Unmanned aerial vehicle electromagnetic domain confrontation training method and device based on game theory

The UAV electromagnetic domain confrontation training method and device based on game theory addresses the susceptibility of drones to electromagnetic interference by simulating interactions in a virtual environment, enhancing pilot and operator skills through strategic simulations.

CN119067168AActive Publication Date: 2024-12-03NAT UNIV OF DEFENSE TECH
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411294824.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-03
Estimated Expiration
2044-09-14

AI Technical Summary

Technical Problem

The challenge of designing effective electromagnetic domain confrontation training for unmanned aerial vehicles (UAVs) in a virtual environment to mitigate the susceptibility of civilian drones to radio electromagnetic interference, leading to damage and economic loss.

Method used

A UAV electromagnetic domain confrontation training method and device based on game theory, utilizing a high-fidelity, low-latency large-scale virtual electromagnetic environment platform to simulate drone and anti-drone interactions, defining pure strategy spaces for both parties, and assigning utility functions to guide optimal strategies through a referee or computer.

Benefits of technology

Enhances the capabilities of UAV pilots and anti-UAV equipment operators by reducing training costs and improving confrontation skills through adversarial training simulations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067168A_ABST
    Figure CN119067168A_ABST
Patent Text Reader

Abstract

The invention discloses an unmanned aerial vehicle electromagnetic domain confrontation training method and device based on the game theory. The method comprises the steps that an unmanned aerial vehicle entity or digital model and an anti-unmanned aerial vehicle equipment entity or digital model are connected to a virtual electromagnetic environment platform, and the entity or digital model type and a training scene are selected; setting the unmanned aerial vehicle entity or the digital model as a first player and defining a pure strategy space of the first player; setting the anti-unmanned aerial vehicle equipment entity or the digital model as a second player and defining a pure strategy space of the second player; under the selected training scene, pure strategies are sequentially selected based on the sequence of unmanned aerial vehicle first and anti-unmanned aerial vehicle equipment later, and a referee or a computer selects a pure strategy space and assigns a utility function; the steps are sequentially and cyclically performed; and after training is stopped, the referee or the computer outputs an optimal strategy and provides adversarial training suggestions. According to the method, interactive linkage between the electromagnetic domain virtual body and the physical entity can be realized, and the personnel training and confrontation cost is greatly reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electromagnetic spectrum technology, and in particular to a method and device for electromagnetic domain confrontation training of unmanned aerial vehicles based on game theory. Background Art

[0002] In recent years, drones have been widely used in agriculture, aerial photography, firefighting, logistics and other fields, providing concrete impetus for economic development and improvement of people's quality of life.

[0003] At present, due to the different operating difficulties of various types of civilian drones and their susceptibility to interference from the radio electromagnetic environment, a large number of new pilots operate expensive drones, which are easily damaged or destroyed, causing great economic losses.

[0004] Therefore, how to design and develop a technical solution for electromagnetic domain confrontation training of UAVs in a virtual environment has become an urgent problem to be solved. Summary of the invention

[0005] To this end, the present invention provides a UAV electromagnetic domain confrontation training method and device based on game theory, which realizes the interactive linkage between the electromagnetic domain virtual body and the physical entity through a high-fidelity, low-latency large-scale virtual electromagnetic environment platform. The UAV pilot or anti-UAV equipment operator selects a pure strategy space, and the referee / computer assigns a utility function according to the equipment parameters and training scenarios. The offensive and defensive parties can guide the next action or game according to the utility function. After the end, the referee / computer gives the optimal strategy under the pure strategy or mixed strategy equilibrium conditions. Under this confrontation training method, the capabilities of the UAV pilot or anti-UAV equipment operator are enhanced, which greatly reduces the costs of personnel training, cultivation, and confrontation.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a UAV electromagnetic domain confrontation training method based on game theory, comprising:

[0007] Connecting a drone entity or a drone digital model, and an anti-drone equipment entity or a anti-drone equipment digital model to a virtual electromagnetic environment platform; selecting a physical or digital model type in the virtual electromagnetic environment platform, and selecting a training scenario;

[0008] The drone entity or the drone digital model is set as the first player; the pure strategy space of the first player is defined, and the navigation and communication mode states of the first player are determined;

[0009] The anti-UAV equipment entity or the anti-UAV equipment digital model is set as the second player; the pure strategy space of the second player is defined, and the strategy of the second player to interfere with navigation or communication is determined;

[0010] In the selected training scenario, the first player is controlled to select the pure strategy of the first player, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; the second player is controlled to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; the process is repeated in sequence until the goal of the first player or the second player is reached, or the training time is reached, and the training is stopped;

[0011] After stopping the training, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium conditions to provide adversarial training suggestions to the operator.

