therefore, by adopting the embodiments of the present application, the accuracy of analyzing the collaborative performance of the drone swarm can be improved.
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 method, system, medium and electronic equipment for analyzing the collaborative performance of a drone swarm. Background Art

[0002] In the current military and civilian fields, drone technology has made significant progress, especially drone swarm technology. Drone swarm technology refers to the technology of multiple drones working together to achieve a common goal. It has the advantages of coordinated operations, flexible and diverse task execution, self-organization and scalability. This technology has been widely used in reconnaissance, strike, search and rescue and other fields, and is showing an increasingly broad application prospect.

[0003] In related technologies, drone swarms are formed into groups of drones with certain intelligence, centered on information networks and based on collaborative interaction capabilities between platforms, thereby achieving highly intelligent and autonomous collaboration between drones. Collaborative performance analysis is an important criterion for reflecting the quality of drone swarms. The current method of relying on expert experience to conduct overall performance evaluation has low accuracy. Summary of the invention

[0004] The embodiments of the present application provide a method, system, medium and electronic device for analyzing the collaborative performance of a drone swarm. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a method for analyzing the collaborative performance of a drone swarm, the method comprising:

[0006] Receive mission instructions, which carry the mission allocation parameters and trajectory planning parameters of the drone swarm;

[0007] Generate flight control information based on task allocation parameters and trajectory planning parameters, and send it to the drone swarm to control the drone swarm to fly;

[0008] Collect flight data during the flight of the drone swarm, including qualitative mission indicators and quantitative track indicators;

[0009] Based on the qualitative indicators of the mission and the quantitative indicators of the track, the collaborative performance of the UAV swarm is analyzed, and the collaborative performance level of the UAV swarm is obtained.

[0010] Optionally, the qualitative indicators of the task include task completion time, task execution efficiency, and energy consumption rate; the quantitative indicators of the track include track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency;

[0011] Based on the qualitative indicators of the mission and the quantitative indicators of the track, the collaborative performance of the UAV swarm is analyzed, and the collaborative performance level of the UAV swarm is obtained, including:

[0012] Normalizing the task completion time, task execution efficiency, and energy consumption rate to obtain a plurality of first normalized parameters;

[0013] Normalizing the track execution accuracy, the actual flight speed, the actual flight altitude, the obstacle avoidance information, and the communication frequency to obtain a plurality of second normalized parameters;

[0014] Constructing a flight parameter matrix of the drone swarm according to the plurality of first normalized parameters and the plurality of second normalized parameters;

[0015] Inputting the flight parameter matrix into the pre-trained coordinated performance level analysis model;

[0016] Output the coordination performance level corresponding to the drone swarm.

[0017] Optionally, a flight parameter matrix of the drone swarm is constructed according to the multiple first normalized parameters and the multiple second normalized parameters, including:

[0018] Establish a two-dimensional coordinate system according to the preset coordinate parameters;

[0019] On the abscissa of the two-dimensional coordinate system, establishing abscissa values ​​corresponding to the task completion time, the task execution efficiency, and the energy consumption rate according to a plurality of first normalized parameters and a first preset order;

[0020] On the ordinate of the two-dimensional coordinate system, establishing ordinate values ​​of track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency according to a plurality of second normalized parameters and a second preset order;

[0021] Combine each horizontal coordinate value with each vertical coordinate value in pairs to obtain the coordinate parameters of each two-dimensional coordinate point;

[0022] Based on each two-dimensional coordinate point and the coordinate parameters of each two-dimensional coordinate point, the flight parameter matrix of the drone swarm is constructed.

[0023] Optionally, a pre-trained coordination performance level analysis model is generated by following the steps below, including:

[0024] Collect historical flight data for each drone swarm;

[0025] According to the historical flight data of each group of drone swarms, a model training sample is constructed, and the model training sample includes a historical flight parameter matrix;

[0026] Create a neural network;

[0027] Construct the dimension constraint loss of the historical flight parameter matrix, and based on the dimension constraint loss, construct the loss function of the neural network to obtain the coordination performance level analysis model;

[0028] Input the model training samples into the coordination performance level analysis model, and output the loss value of the coordination performance level analysis model;

[0029] When the loss value reaches the minimum, a pre-trained coordination performance level analysis model is generated.

