基于态势演化博弈的无人机集群动态攻防

doi:10.12305/j.issn.1001-506X.2023.08.06

摘要/Abstract

摘要：

针对无人机集群动态攻防问题, 提出了态势演化博弈模型。首先，从基地与守方无人机集群相互作用以及攻防双方动态斗争角度出发, 构建了攻方无人机与守方无人机的态势演化博弈模型。其次，设计了同态势演化博弈模型相对应的态势评估函数, 使每阶段个体的策略选择都为该阶段的最优解。然后，根据策略选择, 结合社会力模型, 驱动无人机向指定目标运动, 完成攻防双方无人机集群的动态对抗。实验结果表明, 无人机集群的动态运动符合空战情况, 验证了基地在具备功能时的优越性, 以及设计的态势演化博弈模型能够实现无人机集群对抗决策的自适应选择。

关键词: 无人机, 演化博弈, 态势评估, 智能体决策, 集群对抗策略

Abstract:

To solve the problem of dynamic offense and defense in unmanned aerial vehicle (UAV) swarms, a situation evolution game model is proposed. Firstly, building upon the interactions between both the base and the defender's UAV swarms, as well as the descriptions of the dynamic struggle between offender and defender, a situation evolution game model is established by taking into account situation evolution among offending and defending UAVs. Secondly, a corresponding situation evaluation function is designed to optimize individual strategy selection at each stage of combat. Then, based on this strategy selection and through the use of the social force model, the UAVs are driven to move towards designated targets, resulting in a dynamic confrontation between the offending and defending UAV swarms. Experimental results demonstrate that the dynamic movement of the UAV swarms conforms to those observed in actual air combat scenarios, verifies the superior position of a functioning base, and confirms the accuracy of the UAV swarms'adaptive decision-making through the use of the situation evolution game model.

Key words: unmanned aerial vehicle (UAV), evolutionary game, situation assessment, agent decision-making, swarm confrontation strategy

中图分类号:

V279

盛磊, 时满红, 亓迎川, 李浩, 庞明军. 基于态势演化博弈的无人机集群动态攻防[J]. 系统工程与电子技术, 2023, 45(8): 2332-2342.

Lei SHENG, Manhong SHI, Yingchuan QI, Hao LI, Mingjun PANG. Dynamic offense and defense of UAV swarm based on situation evolution game[J]. Systems Engineering and Electronics, 2023, 45(8): 2332-2342.

