Mechanisms of Group Intelligence Emergence in UAV Swarms

doi:10.12382/bgxb.2022.1181

Abstract

Abstract:

Understanding the emergence of autonomous cooperative behavior in UAV swarms is a challenging problem. In this study, an analysis method for studying the autonomous cooperative behavior emergence in multi-agent systems is proposed. The method analyzes three levels of the system: the micro-individual layer, the meso-structure layer, and the macro-network layer. It also quantifies the dynamic evolution process of the system from the bottom up, revealing the internal logic of the system from micro to macro and identifying problems in system evolution. The computational experimental model of UAV swarms is also introduced, and the information network of UAV swarm association is designed according to the key features of swarm operations. The game mechanism for public goods is introduced, and the cooperative evolution model of swarms is constructed. The evolution dynamics of swarms on the association network is revealed. Through numerical simulation, the emergence of swarm cooperative behaviors is quantitatively analyzed from different levels of the UAV swarm system, so as to understand the emergence mechanisms of autonomous and cooperative swarm behaviors and provide decision support for the optimization of UAV swarm cooperative mechanisms.

Key words: UAV swarm, swarm intelligence, emergence mechanism, evolutionary game, complex network

CLC Number:

GONG Yuanqiang, ZHANG Yepeng, MA Wanpeng, XUE Xiao. Mechanisms of Group Intelligence Emergence in UAV Swarms[J]. Acta Armamentarii, 2023, 44(9): 2661-2671.

Figures/Tables 12

Fig.1 Analysis framework of emergence in complex systems

Fig.2 Agent's behavior process at micro level

Fig.3 Organizational structure of multi-agent systems

Fig.4 Emergence process of swarm behaviors at macro level

Table 1 Conceptual mapping between UAV swarm collaboration and public goods game

公共物品演化博弈	无人机蜂群自主协同机制
空间结构种群	无人机蜂群
公共物品	作战资源(弹药、通信等)
个体	无人机个体
合作策略(Collaboration, C)	无人机选择向蜂群贡献资源
非合作策略(Defection, D)	无人机拒绝向蜂群贡献资源
收益	无人机的作战效益
演化	多轮博弈中,无人机策略动态变化, 蜂群策略分布也在动态变化
博弈	无人机之间进行通信并根据收益进行策略选择

Table 2 Attributes of a UAV agent

属性	属性描述	现实映射
T	Agent的类型	无人机蜂群由多个子群组成
R	Agent具有的资源	无人机携带的作战资源
k	Agent的节点度	无人机通过链路进行通信
r	协作因子	无人机合作会产生规模效益
s	Agent的策略	无人机可以选择合作/非合作策略
c	选择合作策略的代价	无人机需要贡献自身资源
f	收益	无人机获得任务反馈情况
ω	选择强度	无人机更新策略的活跃度
α	期望水平	无人机对于自身收益的预设期望

Fig.5 UAV swarm communication network

Fig.6 Communication network topology for cooperative UAV swarm operations

Table 3 Experimental parameter setting

无人机属性	属性设置
蜂群规模	无人机蜂群的初始数量N=100
无人机种类	不同功能的无人机种群数量M=5,新生成的无人机随机加入一个无人机子群
无人机初始策略	随机选择合作策略C或非合作策略D
作战成本	无人机在每次博弈中选择合作策略的行为成本c=1
选择强度	为了不失一般性,本文设定选择强度ω=1
节点平均度	节点内连接m=2,外连接n=1,平均度 $k ¯$ ≈4
协作因子	r=10
无人机蜂群规模	无人机蜂群的初始数量N=100