[0030] Optionally, build model training samples based on the historical flight data of each group of drone swarms, including:

[0031] Based on historical flight data, a historical flight parameter matrix of each drone swarm is constructed;

[0032] The analytic hierarchy process was used to determine the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms;

[0033] From the mapping relationship between the pre-generated comprehensive performance score and the collaborative performance level, the collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of UAV swarms is obtained;

[0034] The collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of UAV swarms is used as the label of the historical flight parameter matrix of each group of UAV swarms to obtain the model training samples.

[0035] Optionally, the loss function of the neural network is expressed as:

[0036]

[0037] Among them, L is the model loss value, is the cross entropy loss function that coordinates the performance grading, is a natural constant, are the fully connected layer parameters, is the transpose operation, represents the dimensionality constraint loss of the historical flight parameter matrix when the coordinated performance level division is wrong, is the number of elements in the historical flight parameter matrix, is the first element in the historical flight parameter matrix, represents the features extracted by the model from the input historical flight parameter matrix and its associated coordinated performance level; h is an indicator function. When the coordination performance level is wrong, =1, otherwise h =0; is the weight of the constraint; is the coordination performance level associated with the historical flight parameter matrix of the i-th group of UAV swarms; is the dimensionality constraint loss on the historical flight parameter matrix when the coordinated performance level division is correct, and is a preset non-zero constant.

[0038] Optionally, the task allocation parameters include task type, task priority and task start time; the track planning parameters include geographic image data, obstacle information and weather information of the target area;

[0039] Generate flight control information based on task allocation parameters and trajectory planning parameters, including:

[0040] Generate the task subject information that each drone in the drone swarm needs to perform according to the task type, task priority and task start time;

[0041] Obtain the flight path of each drone based on geographic image data, obstacle information, and meteorological information;

[0042] Generate the flight altitude, flight speed, turning radius, and take-off and landing points of each drone based on the mission subject information and flight path;

[0043] The flight altitude, flight speed, turning radius, and take-off and landing points of each UAV are used as flight control information.

[0044] In a second aspect, an embodiment of the present application provides a system for analyzing the collaborative performance of a drone swarm, the system comprising:

[0045] The command receiving module is used to receive the task command, which carries the task allocation parameters and trajectory planning parameters of the UAV swarm;

[0046] A flight control information generation module is used to generate flight control information according to task allocation parameters and trajectory planning parameters, and send the information to the drone swarm to control the drone swarm to fly;

[0047] The flight data collection module is used to collect flight data during the flight of the drone swarm. The flight data includes qualitative indicators of the mission and quantitative indicators of the track.

[0048] The coordination performance analysis module is used to analyze the coordination performance of the UAV swarm based on the qualitative indicators of the mission and the quantitative indicators of the track, and obtain the coordination performance level of the UAV swarm.

[0049] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0050] In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0051] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0052] In an embodiment of the present application, flight data of a drone swarm is collected during its flight, and the flight data includes qualitative mission indicators and quantitative track indicators. Since the indicators are calculated based on flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm.

[0053] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] Figure 1 It is a flow chart of a method for analyzing the collaborative performance of a drone swarm provided in an embodiment of the present application;

[0056] Figure 2 This is a schematic diagram of an application scenario of a client, a server, and a drone swarm provided in an embodiment of the present application;

[0057] Figure 3 This is a schematic diagram of a scene of a drone swarm in a target test area provided by an embodiment of the present application;

[0058] Figure 4 It is a flowchart of a coordination performance level analysis model training method provided in an embodiment of the present application;

[0059] Figure 5 It is a structural schematic diagram of a cooperative performance analysis system of a drone swarm provided in an embodiment of the present application;

[0060] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following description and the accompanying drawings sufficiently illustrate specific embodiments of the present application to enable those skilled in the art to practice them.