图/表 21

图1

图2

图3

表1

表2

表3

图4

图5

图6

图7

表4

表5

表6

图8

图9

图10

图11

图12

图13

图14

图15

参考文献 30

1	伍文迪, 武云龙, 李晶华, 等. 基于层次式动态任务调度架构下的多无人机巡逻实现[J]. 中南大学学报, 2020, 27 (9): 2614- 2627.
	WU W D , WU Y L , LI J H , et al. Multi-UAV surveillance implementation under hierarchical dynamic task scheduling architecture[J]. Journal of Central South University, 2020, 27 (9): 2614- 2627.
2	DERAFA L , BENALLEGUE A , FRIDMAN L J J O T F I . Super twisting control algorithm for the attitude tracking of a four rotors UAV[J]. Journal of the Franklin Institute, 2012, 349 (2): 685- 699. doi: 10.1016/j.jfranklin.2011.10.011
3	杨圣慧, 郑永军, 刘星星, 等. 基于无人机近地面多光谱图像的蛇龙珠葡萄成熟度判别[J]. 光谱学与光谱分析, 2021, 41 (10): 3220- 3226.
	YANG S H , ZHENG Y J , LIU X X , et al. Cabernet Gernischt maturity determination based on near-ground multispectral fi-gures by using UAVs[J]. Spectroscopy and Spectral Analysis,
4	段海滨, 霍梦真, 范彦铭. 仿鹰群智能的无人机集群协同对抗飞行验证[J]. 控制理论与应用, 2018, 35 (12): 1812- 1819.
	DUAN H B , HUO M Z , FAN Y M . Flight verification of multiple UAVs collaborative air combat imitating the intelligent behavior in hawks[J]. Control Theory & Applications, 2018, 35 (12): 1812- 1819.
5	ZHOU Y K , RAO B , WANG W . UAV swarm intelligence: recent advances and future trends[J]. IEEE Access, 2020, 8, 183856- 183878. doi: 10.1109/ACCESS.2020.3028865
6	高显忠, 项磊, 王宝来, 等. 针对无人机集群对抗的规则与智能耦合约束训练方法[J]. 国防科技大学学报, 2023, 45 (1): 157- 166.
	GAO X Z , XIANG L , WANG B L , et al. Rule and intelligence coupling constraint training method for UAV swarm confrontation[J]. Journal of National University of Defense Technology, 2023, 45 (1): 157- 166.
7	孙智孝, 杨晟琦, 朴海音, 等. 未来智能空战发展综述[J]. 航空学报, 2021, 42 (8): 35- 49.
	SUN Z X , YANG S Q , PIAO H Y , et al. A survey of air combat artificial intelligence[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42 (8): 35- 49.
8	王尔申, 郭靖, 宏晨, 等. 基于随机空间网络的无人机集群协同对抗模型[J]. 北京航空航天大学学报, 2023, 49 (1): 10- 16.
	WANG E S , GUO J , HONG C , et al. Cooperative confrontation model of UAV swarm with random spatial networks[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49 (1): 10- 16.
9	傅莉, 谢福怀, 孟光磊, 等. 基于滚动时域的无人机空战决策专家系统[J]. 北京航空航天大学学报, 2015, 41 (11): 1994- 1999.
	FU L , XIE F H , MENG G L , et al. An UAV air-combat decision expert system based on receding horizon control[J]. Journal of Beijing University of Aeronautics and Astronautics, 2015, 41 (11): 1994- 1999.
10	XING D J , ZHEN Z Y , GONG H J . Offense-defense confrontation decision making for dynamic UAV swarm versus UAV swarm[J]. Proceedings of the Institution of Mechanical Engineers, 2019, 233 (15): 5689- 5702.
11	谭目来, 丁达理, 谢磊, 等. 基于模糊专家系统与IDE算法的UCAV逃逸机动决策[J]. 系统工程与电子技术, 2022, 44 (6): 1984- 1993.
	TAN M L , DING D L , XIE L , et al. UCAV escape maneuvering decision based on fuzzy expert system and IDE algorithm[J]. Systems Engineering and Electronics, 2022, 44 (6): 1984- 1993.
12	YANG Q M , ZHANG J D , SHI G Q , et al. Maneuver decision of UAV in short-range air combat based on deep reinforcement learning[J]. IEEE Access, 2019, 8, 363- 378.
13	FREY E . Evolutionary game theory: theoretical concepts and applications to microbial communities[J]. Physica A, Statistical Mechanics and its Applications, 2010, 389 (20): 4265- 4298.
14	LIU Y , LI H , JIANG Z Z , et al. Prospects for multi-agent colla-boration and gaming challenge, technology, and application[J]. Frontiers of Information Technology & Electronic Engineering, 2022, 23 (7): 1002- 1010.
15	罗俊仁, 张万鹏, 苏炯铭, 等. 多智能体博弈学习研究进展[EB/OL]. [2023-05-01]. https://kns.cnki.net/kcms/detail/11.2422.TN.202220625.1341.018.html.
	LUO J R, ZHANG W P, SU J M, et al. Research progress of multi-agent game theoretic learning[EB/OL]. [2023-05-01]. https://kns.cnki.net/kcms/detail/11.2422.TN.202220625.1341.018.html.
16	OMIDSHAFIEI S, TUYLS K, CZARNECKI W M, et al. Navigating the landscape of games[EB/OL]. [2023-05-01]. https://arxiv.org/abs/2005.06642.
17	MYERSON R B . Game theory: analysis of conflict[M]. Cambridge: Harvard University Press, 1997.
18	ZHANG J L , CAO M , BRIEFS S I E . Strategy competition dynamics of multi-agent systems in the framework of evolutio-nary game theory[J]. IEEE Trans. on Circuits, 2020, 67 (1): 152- 156.
19	DUAN H B , LI P , YU Y X . A predator-prey particle swarm optimization approach to multiple UCAV air combat modeled by dynamic game theory[J]. IEEE/CAA Journal of Automatica Sinica, 2015, 2 (1): 11- 18.
20	YU Y P , LIU J C , WEI C . Hawk and pigeon's intelligence for UAV swarm dynamic combat game via competitive learning pigeon-inspired optimization[J]. Science China Technological Sciences, 2022, 65 (5): 1072- 1086.
21	ALEXOPOULOS A, BADREDDIN E. Decomposition of multi-player games on the example of pursuit-evasion games with unmanned aerial vehicles[C]//Proc. of the American Control Conference, 2016.
22	VICSEK T , CZIROK A , BEN-JACOB E , et al. Novel type of phase transition in a system of self-driven particles[J]. Physical Review Letters, 1995, 75 (6): 1226- 1229.
23	OLFATI-SABER R , MURRAY R . Consensus problems in networks of agents with switching topology and time-delays[J]. IEEE Trans. on Automatic Control, 2004, 49 (9): 1520- 1533.
24	COUZIN I D , KRAUSE J , FRANKS N R , et al. Effective leadership and decision-making in animal groups on the move[J]. Nature, 2005, 433 (7025): 513- 516.
25	HELBING D , FARKAS I , VICSEK T , et al. Simulating dynamical features of escape panic[J]. Nature, 2000, 407 (6803): 487- 490.
26	赵蕊蕊, 于海跃, 游雅倩, 等. 无人集群试验评估现状及技术方法综述[EB/OL]. [2023-05-01]. https://kns.cnki.net/kcms/detail/11.2422.TN.20221025.1057.008.html.
	ZHAO R R, YU H Y, YOU Y Q, et al. Review on current development and technologies of unmanned swarm test evaluation[EB/OL]. [2023-05-01]. https://kns.cnki.net/kcms/detail/11.2422.TN.20221025.1057.008.html.
27	ZHAN C , ZENG Y . Aerial-ground cost tradeoff for multi-UAV-enabled data collection in wireless sensor networks[J]. IEEE Trans. on Communications, 2020, 68 (3): 1937- 1950.
28	YAN M , YUAN H M , XU J , et al. Task allocation and route planning of multiple UAVs in a marine environment based on an improved particle swarm optimization algorithm[J]. EURASIP Journal on Advances in Signal Processing, 2021, 2021 (1): 94.
29	TAYLOR P D , JONKER L B . Evolutionarily stable strategies and game dynamics[J]. Mathematical Biosciences, 1978, 40 (1): 145- 156.
30	ZHANG M , ZHU J J , WANG H H . Evolutionary game analysis of problem processing mechanism in new collaboration[J]. Journal of Systems Engineering and Electronics, 2021, 32 (1): 136- 150.