[0012] As a preferred solution for a UAV electromagnetic domain confrontation training method based on game theory, the process of selecting a training scene from the virtual electromagnetic environment platform also includes selecting a hydrological and meteorological environment corresponding to the training scene.

[0013] As a preferred solution of the electromagnetic domain confrontation training method for drones based on game theory, in the process of defining the pure strategy space of the first player, the pure strategy space of the first player is defined as:

[0014] S1=(s 11 ,s 12 ,…,s 1n )

[0015] Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

[0016] As a preferred solution of the electromagnetic domain confrontation training method for drones based on game theory, in the process of defining the pure strategy space of the person in the second game, the pure strategy space of the person in the second game is defined as:

[0017] S2=(s 21 ,s 22 ,…,s 2m )

[0018] Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21Indicates interference with satellite navigation / no interference with ground UHF band communications; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that the laser kinetic weapon illuminated / did not interfere with communications.

[0019] As a preferred solution of the electromagnetic domain confrontation training method for UAVs based on game theory, in the process where the referee or computer assigns the utility function according to the equipment parameters and the training scenario, the expression of the utility function is:

[0020] U=(u 11 ,u 12 ,-,u 1n ,u 21 ,u 22 ,-,u 2m )

[0021] In the formula, u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses an action in his pure strategy space; u 2j ,j={1,2,...m} represents the utility function of the second player's choice of action in his pure strategy space and under the condition that the first player's choice of action in his pure strategy space.

[0022] The present invention also provides a UAV electromagnetic domain confrontation training device based on game theory, based on the above UAV electromagnetic domain confrontation training method based on game theory, comprising:

[0023] A virtual electromagnetic environment platform access module is used to connect the drone entity or drone digital model, and the anti-drone equipment entity or anti-drone equipment digital model to the virtual electromagnetic environment platform; select the entity or digital model type in the virtual electromagnetic environment platform, and select the training scenario;

[0024] A first player pure strategy space definition module is used to set the drone entity or the drone digital model as the first player; define the pure strategy space of the first player, and determine the navigation and communication mode status of the first player;

[0025] A second player pure strategy space definition module is used to set the anti-UAV equipment entity or the anti-UAV equipment digital model as the second player; define the second player pure strategy space, and determine the second player's strategy for interfering with navigation or communication;

[0026] The adversarial training module is used to control the first player to select the pure strategy of the first player in the selected training scenario, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; control the second player to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; and repeat the steps in sequence until the goal of the first player or the second player is achieved, or the training time is reached, and the training is stopped;

[0027] The optimal strategy and training suggestion output module is used for the referee or computer to output the optimal strategy under the pure strategy or mixed strategy equilibrium conditions after stopping the training, and to provide adversarial training suggestions to the operator.

[0028] As a preferred solution for a UAV electromagnetic domain confrontation training device based on game theory, in the virtual electromagnetic environment platform access module, in the process of selecting a training scene from the virtual electromagnetic environment platform, it also includes selecting a hydrological and meteorological environment corresponding to the training scene.

[0029] As a preferred solution of a UAV electromagnetic domain confrontation training device based on game theory, in the first player's pure strategy space definition module, in the process of defining the first player's pure strategy space, the first player's pure strategy space is defined as:

[0030] S1=(s 11 ,s 12 ,…,s 1n )

[0031] Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

[0032] As a preferred solution of a UAV electromagnetic domain confrontation training device based on game theory, in the second game player pure strategy space definition module, in the process of defining the second game player pure strategy space, the second game player pure strategy space is defined as:

[0033] S2=(s 21 ,s 22 ,…,s 2m )

[0034] Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21 Indicates interference with satellite navigation / no interference with ground UHF band communications; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that the laser kinetic weapon illuminated / did not interfere with communications.