[0062] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0063] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of systems and methods consistent with some aspects of the present application as detailed in the attached claims.

[0064] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0065] The present application provides a method, system, medium and electronic device for analyzing the collaborative performance of a drone swarm to solve the problems existing in the above-mentioned related technical problems. In the technical solution provided by the present application, by collecting flight data during the flight of the drone swarm, the flight data includes qualitative task indicators and quantitative track indicators. Since the indicator is calculated based on the flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm. The following is a detailed description using an exemplary embodiment.

[0066] The following will be combined with the attached Figure 1 -Attached Figure 4 , the cooperative performance analysis method of the drone swarm provided by the embodiment of the present application is introduced in detail. The method can be implemented by relying on a computer program and can be run on a cooperative performance analysis system of the drone swarm based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0067] See also Figure 1, which is a flow chart of a method for analyzing the collaborative performance of a drone swarm according to an embodiment of the present application. Figure 1 As shown, the method of the embodiment of the present application may include the following steps:

[0068] S101, receiving a mission instruction, which carries the mission allocation parameters and trajectory planning parameters of the drone swarm;

[0069] Among them, the mission instructions come from the client used to command the drone swarm.

[0070] In an embodiment of the present application, the client first generates task allocation parameters and trajectory planning parameters for the user to control the drone swarm based on the user's operation information, then encapsulates the task allocation parameters and trajectory planning parameters to obtain task instructions, and finally sends the task instructions to the server; the server first receives the task instruction, and extracts the task allocation parameters and trajectory planning parameters carried by the task instruction.

[0071] S102, generating flight control information according to the task allocation parameters and the trajectory planning parameters, and sending the information to the drone swarm to control the drone swarm to fly;

[0072] Among them, the task allocation parameters include task type, task priority and task start time; the track planning parameters include geographic image data, obstacle information and meteorological information of the target area.

[0073] In an embodiment of the present application, when generating flight control information based on task allocation parameters and track planning parameters, first, based on the task type, task priority and task start time, the task subject information that each drone in the drone swarm needs to perform is generated; then, based on the geographic image data, obstacle information and meteorological information, the track flight path of each drone is obtained; secondly, based on the task subject information and the track flight path, the flight altitude, flight speed, turning radius and take-off and landing point of each drone are generated; finally, the flight altitude, flight speed, turning radius and take-off and landing point of each drone are used as flight control information.

[0074] Specifically, according to the task type, task priority and task start time, the specific processing process of generating the task subject information required to be performed by each drone in the drone swarm includes: combining the task type, task priority and task start time with the preset subject template to obtain the task subject information required to be performed by each drone in the drone swarm. The preset subject template is used to standardize the task type, task priority and task start time.

[0075] Specifically, the flight path of each UAV can be initially planned based on the obstacle avoidance algorithm and obstacle information, and then the planned initial path can be partially modified and fine-tuned according to the geographic image data and meteorological information to obtain the flight path of each UAV.

[0076] Specifically, the application scenario diagram of the client, server and drone swarm is as follows: Figure 2 The user can operate the client, and the client generates control information based on the user's operation and feeds it back to the server. The server can generate flight control information and send it to the drone swarm to control the drone swarm to fly.

[0077] S103, collecting flight data during the flight of the drone swarm, the flight data including qualitative indicators of the mission and quantitative indicators of the track;

[0078] Among them, the qualitative indicators of the task include task completion time, task execution efficiency, and energy consumption rate; the quantitative indicators of the track include track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency. Figure 3 shown.

[0079] In an embodiment of the present application, the server can obtain sensor parameters fed back during the flight of each drone in real time during the control of the drone swarm flight, and can calculate qualitative indicators of the mission and quantitative indicators of the track based on the obtained sensor parameters to obtain flight data during the flight of the drone swarm.

[0080] S104, analyzing the coordination performance of the UAV swarm based on the qualitative indicators of the mission and the quantitative indicators of the track, and obtaining the coordination performance level of the UAV swarm.

