Attack and defense strategy game method and system for multi-uav target assignment

Abstract

The application provides a kind of multi-unmanned aerial vehicle target allocation attack-defense strategy game method and system. Multi-unmanned aerial vehicle formation information of first unmanned aerial vehicle formation and second unmanned aerial vehicle formation is acquired to generate strategy pair of multiple unmanned aerial vehicles according to unmanned aerial vehicle information, and strategy group set of multi-unmanned aerial vehicle formation is generated according to strategy pair, strategy pair can include current unmanned aerial vehicle, attack-defense strategy and strategy target;Attack-defense strategy includes attack strategy, avoidance strategy and interference strategy. By calculating the probability distribution of each unmanned aerial vehicle under different attack-defense strategies, a payoff matrix is constructed, and a zero-sum game matrix model is further generated. Based on the zero-sum game matrix model, the attack-defense strategy game solution of multi-unmanned aerial vehicle target allocation is solved. The application fully considers the three attack-defense strategies of unmanned aerial vehicles, and solves the attack-defense strategy game solution, thereby improving the solution quality of unmanned aerial vehicle target allocation problem.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and specifically to a game theory method and system for attacking and defending strategies in multi-UAV target allocation. Background Technology

[0002] With the increasing intelligence and enhanced performance of drones, multiple drones can execute various combat strategies throughout air combat, significantly impacting target allocation and consequently combat effectiveness. During combat, both sides need to develop reasonable offensive and defensive strategies based on the real-time situation, selecting targets and evading or interfering with enemy attacks. Appropriate attack decisions can rationally allocate limited weapon resources for better firepower strikes; interfering with targets reduces their weapon effectiveness, thereby minimizing damage to friendly drones; and effective evasion based on threat assessment can prevent damage to friendly drones. Similarly, the adversary will also attack, evade, or interfere. How to set up target allocation for coordinated drone formations remains a major challenge.

[0003] Existing methods for multi-UAV target allocation mostly construct the problem as an optimization model. However, these models do not consider the influence of adversary behavior and only optimize for the user, resulting in unsatisfactory performance in practical applications. Furthermore, in multi-UAV target allocation problems that consider offensive and defensive strategies, the specific behavioral strategies of the UAVs are also involved, significantly increasing the policy space. When the number of UAVs is large, existing methods struggle to find an effective solution within a reasonable timeframe, sometimes even failing to produce a result. Therefore, existing multi-UAV target allocation methods offer poor solution quality. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] To address the shortcomings of existing technologies, this invention provides a game theory method and system for attack and defense strategies in multi-UAV target allocation, solving the technical problem of low quality in solving multi-UAV target allocation in existing technologies.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] This invention addresses its technical problem by providing a game-theoretic method for attacking and defending strategies in multi-UAV target allocation. This method is executed by a computer and includes the following steps:

[0009] Obtain multi-drone formation information of the first drone formation and the second drone formation; the multi-drone formation information includes drone information;

[0010] Based on the drone information, multiple drone strategy pairs are generated, and a set of strategy groups for multiple drone formations is generated based on the strategy pairs; each strategy pair includes the current drone number, attack and defense strategy, and strategy target; the attack and defense strategy includes attack strategy, evasion strategy, and interference strategy; the strategy group includes multiple drone strategy pairs from multiple drone formations.

[0011] The strategy probability of each attack and defense strategy for multiple drones is obtained, and the payout matrix is ​​calculated based on the strategy probability.

[0012] Generate a zero-sum game matrix model; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation;

[0013] The zero-sum game matrix model is used to solve the offensive and defensive strategy game scheme for multi-UAV target allocation.

[0014] Preferably, calculating the payoff matrix based on the strategy probabilities includes:

[0015] Construct a strategy parameter matrix; the strategy parameter matrix includes a first strategy parameter matrix for a first UAV formation and a second strategy parameter matrix for a second UAV formation.

[0016] Calculate the first expected survival value of the first UAV formation based on the strategy parameter matrix and the strategy probability; calculate the second expected survival value of the second UAV formation based on the strategy parameter matrix and the strategy probability;

[0017] Calculate the revenue value of the first drone formation based on the first expected survival value and the second expected survival value;

[0018] Generate a profit matrix based on the profit values.