[0035] As a preferred solution of a UAV electromagnetic domain confrontation training device based on game theory, in the confrontation training module, when the referee or computer assigns a utility function according to the equipment parameters and the training scenario, the expression of the utility function is:

[0036] U=(u 11 ,u 12 ,…,u 1n ,u 21 ,u 22 ,…,u 2m )

[0037] In the formula, u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses an action in his pure strategy space; u 2j ,j={1,2,...m} represents the utility function of the second player's choice of action in his pure strategy space and under the condition that the first player's choice of action in his pure strategy space.

[0038] The present invention has the following advantages: connecting a drone entity or a drone digital model and an anti-drone equipment entity or an anti-drone equipment digital model to a virtual electromagnetic environment platform; selecting a physical or digital model type in the virtual electromagnetic environment platform and selecting a training scenario; setting the drone entity or the drone digital model as a first player; defining the pure strategy space of the first player, and determining the navigation and communication mode states of the first player; setting the anti-drone equipment entity or the anti-drone equipment digital model as a second player; defining the pure strategy space of the second player, and determining the strategy of the second player to interfere with navigation or communication; in the selected training scenario, Control the first player to select the pure strategy of the first player, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; control the second player to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; repeat the process in sequence until the goal of the first player or the second player is reached, or the training time is reached, and the training is stopped; after stopping the training, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium condition, and provides adversarial training suggestions to the operator. The present invention establishes a game strategy matrix of drones and anti-drone equipment represented by navigation and communication (including three communication links between machines, stations, and satellites) through a high-fidelity, low-latency large-scale virtual electromagnetic environment platform. The drone pilot or anti-drone equipment operator selects a pure strategy space, and the referee / computer selects each feasible strategy space according to equipment parameters and training scenarios, and assigns a utility function. The offensive and defensive parties can guide the next action according to the utility function, or after the game is over, the referee / computer gives the optimal strategy under the pure strategy or mixed strategy equilibrium condition, guiding the drone pilot or anti-drone equipment operator to improve his business capabilities. This method can be applied to the simulation training occasions of drone pilots and anti-drone equipment operators, and has strong engineering practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0040] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0041] Figure 1 This is a flow chart of a method for electromagnetic domain confrontation training of a drone based on game theory provided in Example 1 of the present invention;

[0042] Figure 2 A schematic diagram of a specific adversarial training process of a UAV electromagnetic domain adversarial training method based on game theory provided in Example 1 of the present invention;

[0043] Figure 3 A schematic diagram of a framework of a large-scale virtual electromagnetic environment platform with high fidelity and low latency in a game theory-based UAV electromagnetic domain confrontation training method provided in Example 1 of the present invention;

[0044] Figure 4 A schematic diagram of a training scenario selected in a UAV electromagnetic domain confrontation training method based on game theory provided in Example 1 of the present invention;

[0045] Figure 5 This is a schematic diagram of an extended representation of a two-step game in a UAV electromagnetic domain confrontation training method based on game theory provided in Example 1 of the present invention;

[0046] Figure 6 A schematic diagram of a possible game tree result in a UAV electromagnetic domain adversarial training method based on game theory provided in Example 1 of the present invention;

[0047] Figure 7 This is a schematic diagram of the architecture of a UAV electromagnetic domain confrontation training device based on game theory provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0048] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1

[0050] See also Figure 1and Figure 2 Embodiment 1 of the present invention provides a UAV electromagnetic domain confrontation training method based on game theory, comprising the following steps:

[0051] S1. Connecting a drone entity or a drone digital model, and an anti-drone equipment entity or a anti-drone equipment digital model to a virtual electromagnetic environment platform; selecting a physical or digital model type in the virtual electromagnetic environment platform, and selecting a training scenario;

[0052] S2. Setting the drone entity or the drone digital model as the first player; defining the pure strategy space of the first player, and determining the navigation and communication mode states of the first player;

[0053] S3. Setting the anti-UAV equipment entity or the anti-UAV equipment digital model as the second player; defining the pure strategy space of the second player, and determining the strategy of the second player to interfere with navigation or communication;

[0054] S4, in the selected training scenario, controlling the first player to select the pure strategy of the first player, the referee or the computer to select the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigning the utility function; controlling the second player to select the pure strategy of the second player, the referee or the computer to select the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigning the utility function; repeating in sequence until the goal of the first player or the second player is reached, or the training time is reached, and the training is stopped;

[0055] S5. After stopping the training, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium condition and provides adversarial training suggestions to the operator.