[0081] In an embodiment of the present application, when analyzing the collaborative performance of a drone swarm based on qualitative task indicators and quantitative track indicators, the task completion time, task execution efficiency, and energy consumption rate are first normalized to obtain a plurality of first normalized parameters, and then the track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency are normalized to obtain a plurality of second normalized parameters. Secondly, based on the plurality of first normalized parameters and the plurality of second normalized parameters, a flight parameter matrix of the drone swarm is constructed. Finally, the flight parameter matrix is ​​input into a pre-trained coordination performance level analysis model to output the collaborative performance level corresponding to the drone swarm.

[0082] In an embodiment of the present application, in the process of constructing a flight parameter matrix of a drone swarm using multiple first normalized parameters and multiple second normalized parameters, the following steps are specifically included: establishing a two-dimensional coordinate system according to preset coordinate parameters; on the horizontal coordinate of the two-dimensional coordinate system, establishing horizontal coordinate values ​​corresponding to task completion time, task execution efficiency, and energy consumption rate according to multiple first normalized parameters and a first preset order; on the vertical coordinate of the two-dimensional coordinate system, establishing vertical coordinate values ​​of track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency according to multiple second normalized parameters and a second preset order; combining each horizontal coordinate value with each vertical coordinate value in pairs to obtain the coordinate parameters of each two-dimensional coordinate point; and constructing a flight parameter matrix of the drone swarm based on the coordinate parameters of each two-dimensional coordinate point and each two-dimensional coordinate point.

[0083] In an embodiment of the present application, a pre-trained coordination performance level analysis model can be generated according to the following steps: collect historical flight data of each group of drone swarms; construct model training samples based on the historical flight data of each group of drone swarms, and the model training samples include a historical flight parameter matrix; create a neural network; construct a dimensionality constraint loss of the historical flight parameter matrix, and based on the dimensionality constraint loss, construct a loss function of the neural network to obtain a coordination performance level analysis model; input the model training samples into the coordination performance level analysis model, and output the loss value of the coordination performance level analysis model; when the loss value reaches the minimum, generate a pre-trained coordination performance level analysis model.

[0084] In an embodiment of the present application, the specific process of constructing a model training sample based on the historical flight data of each group of drone swarms includes: constructing a historical flight parameter matrix for each group of drone swarms based on the historical flight data; using a hierarchical analysis method to determine the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms; obtaining the collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms from the mapping relationship between the pre-generated comprehensive performance score and the collaborative performance level; and marking the collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms as a label of the historical flight parameter matrix of each group of drone swarms to obtain a model training sample.

[0085] Specifically, the loss function expression of the neural network is:

[0086] Among them, L is the model loss value, is the cross entropy loss function that coordinates the performance grading, is a natural constant, are the fully connected layer parameters, is the transpose operation, represents the dimensionality constraint loss of the historical flight parameter matrix when the coordinated performance level division is wrong, is the number of elements in the historical flight parameter matrix, is the first element in the historical flight parameter matrix, represents the features extracted by the model from the input historical flight parameter matrix and its associated coordinated performance level; h is an indicator function. When the coordination performance level is wrong, =1, otherwise h =0; is the weight of the constraint; is the coordination performance level associated with the historical flight parameter matrix of the i-th group of UAV swarms; is the dimensionality constraint loss on the historical flight parameter matrix when the coordinated performance level division is correct, and is a preset non-zero constant, is the specific weight of the constraint, To prevent the denominator from being 0, set =10 -7 .

[0087] In an embodiment of the present application, the present application automatically outputs a coordination performance level through a pre-trained coordination performance level analysis model. The dimensional constraint loss of the historical flight parameter matrix included in the pre-trained coordination performance level analysis model can automatically adjust the differences between categories in actual scenarios, avoiding classification suspicion caused by artificially setting thresholds, thereby improving the output confidence of the collaborative performance level.

[0088] In an embodiment of the present application, flight data of a drone swarm is collected during its flight, and the flight data includes qualitative mission indicators and quantitative track indicators. Since the indicators are calculated based on flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm.