[0019] Preferably, the first strategy parameter matrix includes a first attack strategy parameter matrix, a first evasion strategy parameter matrix, and a first interference strategy parameter matrix;

[0020] The first attack strategy parameter matrix is:

[0021]

[0022] in,

[0023] a ij This represents the attack parameters of drone i in the first drone formation against drone j in the second drone formation;

[0024] m represents the number of drones in the first drone formation, and n represents the number of drones in the second drone formation;

[0025] This indicates the offensive and defensive strategies adopted by drone i; These represent attack strategies, evasion strategies, and interference strategies, respectively. This indicates the strategic target targeted by the offensive and defensive strategies employed by drone i;

[0026] The parameter matrix of the first evasion strategy is as follows:

[0027]

[0028] in,

[0029] h i This represents the avoidance parameters of drone i against the second drone formation;

[0030] The first interference strategy parameter matrix is ​​as follows:

[0031]

[0032] in,

[0033] l ij This represents the interference parameters of drone i on drone j.

[0034] Preferably, the second strategy parameter matrix includes a second attack strategy parameter matrix, a second evasion strategy parameter matrix, and a second interference strategy parameter matrix;

[0035] The second attack strategy parameter matrix is ​​as follows:

[0036]

[0037] in,

[0038] b ji This represents the attack parameters of drone j against drone i;

[0039] This indicates the offensive and defensive strategies adopted by drone j. These represent attack strategies, evasion strategies, and interference strategies, respectively. This represents the strategic objective of drone j;

[0040] The parameter matrix of the second evasion strategy is as follows:

[0041]

[0042] in,

[0043] h j This represents the avoidance parameters of drone j against the first drone formation;

[0044] The second interference strategy parameter matrix is ​​as follows:

[0045]

[0046] in,

[0047] l ji This represents the interference parameters of drone j on drone i.

[0048] Preferably, calculating the first expected survival value of the first UAV formation based on the strategy parameter matrix and the strategy probabilities includes:

[0049]

[0050] in,

[0051] u R (s R ,s B This indicates the first expected survival value of the first drone formation;

[0052] v i This represents the value of drone i in the first drone formation;

[0053] q i Let t represent the probability of drone i avoiding the second drone formation. ij p represents the probability of drone i interfering with drone j. ji Let represent the probability that drone j kills drone i.

[0054] Preferably, calculating the second expected survival value of the second UAV formation based on the strategy parameter matrix and the strategy probabilities includes:

[0055]

[0056] in,

[0057] u B (s R ,s B This indicates the second expected survival value of the second drone formation;

[0058] v j This indicates the value of drone j in the second drone formation;

[0059] q j Let t represent the probability that drone j will avoid the first drone formation. ji p represents the probability of drone j interfering with drone i. ij This represents the probability of drone i killing drone j.

[0060] Preferably, the revenue matrix includes:

[0061]

[0062] u(s R ,s B )=u R (s R ,s B )-u B (s R ,s B )

[0063] Among them, S R s represents the first drone formation strategy group set. R ∈S R S represents a strategy group of the first drone formation. B Indicates the second drone formation strategy group set, s B ∈S B This represents a strategy group for the second drone formation;

[0064] (s R ,s B This indicates that the first drone formation adopted strategy group s R The second drone formation adopted a strategy group s B Strategy group combination; u(s) R ,s B ) for the first drone formation in the strategy group combination (s R ,s B The profit value under ).

[0065] Preferably, the strategy for attacking and defending against multiple unmanned aerial vehicle (UAV) targets, based on the zero-sum game matrix model, includes:

[0066] Obtain a strict game set based on the zero-sum game matrix model;

[0067] Based on the strict game set, the Nash equilibrium solution is obtained, and based on the Nash equilibrium solution, the first initial strategy group of the first drone formation and the second initial strategy group of the second drone formation are selected.

[0068] The first optimal game strategy set that maximizes the marginal return of the first drone formation is calculated based on the second initial strategy set, and the second optimal game strategy set that maximizes the marginal return of the second drone formation is calculated based on the first initial strategy set.

[0069] If the first optimal game strategy set and / or the second optimal game strategy set do not exist in the strict game set, then the strict game set is updated based on the first optimal game strategy set and / or the second optimal game strategy set, and the step of solving for the Nash equilibrium solution based on the strict game set is re-executed based on the updated strict game set.

[0070] If both the first optimal game strategy group and the second optimal game strategy group exist in the strict game set, then the Nash equilibrium solution is determined as an offensive and defensive strategy game scheme for multi-UAV target allocation.