攻方无人机	守方无人机
攻方无人机	出击	防御
进攻	(G₁－C_i－B₁, B₁－C_j－π₁G₁)	(G₁－C_i－B₂－π₃B₃, B₂－C_j－π₁G₁+π₂R+π₃B₃)
防守	(G₂－C_i－B₁, B₁－C_j－G₂)	(G₂－C_i－B₂－π₃B₃, B₂－C_j－G₂+π₂R+π₃B₃)

序号	均衡点坐标(x, y)
1	(0, 0)
2	(1, 0)
3	(0, 1)
4	(1, 1)

均衡点序号	det(J)	tr(J)
1	－(G₁－G₂)(B₂－B₁+B₃π₃+Rπ₂)	B₁－B₂+G₁－G₂－B₃π₃－Rπ₂
2	(G₁－G₂)(B₂－B₁+B₃π₃+Rπ₂)	B₁－B₂－G₁+G₂－B₃π₃－Rπ₂
3	(G₁－G₂)(B₂－B₁+B₃π₃+Rπ₂)	B₂－B₁+G₁－G₂+B₃π₃+Rπ₂
4	－(G₁－G₂)(B₂－B₁+B₃π₃+Rπ₂)	B₂－B₁－G₁+G₂+B₃π₃+Rπ₂

博弈论模型	态势评估函数
B₂	S_ji(d_jb≤r_b)
B₁	S_ji(d_jb>r_b)
G₁	S_ib
π₁	p_i^O
G₂	S_ij
B₃	S_bj
π₃	p_b
R	S_jb
π₂	p_j^D

参数	取值
无人机速度范围/(m/s)	[60, 100]
无人机最大加速度/(m/s²)	a_max=5
无人机探测范围/m	r_s=4 000
无人机存活阈值	P_T=0.2
攻方无人机数目	N₀=10
初始条件攻方无人机采取进攻策略数目	10
初始条件攻方无人机采取防守策略数目	0
无人机携带武器数	Ω=4
无人机攻击范围/m	r_a=3 000
无人机理想杀伤概率	τ=0.6
基地探测范围/m	r_b=6 000
守方无人机数目	N_d=10
初始条件守方无人机采取防御策略数目	10
初始条件守方无人机采取出击策略数目	0