[0089] See also Figure 4 , which is a flow chart of a method for training a coordination performance level analysis model according to an embodiment of the present application. Figure 4 As shown, the method of the embodiment of the present application may include the following steps:

[0090] S201, collecting historical flight data of each group of drone swarms;

[0091] S202, constructing a model training sample based on the historical flight data of each group of drone swarms, wherein the model training sample includes a historical flight parameter matrix;

[0092] S203, creating a neural network;

[0093] S204, constructing a dimensionality constraint loss of the historical flight parameter matrix, and based on the dimensionality constraint loss, constructing a loss function of a neural network to obtain a coordination performance level analysis model;

[0094] S205, inputting the model training sample into the coordination performance level analysis model, and outputting the loss value of the coordination performance level analysis model;

[0095] S206, when the loss value reaches the minimum, generate a pre-trained coordination performance level analysis model.

[0096] In an embodiment of the present application, flight data of a drone swarm is collected during its flight, and the flight data includes qualitative mission indicators and quantitative track indicators. Since the indicators are calculated based on flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm.

[0097] The following is a system embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the system embodiment of the present application, please refer to the method embodiment of the present application.

[0098] See also Figure 5 , which shows a schematic diagram of the structure of a coordinated performance analysis system of a drone swarm provided by an exemplary embodiment of the present application. The coordinated performance analysis system of a drone swarm can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The system 1 includes an instruction receiving module 10, a flight control information generating module 20, a flight data collecting module 30, and a coordinated performance analysis module 40.

[0099] The instruction receiving module 10 is used to receive the task instruction, which carries the task allocation parameters and trajectory planning parameters of the drone swarm;

[0100] The flight control information generation module 20 is used to generate flight control information according to the task allocation parameters and the trajectory planning parameters, and send the flight control information to the drone swarm to control the drone swarm to fly;

[0101] The flight data collection module 30 is used to collect flight data during the flight of the drone swarm, and the flight data includes qualitative indicators of the mission and quantitative indicators of the track;

[0102] The coordination performance analysis module 40 is used to analyze the coordination performance of the UAV swarm based on the qualitative indicators of the mission and the quantitative indicators of the track, and obtain the coordination performance level of the UAV swarm.

[0103] It should be noted that the collaborative performance analysis system of the drone swarm provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when executing the collaborative performance analysis method of the drone swarm. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the collaborative performance analysis system of the drone swarm provided in the above embodiment and the collaborative performance analysis method embodiment of the drone swarm belong to the same concept. The implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0104] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0105] In an embodiment of the present application, flight data of a drone swarm is collected during its flight, and the flight data includes qualitative mission indicators and quantitative track indicators. Since the indicators are calculated based on flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm.

[0106] The present application also provides a computer-readable medium having program instructions stored thereon, which, when executed by a processor, implement the collaborative performance analysis method of a drone swarm provided by the above-mentioned various method embodiments.

[0107] The present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the collaborative performance analysis method of a drone swarm in each of the above-mentioned method embodiments.

[0108] See also Figure 6 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0109] The communication bus 1002 is used to realize the connection and communication between these components.

[0110] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0111] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0112] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0113] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may also be optionally at least one storage system located away from the aforementioned processor 1001. As Figure 6 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a collaborative performance analysis application for a drone swarm.

[0114] exist Figure 6In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the cooperative performance analysis application of the drone swarm stored in the memory 1005, and specifically perform the following operations:

[0115] Receive mission instructions, which carry the mission allocation parameters and trajectory planning parameters of the drone swarm;

[0116] Generate flight control information based on task allocation parameters and trajectory planning parameters, and send it to the drone swarm to control the drone swarm to fly;

[0117] Collect flight data during the flight of the drone swarm, including qualitative mission indicators and quantitative track indicators;

[0118] Based on the qualitative indicators of the mission and the quantitative indicators of the track, the collaborative performance of the UAV swarm is analyzed, and the collaborative performance level of the UAV swarm is obtained.