Table 3 Experimental parameter setting

无人机属性	属性设置
蜂群规模	无人机蜂群的初始数量N=100
无人机种类	不同功能的无人机种群数量M=5,新生成的无人机随机加入一个无人机子群
无人机初始策略	随机选择合作策略C或非合作策略D
作战成本	无人机在每次博弈中选择合作策略的行为成本c=1
选择强度	为了不失一般性,本文设定选择强度ω=1
节点平均度	节点内连接m=2,外连接n=1,平均度 $k ¯$ ≈4
协作因子	r=10
无人机蜂群规模	无人机蜂群的初始数量N=100

Fig.7 Relationship curve between the level of swarm cooperation and the operational cost

Fig.8 The impact of the relative relationship between the value of internal connections and the value of external connections on the level of cooperation

Fig.9 Relationship curve between the level of colony cooperation and the average degree of network

References 30

[1]	BENI G. From swarm intelligence to swarm robotics[C]//Proceedings of International Workshop on Swarm Robotics.Berlin, Heidelberg,Germany:Springer, 2004:1-9.
[2]	KENNEDY J. Swarm intelligence[M]. Handbookof Nature-inspired and InnovativeComputing. Boston, MA,US:Springer, 2006:187-219.
[3]	KARABOGA D, AKAY B. A comparative study of artificial bee colony algorithm[J]. Applied Mathematics and Computation, 2009, 214(1): 108-132. doi: 10.1016/j.amc.2009.03.090 URL
[4]	MARINI F, WALCZAK B. Particle swarm optimization (PSO). a tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149:153-165. doi: 10.1016/j.chemolab.2015.08.020 URL
[5]	GROSS R, DORIGO M. Towards group transport by swarms of robots[J]. International Journal of Bio-Inspired Computation, 2009, 1(1/2):94-99.
[6]	梁晓龙, 张佳强, 吕娜. 无人机集群[M]. 西安: 西北工业大学出版社, 2018:1-6.
	LIANG X L, ZHANG J Q, LÜ N. UAV swarms[M]. Xi'an: Northwestern Polytechnical University Press, 2018:1-6. (in Chinese)
[7]	王华, 赵东杰, 杨海涛, 等. 大数据时代下网络群体智能研究方法[J]. 计算机与现代化, 2015(2): 1-6.
	WANG H, ZHAO D J, YANG H T, et al. Research method of web collective intelligence in era of big data[J]. Computer and Modernization, 2015(2): 1-6. (in Chinese)
[8]	LI W, WU W J, WANG H M, et al. Crowd intelligence in AI2.0 era[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 15-43.
[9]	郭斌. 论智能物联与未来制造——拥抱人机物融合群智计算时代[J]. 人民论坛学术前沿, 2020(13): 32-42. DOI: 10. 16619/j. cnki.rmltxsqy. 2020. 13. 004.
	GUO B. On intelligent IOT and future manufacturing embracing the era of human-computer-things swarm intelligence computing[J]. Frontiers, 2020(13): 32-42. DOI: 10. 16619/j. cnki. rmltxsqy. 2020. 13. 004. (in Chinese)
[10]	赵健, 张鑫褆, 李佳明, 等. 群体智能2.0研究综述[J]. 计算机工程, 2019, 45(12): 1-7. doi: 10.19678/j.issn.1000-3428.0056410
	ZHAO J, ZHANG X T, LI J M, et al. Review on Swarm Intelligence 2.0[J]. Computer Engineering, 2019, 45(12): 1-7. (in Chinese) doi: 10.19678/j.issn.1000-3428.0056410
[11]	BOSKOVIC J, KNOEBEL N, MOSHTAGH N, et al. Collaborative mission planning & autonomous control technology (compact) system employing swarms of uavs[C] //Proceedings of AIAA Guidance, Navigation, and Control Conference. Reston, VA, US:AIAA, 2009: 5653.
[12]	张婷婷, 宋爱国, 蓝羽石. 集群无人系统自适应结构建模与预测[J]. 中国科学:信息科学, 2020, 50(3):16-19.
	ZHANG T T, SONG A G, LAN Y S. Adaptive structural modeling and prediction for unmanned swarms systems[J]. Chinese Science: Information Science, 2020, 50(3):16-19. (in Chinese)