[0071] This invention provides a multi-UAV target allocation offensive and defensive strategy game system to solve its technical problem. The system includes:

[0072] The information acquisition module is configured to acquire multi-drone formation information of a first drone formation and a second drone formation; the multi-drone formation information includes drone information.

[0073] The strategy generation module is configured to generate strategy pairs for multiple drones based on the drone information, and to generate a set of strategy groups for multiple drone formations based on the strategy pairs; the strategy pairs include the current drone number, attack and defense strategies, and strategy targets; the attack and defense strategies include attack strategies, evasion strategies, and interference strategies; the strategy groups include strategy pairs for multiple drones in the multiple drone formations.

[0074] The revenue matrix generation module is configured to acquire the strategy probability of each attack and defense strategy of multiple drones, and generate a revenue matrix based on the strategy probability.

[0075] The model generation module is configured to generate a zero-sum game matrix model; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation.

[0076] The scheme allocation module is configured to solve the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model.

[0077] The present invention provides a computer-readable storage medium that solves its technical problem by storing a computer program for a game of attack and defense strategies for multi-UAV target allocation, wherein the computer program causes a computer to execute the game of attack and defense strategies for multi-UAV target allocation as described above.

[0078] (III) Beneficial Effects

[0079] This invention provides a game theory method and system for attack and defense strategies in multi-UAV target allocation. Compared with existing technologies, it has the following advantages:

[0080] This invention acquires multi-drone formation information from a first drone formation and a second drone formation to generate multiple drone strategy pairs based on the drone information. It then generates a set of strategy groups for the multi-drone formation based on these strategy pairs. Each strategy pair can include the current drone, an attack / defense strategy, and a strategy target. Attack / defense strategies include attack strategies, evasion strategies, and interference strategies. By calculating the probability distribution of each drone under different attack / defense strategies, a payoff matrix is ​​constructed, further generating a zero-sum game matrix model. Based on this zero-sum game matrix model, the attack / defense strategy game scheme for multi-drone target allocation is solved. This invention fully considers the three attack / defense strategies of drones and solves the attack / defense strategy game scheme, thereby improving the solution quality of the drone target allocation problem. Attached Figure Description

[0081] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a schematic diagram of a game theory scenario for the multi-UAV target allocation attack and defense strategy provided in an embodiment of the present invention. Detailed Implementation

[0083] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0084] This application provides a game theory method and system for attacking and defending strategies in multi-UAV target allocation, which solves the problem of low solution quality in existing technologies for multi-UAV target allocation and improves the solution quality of UAV target allocation.

[0085] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0086] This invention provides a game theory method for attack and defense strategies in multi-UAV target allocation. This method is executed by a computer and includes the following steps:

[0087] S1. Obtain multi-drone formation information of the first drone formation and the second drone formation; the multi-drone formation information includes drone information;

[0088] S2. Generate multiple policy pairs for drones based on the drone information, and generate a policy group set for multiple drone formations based on the policy pairs; the policy pair includes the current drone number, attack and defense strategy, and strategy target; the attack and defense strategy includes attack strategy, evasion strategy, and interference strategy; the policy group includes policy pairs for multiple drones in the multiple drone formations;

[0089] S3. Obtain the strategy probability of each attack and defense strategy of multiple drones respectively, and calculate the payout matrix based on the strategy probability;

[0090] S4. Construct a zero-sum game matrix model; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation;

[0091] S5. Solve the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model.

[0092] Figure 1 This is a schematic diagram illustrating a game theory scenario for the multi-UAV target allocation offensive and defensive strategy provided in an embodiment of the present invention. The following is a detailed analysis of each step.

[0093] In step S1, multi-drone formation information of the first drone formation and the second drone formation is obtained. This multi-drone formation information includes drone information.

[0094] P = {R, B} represents multi-drone formation information, characterizing the participants in the game. The two sides of the game include two multi-drone formations, referred to as the red side and the blue side in this embodiment. R represents the red side, referred to as the first drone formation in this embodiment. B represents the blue side, referred to as the second drone formation in this embodiment.

[0095] It should be noted that each drone in the first drone formation is collectively referred to as the first drone; each drone in the second drone formation is collectively referred to as the second drone. Each drone formation may include a number of drones. The red team has m drones, and the blue team has n drones.

[0096] The drone information also includes the value of each drone. The value of R's drones is expressed as... The value of Party B's drone is expressed as:

[0097] In step S2, multiple policy pairs for drones are generated based on the drone information, and a policy group set for multiple drone formations is generated based on the policy pairs.