[0119] In one embodiment, when the processor 1001 analyzes the cooperative performance of the drone swarm based on the qualitative indicators of the mission and the quantitative indicators of the track to obtain the cooperative performance level of the drone swarm, the processor 1001 specifically performs the following operations:

[0120] Normalizing the task completion time, task execution efficiency, and energy consumption rate to obtain a plurality of first normalized parameters;

[0121] Normalizing the track execution accuracy, the actual flight speed, the actual flight altitude, the obstacle avoidance information, and the communication frequency to obtain a plurality of second normalized parameters;

[0122] Constructing a flight parameter matrix of the drone swarm according to the plurality of first normalized parameters and the plurality of second normalized parameters;

[0123] Inputting the flight parameter matrix into the pre-trained coordinated performance level analysis model;

[0124] Output the coordination performance level corresponding to the drone swarm.

[0125] In one embodiment, when the processor 1001 constructs a flight parameter matrix of a drone swarm according to a plurality of first normalized parameters and a plurality of second normalized parameters, the processor 1001 specifically performs the following operations:

[0126] Establish a two-dimensional coordinate system according to the preset coordinate parameters;

[0127] On the abscissa of the two-dimensional coordinate system, establishing abscissa values ​​corresponding to the task completion time, the task execution efficiency, and the energy consumption rate according to a plurality of first normalized parameters and a first preset order;

[0128] On the ordinate of the two-dimensional coordinate system, establishing ordinate values ​​of track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency according to a plurality of second normalized parameters and a second preset order;

[0129] Combine each horizontal coordinate value with each vertical coordinate value in pairs to obtain the coordinate parameters of each two-dimensional coordinate point;

[0130] Based on each two-dimensional coordinate point and the coordinate parameters of each two-dimensional coordinate point, the flight parameter matrix of the drone swarm is constructed.

[0131] In one embodiment, when the processor 1001 generates a pre-trained coordination performance level analysis model, the processor 1001 specifically performs the following operations:

[0132] Collect historical flight data for each drone swarm;

[0133] According to the historical flight data of each group of drone swarms, a model training sample is constructed, and the model training sample includes a historical flight parameter matrix;

[0134] Create a neural network;

[0135] Construct the dimension constraint loss of the historical flight parameter matrix, and based on the dimension constraint loss, construct the loss function of the neural network to obtain the coordination performance level analysis model;

[0136] Input the model training samples into the coordination performance level analysis model, and output the loss value of the coordination performance level analysis model;

[0137] When the loss value reaches the minimum, a pre-trained coordination performance level analysis model is generated.

[0138] In one embodiment, when the processor 1001 constructs a model training sample based on the historical flight data of each group of drone swarms, the processor 1001 specifically performs the following operations:

[0139] Based on historical flight data, a historical flight parameter matrix of each drone swarm is constructed;

[0140] The analytic hierarchy process was used to determine the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms;

[0141] From the mapping relationship between the pre-generated comprehensive performance score and the collaborative performance level, the collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of UAV swarms is obtained;

[0142] The collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of UAV swarms is used as the label of the historical flight parameter matrix of each group of UAV swarms to obtain the model training samples.

[0143] In one embodiment, when the processor 1001 generates flight control information according to the task allocation parameters and the trajectory planning parameters, the processor 1001 specifically performs the following operations:

[0144] Generate the task subject information that each drone in the drone swarm needs to perform according to the task type, task priority and task start time;

[0145] Obtain the flight path of each drone based on geographic image data, obstacle information, and meteorological information;

[0146] Generate the flight altitude, flight speed, turning radius, and take-off and landing points of each drone based on the mission subject information and flight path;

[0147] The flight altitude, flight speed, turning radius, and take-off and landing points of each UAV are used as flight control information.

[0148] In an embodiment of the present application, flight data of a drone swarm is collected during its flight, and the flight data includes qualitative mission indicators and quantitative track indicators. Since the indicators are calculated based on flight parameters of multiple dimensions collected during the flight of the drone swarm, the flight parameters of multiple dimensions can truly reflect the flight details of the drone swarm, thereby improving the accuracy of analyzing the collaborative performance of the drone swarm.

