基于改进ABC算法的有-无人协同空战行为建模

doi:10.16182/j.issn1004731x.joss.24-FZ0753

摘要/Abstract

摘要：

为解决典型有-无人机空战场景下建立协同行为模型困难，模型对抗能力较弱的问题，提出了基于混合决策方式的有-无人机行为建模框架。通过协同规则集、规则子集、战术动作集等工具在该框架下构建了支持推磨战术、单边迂回战术等5种协同战术的分层决策协同行为模型；提出了一种基于改进人工蜂群算法(artificial bee colony，ABC)的行为模型参数优化方法。利用梅森旋转法初始化种群，得到更优的初始蜜源，并改善侦察蜂阶段的探索策略。结果表明：该协同行为模型具备较强的对抗能力，利用改进ABC算法对战术动作集的参数进行优化，可以提升行为模型构建效率和对抗效果。

关键词: 行为建模, 有-无人机协同, 分层决策, 参数优化, 战术动作集

Abstract:

To solve the problem of difficulty in establishing collaborative behavior models and weak adversarial capabilities in typical MAV/UAV air combat scenarios, a mixed decision based MAV/UAV behavior modeling framework is proposed. Using collaborative rule sets, rule subsets, tactical action sets, and other tools, a hierarchical decision collaborative behavior model supporting five types of collaborative tactics, including grinding tactics and unilateral flanking tactics, is constructed in this framework. a behavior model parameter optimization method based on an improved artificial bee colony (ABC) algorithm is proposed. By using the Mason rotation method to initialize the population, a better initial honey source was obtained, and the exploration strategy during the reconnaissance bee stage was improved. The results indicate that the collaborative behavior model has strong adversarial capabilities when simulated and validated in typical aerial combat scenarios. By optimizing the parameters of the tactical action set using the improved ABC algorithm, the efficiency of behavior model construction and adversarial effects can be improved.

Key words: behavioral modeling, MAV/UAV collaboration, layered decision-making, parameter optimization, tactical action set

中图分类号:

TP391

王鹏,刘昊雨,李妮等 . 基于改进ABC算法的有-无人协同空战行为建模[J]. 系统仿真学报, 2024, 36(12): 2871-2883.

Wang Peng,Liu Haoyu,Li Ni,et al . Behavioral Modeling of Manned-unmanned Cooperative Air Combat Based on Improved ABC Algorithm[J]. Journal of System Simulation, 2024, 36(12): 2871-2883.

图/表 21

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

表2

图13

图14

表3

表4

表5

图15

表6

参考文献 20

1	亓鹏程, 董志明, 高昂, 等. 一种基于深度强化学习的计算机生成兵力行为建模框架[C]//第四届体系工程学术会议论文集. 厦门: 国防科技大学系统工程学院, 2022: 165-173.
2	孟光磊, 张慧敏, 朴海音, 等. 非完备信息下的超视距空战双机协同战术识别[J]. 北京航空航天大学学报, 2023, 49(2): 284-294.
	Meng Guanglei, Zhang Huimin, Haiyin Piao, et al. Cooperative Tactical Recognition of Dual-aircraft Formation Under Incomplete Information in BVR Air Combat[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(2): 284-294.
3	赵小茹, 杨任农, 闫孟达, 等. 基于作战管理的有人-无人协同作战体系结构建模[J]. 空军工程大学学报, 2023, 24(5): 41-47.
	Zhao Xiaoru, Yang Rennong, Yan Mengda, et al. Modeling of Cooperative Combat System Architecture of Manned-unmanned Based on Battle Management[J]. Journal of Air Force Engineering University, 2023, 24(5): 41-47.
4	吴华兴. 基于Agent的人机组合行为建模关键技术研究[D]. 西安: 西北工业大学, 2016.
	Wu Huaxing. Study on the Key Technologies in Behavior Representation for Agent-based Pilot-aircraft Combination[D]. Xi'an: Northwestern Polytechnical University, 2016.
5	Zhan Zhijuan, Wang Yunhui, Li Bingfei, et al. Architecture Design of Air-sea Joint Combat System Based on DoDAF[C]//AOPC 2019: AI in Optics and Photonics. Bellingham: SPIE, 2019: 113420L.
6	张琪. 学习驱动的CGF决策行为建模方法研究[D]. 长沙: 国防科技大学, 2018.
	Zhang Qi. Research on Learning Driven Behavior Modeling Methods for Decision Making of Computer Generated Forces(CGFs)[D]. Changsha: National University of Defense Technology, 2018.
7	刘西, 陈伟, 冯志峰, 等. 双机编队空战仿真模型设计[J]. 系统仿真技术, 2023, 19(1): 79-83.
	Liu Xi, Chen Wei, Feng Zhifeng, et al. Design of Air Combat Simulation Model for Dual-aircraft Formation[J]. System Simulation Technology, 2023, 19(1): 79-83.
8	张栋, 唐俊林, 熊威, 等. 基于MATD3的视距内协同空战机动决策[J]. 航空兵器, 2023, 30(3): 20-28.
	Zhang Dong, Tang Junlin, Xiong Wei, et al. Maneuver Decision of Cooperative Air Combat Within Visual Range Based on MATD3[J]. Aero Weaponry, 2023, 30(3): 20-28.
9	史文卿, 王海峰, 陈海昕. 战斗机-无人机编组协同系统需求捕获与验证[J]. 系统工程与电子技术, 2023, 45(1): 108-118.
	Shi Wenqing, Wang Haifeng, Chen Haixin. Fighter-drone Teaming System Requirements Elicitation and Verification[J]. Systems Engineering and Electronics, 2023, 45(1): 108-118.
10	卢卓, 吴启晖, 周福辉. 有人机/无人机智能协同目标搜索和轨迹规划算法[J]. 通信学报, 2024, 45(1): 31-40.
	Lu Zhuo, Wu Qihui, Zhou Fuhui. Algorithm for Intelligent Collaborative Target Search and Trajectory Planning of MAV/UAV[J]. Journal on Communications, 2024, 45(1): 31-40.
11	Ma Ning, Cao Yunfeng. Consensus-based Distributed Formation Control for Coordinated Battle System of Manned/Unmanned Aerial Vehicles[J]. Transactions of the Institute of Measurement and Control, 2024, 46(1): 3-14.
12	Zhou Yaozhe, Lu Yujun, Liye Lü. Grid-based Non-uniform Probabilistic Roadmap-based AGV Path Planning in Narrow Passages and Complex Environments[J]. Electronics, 2024, 13(1): 225.
13	李浩. 基于改进人工蜂群算法的无人机协同应急重规划研究[D]. 济南: 山东交通学院, 2024.
	Li Hao. Research on UAV Collaborative Emergency Path Replanning Based on Improved Artificial Bee Colony Algorithm[D]. Ji'nan: Shandong Jiaotong University, 2024.
14	Cui Yibing, Hu Wei, Rahmani Ahmed. Fractional-order Artificial Bee Colony Algorithm with Application in Robot Path Planning[J]. European Journal of Operational Research, 2023, 306(1): 47-64.
15	高岳林, 杨钦文, 王晓峰, 等. 新型群体智能优化算法综述[J]. 郑州大学学报(工学版), 2022, 43(3): 21-30.
	Gao Yuelin, Yang Qinwen, Wang Xiaofeng, et al. Overview of New Swarm Intelligent Optimization Algorithms[J]. Journal of Zhengzhou University(Engineering Science), 2022, 43(3): 21-30.
16	Lee H W. Research on Multi-functional Logistics Intelligent Unmanned Aerial Vehicle[J]. Engineering Applications of Artificial Intelligence, 2022, 116: 105341.
17	Ziyadullaev Davron, Muhamediyeva Dildora, Ziyaeva Sholpan, et al. Development of a Traditional Transport System Based on the Bee Colony Algorithm[C]//E3S Web of Conferences. Les Ulis: EDP Sciences, 2023: 01017.
18	Cui Yibing, Hu Wei, Rahmani Ahmed. A Reinforcement Learning Based Artificial Bee Colony Algorithm with Application in Robot Path Planning[J]. Expert Systems with Applications, 2022, 203: 117389.
19	Rashid T, Samvelyan Mikayel, Christian Schroeder De Witt, et al. Monotonic Value Function Factorisation for Deep Multi-agent Reinforcement Learning[J]. The Journal of Machine Learning Research, 2020, 21(1): 7234-7284.
20	Xu Ximeng, Yang Rennong, Yu Yang. Threat Assessment in Air Combat Based on ELM Neural Network[C]//2019 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). Piscataway: IEEE, 2019: 114-120.