[0098] The strategy pair includes the current drone number, attack and defense strategy, and strategy target; the attack and defense strategy includes attack strategy, evasion strategy, and interference strategy; the strategy group includes strategy pairs of multiple drones in a multi-drone formation.

[0099] In multi-drone games, each drone can adopt three strategies: attack, evasion, and interference. A drone can also use a strategy to target any of its opponent's drones; the targeted objective is called the strategy objective. Drones can be equipped with both offensive and electronic warfare weapons. A drone can attack an enemy drone, evade an attack from an enemy drone, or interfere with an enemy drone's attack, but can only choose to execute one strategy at a time.

[0100] Drones can engage in game theory using strategy pairs, which refer to the offensive and defensive strategies and objectives adopted by a particular drone.

[0101] Taking the i-th drone of the red team as an example, its strategy pair is (p,j), indicating that it adopts attack / defense strategy p, and the strategy target is the j-th drone of the blue team. Since the red team drones can adopt 3 strategies, and the strategy target can be set to any one of the n blue team drones, each red team drone can have (3×n) strategy pairs. Similarly, the blue team drones can adopt 3 strategies, and the strategy target can be set to any one of the m red team drones, so each blue team drone can have (3×m) strategy pairs.

[0102] It should be noted that for a drone swarm, each drone adopts a strategy pair during mission execution, and the strategy pairs adopted by all drones together constitute the current strategy group of the drone swarm. As the strategy pairs adopted by each drone may be different, the overall strategy group of the drone swarm will also be different.

[0103] In this embodiment of the application, using This represents a strategy group for player R. This indicates the strategy pair adopted by drone i of side R, including offensive and defensive strategies and strategic objectives. This indicates the strategy adopted by drone i. These represent three offensive and defensive strategies: attack, evasion, and interference. This represents the strategic objectives of R-side drone i in attacking, evading, and interfering with other drones. For example, if the strategy group formed by R-side's attack and defense strategy is [(1,2),(2,3),(3,3)], it means that R-side drone 1 attacks B-side drone 2, R-side drone 2 evades the attack of B-side drone 3, and R-side drone 3 interferes with B-side drone 3.

[0104] use This can represent a strategy group of Party B. This indicates the strategy adopted by drone j of party B. This indicates the offensive and defensive strategies adopted by drone j. These represent three offensive and defensive strategies: attack, evasion, and interference. This indicates the target that the drone is attacking, evading, or interfering with.

[0105] For a drone swarm, each drone selects a strategy pair. The strategy pairs of all drones are counted to form a strategy group for the drone swarm. Different strategy groups can be obtained by considering the different strategy pairs selected by the drones. All possible strategy group combinations are counted to generate a set of strategy groups, which represents the game strategies that the drone swarm can employ.

[0106] In step S3, the strategy probability of each attack and defense strategy of multiple drones is obtained, and the payout matrix is ​​calculated based on the strategy probability.

[0107] Each offensive and defensive strategy can be configured with a probability, including the kill probability of an attack strategy, the evasion probability of an evasion strategy, and the interference probability of an interference strategy.

[0108] The probabilities of the three strategies are represented as follows:

[0109] (1) Probability of lethality

[0110] Kill probability represents the probability that one drone successfully destroys another drone. The kill probability of Rf1 against Bf1j can be expressed as: The kill probability matrix of R against B can be expressed as: Where p ij Let $\frac{i}{R}$ represent the probability of killing UAV $j from UAV $B$. Similarly, the probability of killing UAV $j from UAV $R$ can be expressed as: The probability matrix of B's ​​kill on R can be expressed as:

[0111] (2) Probability of avoidance

[0112] The evasion probability represents the probability that one drone successfully evades an attack from another drone. The evasion probability of Ri against Bi's attack can be expressed as: The avoidance probability matrix of R against B can be expressed as: Similarly, the probability of B's ​​j avoiding R's attack can be expressed as: The avoidance probability matrix of Party B against Party R can be expressed as follows:

[0113] (3) Interference probability

[0114] The interference probability represents the probability that one drone successfully interferes with an attack by another drone. The interference probability of Rsquarei against Bsquarej can be expressed as: The interference probability matrix of R to B can be expressed as: Similarly, the probability of interference from B_j to R_i can be expressed as: The interference probability matrix of B to R can be expressed as:

[0115] Each probability can be pre-generated, and the probability of each strategy for the drone can be randomly generated.