[0056] In this embodiment, in step S1, a drone entity or a drone digital model and an anti-drone equipment entity or an anti-drone equipment digital model are connected to a virtual electromagnetic environment platform; a physical or digital model type is selected in the virtual electromagnetic environment platform, and a training scenario is selected;

[0057] Among them, the framework of the virtual electromagnetic environment platform is as follows Figure 3As shown, based on the cloud server, services are provided for the scene design, entity design, situation output and performance evaluation involved by both the offensive and defensive sides (the client supporting the drone pilot and the client supporting the anti-drone equipment operator). The physical / digital model status and scene information of both sides are given through the network communication interface, and interactive decisions are made according to the interactive rules. The interactive decision process is based on the manual command control and predetermined plan issued by the client supporting the drone pilot, and the action instructions of the client supporting the anti-drone equipment operator to make game behavior judgments. At the same time, the simulation engine is used to obtain the corresponding entity model from the entity model library, perform time management and generate posture playback files / interaction process recording files, and perform performance evaluation based on the generated posture playback files / interaction process recording files. In the process of selecting training scenes from the virtual electromagnetic environment platform, it also includes selecting flight simulation related parameters corresponding to the training scenes, as well as hydrological and meteorological environmental information, such as Figure 4 The figure shows a feasible training scenario configuration. Users can choose appropriate parameter configuration according to their own needs to meet different training confrontation requirements.

[0058] In this embodiment, in step S2, the drone entity or the drone digital model is set as the first player; the pure strategy space of the first player is defined, and the navigation and communication mode states of the first player are determined;

[0059] Specifically, the drone entity or the drone digital model is set as the first player (ie, player 1). In the process of defining the pure strategy space of the first player, the pure strategy space of the first player is defined as:

[0060] S1=(s 11 ,s 12 ,…,s 1n )

[0061] Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

[0062] In this embodiment, in step S3, the anti-UAV equipment entity or the anti-UAV equipment digital model is set as the second player; the pure strategy space of the second player is defined, and the strategy of the second player to interfere with navigation or communication is determined;

[0063] Specifically, the anti-UAV equipment entity or the anti-UAV equipment digital model is set as the second player (ie, player 2). In the process of defining the pure strategy space of the second player, the pure strategy space of the second player is defined as:

[0064] S2=(s 21 ,s 22 ,…,s 2m )

[0065] Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21 Indicates interference with satellite navigation / no interference with ground UHF band communications; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that the laser kinetic weapon illuminated / did not interfere with communications.

[0066] In this embodiment, in step S4, under the selected training scenario, the first player is controlled to select the pure strategy of the first player, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; the second player is controlled to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; the process is repeated in sequence until the goal of the first player or the second player is reached, or the training time is reached, and the training is stopped;

[0067] Specifically, in the selected training scenario, based on the order of UAV first and then anti-UAV equipment, select your own pure strategy in turn, and the referee / computer selects each step of the feasible strategy space according to the equipment parameters and training scenario, and assigns the utility function. The expression of the utility function is:

[0068] U=(u 11 ,u 12 ,-,u 1n ,u 21 ,u 22 ,…,u 2m )

[0069] In the formula, u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses an action in his pure strategy space; u 2j,j={1,2,...m} represents the utility function of the second player's choice of action in his pure strategy space and under the condition that the first player's choice of action in his pure strategy space.

[0070] In this example, the first player chooses the pure strategy S 13 In the second game, the player chooses pure strategy S 23 , the two-step game extended expression is as follows Figure 5 shown.

[0071] In this embodiment, in step S5, after stopping the training, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium condition to provide adversarial training suggestions to the operator.