战术号	动作号	机动动作	参数注释
1	3	最速爬升	结束条件：俯仰角>30°
1	10	偏置	结束条件：方位角>60°
2	7	俯冲	期望俯仰角
2	10	偏置	结束条件：转离目标角度>40°
14	3	最速爬升	结束条件：俯仰角>20°
14	7	俯冲	结束条件：攻方战机海拔<4 000 m
27	7	俯冲	结束条件：攻方战机海拔<2 600 m
30	9	斜筋斗	斜筋斗角度
32	3	最速爬升	结束条件：攻方战机海拔>3 000 m
33	7	俯冲	结束条件：攻方战机海拔<2 600 m
34	10	偏置	结束条件：转离友机角度>130°

飞机名称	飞机编号	经度/(˚)	纬度/(˚)	高度/m
防守方长机	1	123.4	41.21	6 000
防守方僚机	2	123.3	41.19	10 000
进攻方长机	3	123.3	42.51	6 000
进攻方僚机	4	123.4	42.49	10 000

局数	战损比	长机存活	局数	战损比	长机存活
1	0∶2	是	11	0∶2	是
2	0∶1	是	12	0∶1	是
3	0∶1	是	13	1∶1	否
4	0∶2	是	14	1∶1	是
5	0∶2	是	15	0∶2	是
6	0∶1	是	16	1∶1	是
7	0∶2	是	17	0∶1	是
8	0∶2	是	18	0∶1	是
9	0∶2	是	19	1∶2	是
10	0∶1	是	20	0∶0	是

动作号	原值	遗传算法	ABC算法	改进ABC算法
3	30.00	15.04	25.77	30.00
10	140.00	98.50	103.45	90.23
7	-20.00	-17.46	-6.10	-0.27
10	80.00	87.99	95.52	46.56
3	20.00	17.51	2.46	0.99
7	4 000.00	3 176.54	5 146.04	4 984.92
7	2 600.00	3 843.90	2 850.42	3 238.78
9	80.00	72.78	61.22	33.96
3	3 000.00	4 557.04	4 689.48	3 400.59
7	2 600.00	3 619.87	2 918.81	3 702.78
10	130.00	105.67	164.91	92.24

战术号	动作号	每局使用次数	每局时间占比/%
1	3	43.2	1.3
1	10	42.3	6.5
2	7	39.7	1.6
2	10	39.2	3.3
14	3	462.9	2.2
14	7	292.8	0.9
27	7	1 938.2	1.4
30	9	218.2	0.2
32	3	45.0	1.3
33	7	1 093.8	6.4
34	10	108.6	2.6