[0116] Calculating the payoff matrix based on the strategy probabilities includes the following steps:

[0117] S211. Construct the strategy parameter matrix. The strategy parameter matrix includes the first strategy parameter matrix for the first UAV formation and the second strategy parameter matrix for the second UAV formation.

[0118] The first strategy parameter matrix includes the first attack strategy parameter matrix, the first evasion strategy parameter matrix, and the first interference strategy parameter matrix.

[0119] The parameter matrix for the first attack strategy is:

[0120]

[0121] in,

[0122] a ij This represents the attack parameters of drone i in the first drone formation against drone j in the second drone formation;

[0123] m represents the number of drones in the first drone formation, and n represents the number of drones in the second drone formation;

[0124] This indicates the offensive and defensive strategies adopted by drone i; These represent attack strategies, evasion strategies, and interference strategies, respectively. This indicates the strategic target targeted by the offensive and defensive strategies employed by drone i.

[0125] The parameter matrix of the first evasion strategy is as follows:

[0126]

[0127] in,

[0128] h i This represents the avoidance parameters of drone i against the second drone formation.

[0129] The first interference strategy parameter matrix is ​​as follows:

[0130]

[0131] in,

[0132] l ij This represents the interference parameters of drone i on drone j.

[0133] The second strategy parameter matrix includes the second attack strategy parameter matrix, the second evasion strategy parameter matrix, and the second interference strategy parameter matrix.

[0134] The second attack strategy parameter matrix is ​​as follows:

[0135]

[0136] in,

[0137] b ji This represents the attack parameters of drone j against drone i;

[0138] This indicates the offensive and defensive strategies adopted by drone j. These represent attack strategies, evasion strategies, and interference strategies, respectively. This represents the strategic objective of drone j.

[0139] The parameter matrix of the second evasion strategy is as follows:

[0140]

[0141] in,

[0142] h j This represents the avoidance parameters of drone j against the first drone formation.

[0143] The second interference strategy parameter matrix is ​​as follows:

[0144]

[0145] in,

[0146] l ji This represents the interference parameters of drone j on drone i.

[0147] S212. Calculate the first expected survival value of the first UAV formation based on the strategy parameter matrix and the strategy probability. Calculate the second expected survival value of the second UAV formation based on the strategy parameter matrix and the strategy probability.

[0148] The first expected survival value is expressed as:

[0149]

[0150] in,

[0151] u R (s R ,s B This indicates the first expected survival value of the first drone formation;

[0152] v i This represents the value of drone i in the first drone formation;

[0153] q i Let t represent the probability of drone i avoiding the second drone formation. ij p represents the probability of drone i interfering with drone j. ji Let represent the probability that drone j kills drone i.

[0154]

[0155] The machine's total expected survival value.

[0156] Let i represent the survival probability of drone i from side R;

[0157] This indicates the probability that drone i failed to evade and was destroyed. This indicates the probability that drone i failed to evade the attack.

[0158] This represents the probability that drone i will be destroyed;

[0159] This indicates the probability that drone i will not be destroyed;

[0160] This represents the probability that drone i is not destroyed by drone j from side B. Let represent the probability that drone i is destroyed by drone j. This represents the probability that drone j was not successfully interfered with by drone R.

[0161] The second expected survival value is expressed as:

[0162]

[0163] in,

[0164] u B (s R ,s B This indicates the second expected survival value of the second drone formation;

[0165] v j This indicates the value of drone j in the second drone formation;

[0166] q jLet t represent the probability that drone j will avoid the first drone formation. ji p represents the probability of drone j interfering with drone i. ij This represents the probability of drone i killing drone j.

[0167] S213. Calculate the revenue value of the first drone formation based on the first expected survival value and the second expected survival value.

[0168] The profit value of the first drone formation is expressed as follows:

[0169] u(s R ,s B )=u R (s R ,s B )-u B (s R ,s B )

[0170] in,

[0171] u(s R ,s B ) represents the revenue value of the first drone formation.

[0172] S214. Generate a profit matrix based on the profit values. The profit matrix can be represented as:

[0173]

[0174] Among them, S R s represents the first drone formation strategy group set. R ∈S R S represents a strategy group of the first drone formation. B Indicates the second drone formation strategy group set, s B ∈S B This refers to a strategy group within the second drone formation.