[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program for analyzing the cooperative performance of drone swarms can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program for analyzing the cooperative performance of drone swarms can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0150] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for analyzing the collaborative performance of a drone swarm, characterized in that: The method comprises: Receive mission instructions, which carry the mission allocation parameters and trajectory planning parameters of the drone swarm; Generate flight control information according to the task allocation parameters and the trajectory planning parameters, and send the information to the drone swarm to control the drone swarm to fly; Collecting flight data during the flight of the drone swarm, wherein the flight data includes qualitative mission indicators and quantitative track indicators; Based on the qualitative indicators of the mission and the quantitative indicators of the track, the collaborative performance of the UAV swarm is analyzed to obtain the collaborative performance level of the UAV swarm; wherein, The qualitative indicators of the mission include mission completion time, mission execution efficiency, and energy consumption rate; the quantitative indicators of the track include track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency; The step of analyzing the collaborative performance of the drone swarm based on the qualitative task indicators and the quantitative track indicators to obtain the collaborative performance level of the drone swarm includes: Normalizing the task completion time, task execution efficiency, and energy consumption rate to obtain a plurality of first normalized parameters; Normalizing the track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency to obtain a plurality of second normalized parameters; Constructing a flight parameter matrix of the drone swarm according to the plurality of first normalized parameters and the plurality of second normalized parameters; Inputting the flight parameter matrix into a pre-trained coordinated performance level analysis model; Output the coordination performance level corresponding to the drone swarm; wherein, The following steps are used to generate a pre-trained coordination performance rating analysis model, including: Collect historical flight data for each drone swarm; Constructing a model training sample based on the historical flight data of each group of drone swarms, wherein the model training sample includes a historical flight parameter matrix; Create a neural network; Constructing a dimensionality constraint loss of a historical flight parameter matrix, and based on the dimensionality constraint loss, constructing a loss function of the neural network to obtain a coordination performance level analysis model; Inputting the model training sample into the coordination performance level analysis model, and outputting the loss value of the coordination performance level analysis model; When the loss value reaches the minimum, a pre-trained coordination performance level analysis model is generated; wherein, The loss function expression of the neural network is: Among them, L is the model loss value, is the cross entropy loss function that coordinates the performance grading, is a natural constant, are the fully connected layer parameters, is the transpose operation, represents the dimensionality constraint loss of the historical flight parameter matrix when the coordinated performance level division is wrong, is the number of elements in the historical flight parameter matrix, is the first element in the historical flight parameter matrix, represents the features extracted by the model from the input historical flight parameter matrix and its associated coordinated performance level; h is an indicator function. When the coordination performance level is wrong, =1, otherwise h =0; is the weight of the constraint; is the coordination performance level associated with the historical flight parameter matrix of the i-th group of UAV swarms; is the dimensionality constraint loss on the historical flight parameter matrix when the coordinated performance level division is correct, and is a preset non-zero constant.

2. The method according to claim 1, characterized in that: Constructing a flight parameter matrix of the drone swarm according to the plurality of first normalized parameters and the plurality of second normalized parameters, comprising: Establish a two-dimensional coordinate system according to the preset coordinate parameters; On the abscissa of the two-dimensional coordinate system, establishing abscissa values ​​corresponding to the task completion time, task execution efficiency, and energy consumption rate according to the plurality of first normalized parameters and a first preset order; On the ordinate of the two-dimensional coordinate system, establishing ordinate values ​​of the track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency according to the plurality of second normalized parameters and the second preset order; Combine each horizontal coordinate value with each vertical coordinate value in pairs to obtain the coordinate parameters of each two-dimensional coordinate point; Based on each two-dimensional coordinate point and the coordinate parameters of each two-dimensional coordinate point, a flight parameter matrix of the drone swarm is constructed.