[0072] Specifically, the game stops when either player reaches the goal or reaches the training time (limited time), and the following is obtained: Figure 6 The extended game tree shown in Figure 1. The operation results of the drone pilot and the anti-drone equipment operator are as follows: Figure 6 Medium 13 ,s 23 ,…,s 24 ) path, but the referee / computer gives the optimal strategy under the pure strategy or mixed strategy equilibrium condition as (s 13 ,s 21 ,s 11 ,s 22 ,…,s 24 ) path, and then give the UAV pilot or anti-UAV equipment operator the confrontation training suggestion, and can continue to re-execute step S1 or exit.

[0073] In summary, the present invention connects a drone entity or a drone digital model and an anti-drone equipment entity or an anti-drone equipment digital model to a virtual electromagnetic environment platform; selects a physical or digital model type in the virtual electromagnetic environment platform, and selects a training scenario; sets the drone entity or the drone digital model as a first player; defines a pure strategy space for the first player, and determines the navigation and communication mode states of the first player; sets the anti-drone equipment entity or the anti-drone equipment digital model as a second player; defines a pure strategy space for the second player, and determines the strategy for the second player to interfere with navigation or communication; and controls the player in the selected training scenario. The first player is controlled to select the pure strategy of the first player, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; the second player is controlled to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; the process is repeated in sequence until the goal of the first player or the second player is achieved, or the training time is reached, and the training is stopped; after the training is stopped, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium condition, and provides adversarial training suggestions to the operator. The present invention establishes a game strategy matrix of drones and anti-drone equipment represented by navigation and communication (including three communication links between machines, stations, and satellites) through a high-fidelity, low-latency large-scale virtual electromagnetic environment platform. The drone pilot or anti-drone equipment operator selects a pure strategy space, and the referee / computer selects each feasible strategy space according to equipment parameters and training scenarios, and assigns a utility function. The offensive and defensive parties can guide the next action according to the utility function, or after the game is over, the referee / computer gives the optimal strategy under the pure strategy or mixed strategy equilibrium condition, guiding the drone pilot or anti-drone equipment operator to improve his business capabilities. This method can be applied to the simulation training occasions of drone pilots and anti-drone equipment operators, and has strong engineering practical value.

[0074] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0075] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0076] Example 2

[0077] See also Figure 7 Embodiment 2 of the present invention further provides a UAV electromagnetic domain confrontation training device based on game theory, comprising:

[0078] The virtual electromagnetic environment platform access module 001 is used to connect the drone entity or drone digital model, and the anti-drone equipment entity or anti-drone equipment digital model to the virtual electromagnetic environment platform; select the entity or digital model type in the virtual electromagnetic environment platform, and select the training scenario;

[0079] A first player pure strategy space definition module 002 is used to set the drone entity or the drone digital model as the first player; define the pure strategy space of the first player, and determine the navigation and communication mode status of the first player;

[0080] The second player pure strategy space definition module 003 is used to set the anti-UAV equipment entity or the anti-UAV equipment digital model as the second player; define the second player pure strategy space, and determine the second player's strategy for interfering with navigation or communication;

[0081] The adversarial training module 004 is used to control the first player to select the pure strategy of the first player in the selected training scenario, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns the utility function; control the second player to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; and repeat the steps in sequence until the goal of the first player or the second player is achieved, or the training time is reached, and the training is stopped;

[0082] The optimal strategy and training suggestion output module 005 is used for the referee or computer to output the optimal strategy under the pure strategy or mixed strategy equilibrium condition after stopping the training, and to provide adversarial training suggestions to the operator.

[0083] In this embodiment, in the virtual electromagnetic environment platform access module 001, in the process of selecting a training scene from the virtual electromagnetic environment platform, it also includes selecting a hydrological and meteorological environment corresponding to the training scene.