[0175] (s R ,s B This indicates that the first drone formation adopted strategy group s R The second drone formation adopted a strategy group s B Strategy group combination; u(s) R ,s B ) for the first drone formation in the strategy group combination (s R ,s B The profit value under ).

[0176] In step S4, a zero-sum game matrix model is constructed. This zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation.

[0177] Considering that the strategies adopted by both drone formations will affect the other's payoff, the game is modeled as a zero-sum game matrix model G = (P, S, U). This game model includes the drone component, the strategy component, and the payoff component.

[0178] The drone component P represents multi-drone formation information, the strategy component S represents multi-drone strategy information, and the revenue component U represents the revenue matrix.

[0179] Wherein, the strategy part S = S R ×S B , representing the set of strategies employed by the two drone formations in a game. S R Let s represent the set of strategy groups for the first drone formation, i.e., the set of strategy groups for the red side. R ∈S R S represents a strategy group for the red team. B s represents the second drone formation strategy set, i.e., the strategy set of the blue team. B ∈S B This represents a strategy group for the blue team. The strategy group includes the strategy pair information for each drone in the drone formation.

[0180] For the red team formation, since each of the m red team drones can have (3×n) policy pairs, the number of policy pairs τ in the red team formation is... R (3×n) m Similarly, the number of strategies τ for the blue team's formation. B (3×m) n The strategy space of an adversary is equal to the product of the number of possible strategy pairs that each adversary can take. Therefore, the size of the strategy space in this game is S|=τ. R ·τ B = (3×n) m ·(3×m) n .

[0181] For the payoff matrix of the game, u(s) R ,s B ) is R's strategy combination (s R ,s B The profit value for Party B under the given condition is -u(s). R ,s B ).

[0182] In step S5, the attack and defense strategy game scheme for multi-UAV target allocation is solved according to the zero-sum game matrix model.

[0183] Specifically, it includes the following steps:

[0184] S501. Obtain a strict game set based on the zero-sum game matrix model.

[0185] We can select p strategy groups from the first set of UAV formation strategy groups and q strategy groups from the second set of UAV formation strategy groups; where p and q are positive integers, and p≥2, q≥2. Specifically, we can select strategy groups from the first set of UAV formation strategy groups S. R Two strategy groups are selected, and in the second UAV formation strategy group S B Select two strategy groups.

[0186] The first strict game set of the first drone formation is generated based on p policy groups, and the second strict game set of the second drone formation is generated based on q policy groups.

[0187] For example, the first strict game set can include S R The two strategy groups selected in the second strict game set can be included in S. B The two strategy groups selected

[0188] S502. Solve for the Nash equilibrium solution based on the strict game set, and select the first initial strategy group for the first drone formation and the second initial strategy group for the second drone formation based on the Nash equilibrium solution. This includes the following steps:

[0189] The first and second strict game sets are processed using a pre-defined algorithm to obtain the first and second Nash equilibrium solutions. The first Nash equilibrium solution includes a first probability distribution of p strategy groups, and the second Nash equilibrium solution includes a second probability distribution of q strategy groups. The pre-defined algorithm can be a probability distribution algorithm.

[0190] The strategy group with the highest probability in the first probability distribution is determined as the first initial strategy group, and the strategy group with the highest probability in the second probability distribution is determined as the second initial strategy group.

[0191] S503. Based on the second initial strategy set, find the first optimal game strategy set that maximizes the marginal return of the first drone formation, and based on the first initial strategy set, find the second optimal game strategy set that maximizes the marginal return of the second drone formation.

[0192] S504. If the first optimal game strategy group and / or the second optimal game strategy group do not exist in the strict game set, that is, not both optimal game strategy groups exist in the strict game set, then update the strict game set based on the first optimal game strategy group and / or the second optimal game strategy group.

[0193] The update method is to add the first optimal response strategy set and / or the second optimal response strategy set that do not exist in the strict game set to the strict game set.

[0194] Then, based on the updated strict game set, the steps of solving for the Nash equilibrium solution based on the strict game set are re-executed.

[0195] If both the first optimal game strategy group and the second optimal game strategy group exist in the strict game set, then the Nash equilibrium solution is determined as an offensive and defensive strategy game scheme for multi-UAV target allocation.

[0196] This invention also provides a game theory system for attack and defense strategies involving multiple unmanned aerial vehicle (UAV) target allocation, characterized in that the system includes:

[0197] The information acquisition module is configured to acquire multi-drone formation information of a first drone formation and a second drone formation; the multi-drone formation information includes drone information.