3. The method according to claim 1, characterized in that The step of constructing a model training sample based on the historical flight data of each group of drone swarms includes: Constructing a historical flight parameter matrix of each group of drone swarms according to the historical flight data; Using the analytic hierarchy process, determining the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms; Obtaining the collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms from the pre-generated mapping relationship between the comprehensive performance score and the collaborative performance level; The collaborative performance level corresponding to the comprehensive performance score of the historical flight parameter matrix of each group of drone swarms is used as a label of the historical flight parameter matrix of each group of drone swarms to obtain a model training sample.

4. The method according to claim 1, characterized in that: The task allocation parameters include task type, task priority and task start time; the track planning parameters include geographic image data, obstacle information and meteorological information of the target area; Generating flight control information according to the task allocation parameters and the trajectory planning parameters includes: Generate task subject information that each drone in the drone swarm needs to perform according to the task type, task priority and task start time; Obtaining the flight path of each drone according to the geographic image data, obstacle information and meteorological information; Based on the mission subject information and the track flight path, generate the flight altitude, flight speed, turning radius and take-off and landing point of each UAV; The flight altitude, flight speed, turning radius and take-off and landing point of each UAV are used as flight control information.

5. A collaborative performance analysis system for drone swarms, characterized in that: The system comprises: The command receiving module is used to receive the task command, which carries the task allocation parameters and trajectory planning parameters of the UAV swarm; A flight control information generation module, used to generate flight control information according to the task allocation parameters and the trajectory planning parameters, and send the flight control information to the drone swarm to control the drone swarm to fly; A flight data collection module, used to collect flight data during the flight of the drone swarm, wherein the flight data includes qualitative mission indicators and quantitative track indicators; A coordination performance analysis module is used to analyze the coordination performance of the UAV swarm based on the qualitative indicators of the mission and the quantitative indicators of the track to obtain the coordination performance level of the UAV swarm; wherein, The qualitative indicators of the mission include mission completion time, mission execution efficiency, and energy consumption rate; the quantitative indicators of the track include track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency; The coordination performance analysis module is specifically used for: Normalizing the task completion time, task execution efficiency, and energy consumption rate to obtain a plurality of first normalized parameters; Normalizing the track execution accuracy, actual flight speed, actual flight altitude, obstacle avoidance information, and communication frequency to obtain a plurality of second normalized parameters; Constructing a flight parameter matrix of the drone swarm according to the plurality of first normalized parameters and the plurality of second normalized parameters; Inputting the flight parameter matrix into a pre-trained coordinated performance level analysis model; Output the coordination performance level corresponding to the drone swarm; wherein, The following steps are used to generate a pre-trained coordination performance rating analysis model, including: Collect historical flight data for each drone swarm; Constructing a model training sample based on the historical flight data of each group of drone swarms, wherein the model training sample includes a historical flight parameter matrix; Create a neural network; Constructing a dimensionality constraint loss of a historical flight parameter matrix, and based on the dimensionality constraint loss, constructing a loss function of the neural network to obtain a coordination performance level analysis model; Inputting the model training sample into the coordination performance level analysis model, and outputting the loss value of the coordination performance level analysis model; When the loss value reaches the minimum, a pre-trained coordination performance level analysis model is generated; wherein, The loss function expression of the neural network is: Among them, L is the model loss value, is the cross entropy loss function that coordinates the performance grading, is a natural constant, are the fully connected layer parameters, is the transpose operation, represents the dimensionality constraint loss of the historical flight parameter matrix when the coordinated performance level division is wrong, is the number of elements in the historical flight parameter matrix, is the first element in the historical flight parameter matrix, represents the features extracted by the model from the input historical flight parameter matrix and its associated coordinated performance level; h is an indicator function. When the coordination performance level is wrong, =1, otherwise h =0; is the weight of the constraint; is the coordination performance level associated with the historical flight parameter matrix of the i-th group of UAV swarms; is the dimensionality constraint loss on the historical flight parameter matrix when the coordinated performance level division is correct, and is a preset non-zero constant.

6. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method according to any one of claims 1 to 4.