[0084] In this embodiment, in the first player's pure strategy space definition module 002, in the process of defining the first player's pure strategy space, the first player's pure strategy space is defined as:

[0085] S1=(s 11 ,s 12 ,…,s 1n )

[0086] Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

[0087] In this embodiment, in the second player's pure strategy space definition module 003, in the process of defining the second player's pure strategy space, the second player's pure strategy space is defined as:

[0088] S2=(s 21 ,s 22 ,-,s 2m )

[0089] Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21 Indicates interference with satellite navigation / no interference with ground UHF band communications; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that the laser kinetic weapon illuminated / did not interfere with communications.

[0090] In this embodiment, in the adversarial training module 004, when the referee or computer assigns a utility function according to the equipment parameters and the training scenario, the utility function is expressed as:

[0091] U=(u 11 ,u 12 ,-,u 1n ,u 21 ,u 22,-,u 2m )

[0092] In the formula, u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses an action in his pure strategy space; u 2j ,j={1,2,...m} represents the utility function of the second player's choice of action in his pure strategy space and under the condition that the first player's choice of action in his pure strategy space.

[0093] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown above in the present application, and will not be repeated here.

[0094] Example 3

[0095] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a UAV electromagnetic domain adversarial training method based on game theory is stored. The program code includes instructions for executing Embodiment 1 or any possible implementation method of a UAV electromagnetic domain adversarial training method based on game theory.

[0096] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0097] Example 4

[0098] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0099] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute a game theory-based UAV electromagnetic domain confrontation training method of Example 1 or any possible implementation thereof.

[0100] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable systems. The computer instructions can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0102] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by a program code executable by a computing system, so that they can be stored in a storage system and executed by the computing system, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0103] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A UAV electromagnetic domain confrontation training method based on game theory, characterized by: include: Connecting a physical drone or a digital drone model, and a physical counter-drone equipment or a digital counter-drone equipment model to a virtual electromagnetic environment platform; Selecting a physical or digital model type in the virtual electromagnetic environment platform and selecting a training scenario; The drone entity or the drone digital model is set as a first player; a pure strategy space of the first player is defined, and the navigation and communication mode states of the first player are determined; The anti-UAV equipment entity or the anti-UAV equipment digital model is set as a second player; a pure strategy space of the second player is defined, and a strategy for the second player to interfere with navigation or communication is determined; In the selected training scenario, the first player is controlled to select the pure strategy of the first player, and the referee or computer selects the pure strategy space of the second player according to the equipment parameters and the training scenario, and assigns a utility function; the second player is controlled to select the pure strategy of the second player, and the referee or computer selects the pure strategy space of the first player according to the equipment parameters and the training scenario, and assigns the utility function; this process is repeated in a loop until the goal of the first player or the second player is achieved, or the training time is reached, and the training is stopped; After stopping the training, the referee or computer outputs the optimal strategy under the pure strategy or mixed strategy equilibrium conditions to provide adversarial training suggestions to the operator.

2. The method for electromagnetic domain confrontation training of UAV based on game theory according to claim 1, characterized in that: The process of selecting a training scene from the virtual electromagnetic environment platform also includes selecting a hydrological and meteorological environment corresponding to the training scene.

3. The method for electromagnetic domain confrontation training of UAV based on game theory according to claim 2 is characterized in that: In the process of defining the pure strategy space of the first player, the pure strategy space of the first player is defined as: S1=(s 11 ,s 12 ,…,s 1n ) Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

4. The method for electromagnetic domain confrontation training of UAV based on game theory according to claim 3 is characterized in that: In the process of defining the pure strategy space of the second player, the pure strategy space of the second player is defined as: S2=(s 21 ,s 22 ,…,s 2m ) Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21 Indicates interference with satellite navigation / non-interference with UHF band communication; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that laser kinetic energy weapons illuminated / did not interfere with communications.

5. The method for electromagnetic domain confrontation training of UAV based on game theory according to claim 4 is characterized in that: When the referee or computer assigns the utility function according to the equipment parameters and the training scenario, the utility function is expressed as follows: U=(u 11 ,in 12 ,…,in 1n ,in 21 ,in 22 ,…,in 2m ) Where u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses his pure strategy space; u 2j ,j={1,2,...m} represents the utility function of the second player in the pure strategy space under the condition that the player in the first game chooses actions in the pure strategy space.