[0198] The strategy generation module is configured to generate strategy pairs for multiple drones based on the drone information, and to generate a set of strategy groups for multiple drone formations based on the strategy pairs; the strategy pairs include the current drone number, attack and defense strategies, and strategy targets; the attack and defense strategies include attack strategies, evasion strategies, and interference strategies; the strategy groups include strategy pairs for multiple drones in the multiple drone formations.

[0199] The revenue matrix generation module is configured to acquire the strategy probability of each attack and defense strategy of multiple drones, and generate a revenue matrix based on the strategy probability.

[0200] The model generation module is configured to generate a zero-sum game matrix model; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation.

[0201] The scheme allocation module is configured to solve the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model.

[0202] It is understood that the target allocation system provided in this embodiment of the invention corresponds to the attack and defense strategy game method. The explanation, examples, and beneficial effects of the relevant content can be referred to the corresponding content in the attack and defense strategy game method for multi-UAV target allocation, and will not be repeated here.

[0203] The invention also provides a computer-readable storage medium storing a computer program for a multi-UAV target allocation attack and defense strategy game, wherein the computer program causes a computer to execute the above-described multi-UAV target allocation attack and defense strategy game method. In summary, compared with the prior art, it has the following beneficial effects:

[0204] This invention acquires multi-drone formation information from a first drone formation and a second drone formation to generate multiple drone strategy pairs based on the drone information. A set of strategy groups for the multi-drone formation is then generated based on these strategy pairs. Each strategy pair can include the current drone, an attack / defense strategy, and a strategy target. Attack / defense strategies include attack strategies, evasion strategies, and interference strategies. By calculating the probability distribution of each drone under different attack / defense strategies, a payoff matrix is ​​constructed, further generating a zero-sum game matrix model. Based on this zero-sum game matrix model, the attack / defense strategy game scheme for multi-drone target allocation is solved. This invention fully considers the three attack / defense strategies of drones and solves the attack / defense strategy game scheme, thereby improving the solution quality of the drone target allocation problem.

[0205] It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms. The technical solutions described above, in essence or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or certain parts of embodiments. Numerous specific details are set forth in the specification provided herein. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0206] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0207] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A game theory method for attacking and defending strategies in multi-UAV target allocation, wherein the game theory method is executed by a computer, characterized in that, Includes the following steps: Obtain multi-drone formation information of the first drone formation and the second drone formation; the multi-drone formation information includes drone information; Based on the drone information, multiple drone strategy pairs are generated, and a set of strategy groups for multiple drone formations is generated based on the strategy pairs; each strategy pair includes the current drone number, attack and defense strategy, and strategy target; the attack and defense strategy includes attack strategy, evasion strategy, and interference strategy; the strategy group includes multiple drone strategy pairs from multiple drone formations. The strategy probability of each attack and defense strategy for multiple drones is obtained, and the payout matrix is ​​calculated based on the strategy probability. A zero-sum game matrix model is constructed; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation; Solve the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model; The calculation of the payoff matrix based on the strategy probabilities includes: Construct a strategy parameter matrix; the strategy parameter matrix includes a first strategy parameter matrix for a first UAV formation and a second strategy parameter matrix for a second UAV formation. Calculate the first expected survival value of the first UAV formation based on the strategy parameter matrix and the strategy probability; calculate the second expected survival value of the second UAV formation based on the strategy parameter matrix and the strategy probability; Calculate the revenue value of the first drone formation based on the first expected survival value and the second expected survival value; Calculate the profit matrix based on the profit values; The first strategy parameter matrix includes a first attack strategy parameter matrix, a first evasion strategy parameter matrix, and a first interference strategy parameter matrix; The first attack strategy parameter matrix is ​​as follows: in, Indicates the drones in the first drone formation i For the drones in the second drone formation j Attack parameters; m This indicates the number of drones in the first drone formation. n Indicates the number of drones in the second drone formation; Indicates drone i The offensive and defensive strategies adopted; , representing attack strategy, evasion strategy and interference strategy respectively; Indicates drone i The strategic objectives targeted by offensive and defensive strategies; The parameter matrix of the first evasion strategy is as follows: in, Indicates drone i Avoidance parameters for the second drone formation; The first interference strategy parameter matrix is ​​as follows: in, Indicates drone i For drones j Interference parameters.

2. The attack and defense strategy game method according to claim 1, characterized in that, The second strategy parameter matrix includes a second attack strategy parameter matrix, a second evasion strategy parameter matrix, and a second interference strategy parameter matrix; The second attack strategy parameter matrix is ​​as follows: in, Indicates drone j For drones i Attack parameters; Indicates drone j The offensive and defensive strategies adopted , representing attack strategy, evasion strategy and interference strategy respectively; Indicates drone j The strategic objective; The parameter matrix of the second evasion strategy is as follows: in, Indicates drone j Avoidance parameters for the first drone formation; The second interference strategy parameter matrix is ​​as follows: in, Indicates drone j For drones i Interference parameters.

3. The attack and defense strategy game method according to claim 2, characterized in that, The first expected survival value of the first UAV formation is calculated based on the strategy parameter matrix and the strategy probability, including: in, This indicates the primary expected survival value of the first drone formation; This indicates the first drone formation strategy group assembly. This indicates the second drone formation strategy group set; Indicates the drones in the first drone formation i Value; Indicates drone i The probability of avoiding the second drone formation Indicates drone i For drones j The probability of interference, Indicates drone j For drones i The probability of causing damage.

4. The attack and defense strategy game method according to claim 3, characterized in that, The second expected survival value of the second UAV formation is calculated based on the strategy parameter matrix and the strategy probability, including: in, This indicates the second expected survival value of the second drone formation; This indicates the drones in the second drone formation. j Value; Indicates drone j The probability of avoiding the first drone formation Indicates drone j For drones i The probability of interference, Indicates drone i For drones j The probability of causing damage.

5. The attack and defense strategy game method according to claim 4, characterized in that, The payout matrix includes: in, This indicates the first drone formation strategy group assembly. This represents a strategy group for the first drone formation. This indicates the assembly of the second drone formation strategy group. This represents a strategy group for the second drone formation; The first drone formation indicated that it adopted a strategy group. The second drone formation adopted a strategy group Strategy group combination; For the first drone formation in the strategy group combination The profit value below.

6. The attack and defense strategy game method according to claim 1, characterized in that, Solving the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model includes: Obtain a strict game set based on the zero-sum game matrix model; Based on the strict game set, the Nash equilibrium solution is obtained, and based on the Nash equilibrium solution, the first initial strategy group of the first drone formation and the second initial strategy group of the second drone formation are selected. The first optimal game strategy set that maximizes the marginal return of the first drone formation is calculated based on the second initial strategy set, and the second optimal game strategy set that maximizes the marginal return of the second drone formation is calculated based on the first initial strategy set. If the first optimal game strategy set and / or the second optimal game strategy set do not exist in the strict game set, then the strict game set is updated based on the first optimal game strategy set and / or the second optimal game strategy set, and the step of solving for the Nash equilibrium solution based on the strict game set is re-executed based on the updated strict game set. If both the first optimal game strategy group and the second optimal game strategy group exist in the strict game set, then the Nash equilibrium solution is determined as an offensive and defensive strategy game scheme for multi-UAV target allocation.

7. A multi-UAV target allocation attack and defense strategy game system, applied to the attack and defense strategy game method as described in claim 1, characterized in that, The system includes: The information acquisition module is configured to acquire multi-drone formation information of a first drone formation and a second drone formation; the multi-drone formation information includes drone information. The strategy generation module is configured to generate strategy pairs for multiple drones based on the drone information, and to generate a set of strategy groups for multiple drone formations based on the strategy pairs; the strategy pairs include the current drone number, attack and defense strategies, and strategy targets; the attack and defense strategies include attack strategies, evasion strategies, and interference strategies; the strategy groups include strategy pairs for multiple drones in the multiple drone formations. The revenue matrix generation module is configured to acquire the strategy probability of each attack and defense strategy of multiple drones, and generate a revenue matrix based on the strategy probability. The model generation module is configured to generate a zero-sum game matrix model; the zero-sum game matrix model includes multi-drone formation information, multi-drone strategy information, and a payoff matrix; the multi-drone strategy information includes a set of strategy groups for the multi-drone formation. The scheme allocation module is configured to solve the attack and defense strategy game scheme for multi-UAV target allocation based on the zero-sum game matrix model.

8. A computer-readable storage medium, characterized in that, It stores a computer program for a game of offensive and defensive strategies for multi-UAV target allocation, wherein the computer program causes a computer to execute the game of offensive and defensive strategies for multi-UAV target allocation as described in any one of claims 1 to 6.

Images