6. A UAV electromagnetic domain confrontation training device based on game theory, adopting a UAV electromagnetic domain confrontation training method based on game theory according to any one of claims 1 to 5, characterized in that: include: A virtual electromagnetic environment platform access module is used to connect the drone entity or drone digital model, and the anti-drone equipment entity or anti-drone equipment digital model to the virtual electromagnetic environment platform; select the entity or digital model type in the virtual electromagnetic environment platform, and select a training scenario; A first player pure strategy space definition module is configured to set a drone entity or a drone digital model as the first player; define the first player's pure strategy space and determine the first player's navigation and communication mode states; A second player pure strategy space definition module is configured to set an anti-UAV equipment entity or an anti-UAV equipment digital model as a second player; define the second player's pure strategy space and determine the second player's strategy for interfering with navigation or communication; The adversarial training module is configured to, under the selected training scenario, control the first player to select the first player's pure strategy, and the referee or computer to select the second player's pure strategy space based on equipment parameters and the training scenario, and assign a utility function; control the second player to select the second player's pure strategy, and the referee or computer to select the first player's pure strategy space based on equipment parameters and the training scenario, and assign the utility function; and repeat the process in a loop until the first player or the second player reaches their goal or the training time is reached, and then terminate the training; The optimal strategy and training suggestion output module is used for the referee or computer to output the optimal strategy under the pure strategy or mixed strategy equilibrium conditions after stopping training, and provide adversarial training suggestions to the operator.

7. The UAV electromagnetic domain confrontation training device based on game theory according to claim 6 is characterized in that: In the virtual electromagnetic environment platform access module, the process of selecting a training scene from the virtual electromagnetic environment platform also includes selecting a hydrological and meteorological environment corresponding to the training scene.

8. The UAV electromagnetic domain confrontation training device based on game theory according to claim 7 is characterized in that: In the first player's pure strategy space definition module, in the process of defining the first player's pure strategy space, the first player's pure strategy space is defined as: S1=(s 11 ,s 12 ,…,s 1n ) Where S1 is the pure strategy space of the first player, which represents the navigation and communication mode state selected by the drone, including but not limited to: S 11 Indicates integrated navigation / aircraft-ground UHF band communication; S 12 Indicates integrated navigation / aircraft-ground C-band communication; S 13 Indicates combined navigation / autonomous flight mode; S 14 Indicates pure inertial navigation / aircraft-satellite Ku-band communication.

9. The UAV electromagnetic domain confrontation training device based on game theory according to claim 8 is characterized in that: In the second-game player pure strategy space definition module, in the process of defining the second-game player pure strategy space, the second-game player pure strategy space is defined as: S2=(s 21 ,s 22 ,…,s 2m ) Where S2 is the pure strategy space of the second player, which represents the strategy of interference with navigation or communication selected by the anti-UAV equipment, including but not limited to: S 21 Indicates interference with satellite navigation / non-interference with UHF band communication; S 22 Indicates interference with satellite navigation / jammer C-band communications; S 23 Indicates spoofing satellite navigation / not interfering with communications; S 24 Indicates that laser kinetic energy weapons illuminated / did not interfere with communications.

10. The UAV electromagnetic domain confrontation training device based on game theory according to claim 9 is characterized in that: In the adversarial training module, when the referee or computer assigns a utility function based on the equipment parameters and the training scenario, the utility function is expressed as: U=(u 11 ,in 12 ,…,in 1n ,in 21 ,in 22 ,…,in 2m ) Where u 1i , i = {1, 2, ... n} represents the utility function of the first player in his pure strategy space under the condition that the second player chooses his pure strategy space; u 2j ,j={1,2,...m} represents the utility function of the second player in the pure strategy space under the condition that the player in the first game chooses actions in the pure strategy space.

Citation Information

Patent Citations

  • Adversarial game target damage strategy evaluation method

    CN112651107A

  • Unmanned aerial vehicle group collaborative autonomous decision-making method and device based on multi-body game

    CN114460959A

  • Model training method and system and electronic equipment

    CN116362327A

  • Intelligent confrontation method based on neural virtual self-gaming

    CN116866895A

  • Unmanned aerial vehicle air combat decision-making method and system combining reinforcement learning and game theory

    CN117930880A