[13]	HOUSSEIN E H, SABER E, WAZERY Y M, et al. Swarm intelligence algorithms-based machine learning framework for medical diagnosis:a comprehensive review[J]. Integrating Heuristics and Machine Learning for Real-World Optimization Problems, 2022, 1038: 85-106.
[14]	YU M G, HE M, MA Z Y, et al. Cooperative evolution mechanism of unmanned swarm within the framework of public goods game[J]. Mathematical Problems in Engineering, 2021, 2021(1):1-12.
[15]	ZHOU D Y, XUE X, ZHOU Z B. Sle2:the improved social learning evolution model of cloud manufacturing service ecosystem[J]. IEEE Transactions on Industrial Informatics, 2022, 18(12):9017-9026. doi: 10.1109/TII.2022.3173053 URL
[16]	XUE X, WANG S F, ZHANG L J, et al. Social learning evolution(sle):computational experiment-based modeling framework of social manufacturing[J]. IEEE Transactions on Industrial Informatics, 2018, 15(6):3343-3355. doi: 10.1109/TII.9424 URL
[17]	XUE X, YU X N, ZHOU D Y, et al. Computational experiments for complex social systems—part iii:the docking of domain models[J]. IEEE Transactions on Computational Social Systems, 2023:1-15. DOI:10.1109/TCSS.2023.3243894.
[18]	XUE X, CHEN F Y, ZHOU D Y, et al. Computational experiments for complex social systems—part i:the customization of computational model[J]. IEEE Transactions on Computational Social Systems, 2021, 9(5):1330-1344. doi: 10.1109/TCSS.2021.3125287 URL
[19]	LU M, CHEN S Z, XUE X, et al. Computational experiments for complex social system Part Ⅱ: the evaluation of computational model[J]. IEEE Transactions on Computational Social Systems, 2022, 9(4):1224-1236. doi: 10.1109/TCSS.2021.3121323 URL
[20]	薛霄, 于湘凝, 周德雨, 等. 计算实验方法的溯源、现状与展望[J]. 自动化学报, 2023, 49(2):246-271.
	XUE X, YU X N, ZHOU D Y, et al. Computational experiments: past, present and perspective[J]. Acta Automatica Sinica, 2023, 49(2): 246-271. (in Chinese)
[21]	XUE X, LI G D, ZHOU D Y, et al. Research roadmap of service ecosystems: a crowd intelligence perspective[J]. International Journal of Crowd Science, 2022, 6(4):195-222. doi: 10.26599/IJCS.2022.9100026 URL
[22]	FROMM J. Types and forms of emergence:arXiv preprint nlin/0506028[R]. Ithaca,NY,US:Cornell,University, 2005:preprint nlin/0506028.
[23]	FALOUTSOS M, FALOUTSOS P, FALOUTSOS C. On power-law relationships of the Internet topology[J]. Poceedings of Acm Sigcomm, 1999, 29(4):251-262.
[24]	VINCENT T L, BROWN J S. Evolutionary game theory, natural selection, and darwinian dynamics: evolutionary ecology[M] //VINCENTT L, BROWNJ S. New York,NY, US: Cambridge University Press, 2005:343-363.
[25]	TAN JONATHAN H W, BOLLE F. Team competition and the public goods game[J]. Economics Letters, 2007, 96(1):133-139. doi: 10.1016/j.econlet.2006.12.031 URL
[26]	王龙. 多智能体协调控制的演化博弈方法[J]. 系统科学与数学, 2016, 36(3):302-318. doi: 10.12341/jssms12735
	WANG L. Evolutionary game method for multi-agent coordinated control[J]. Systems Science and Mathematics, 2016, 36(3):302-318. (in Chinese)
[27]	GYORGY S, CSABA T. Evolutionary prisoner's dilemma game on a square lattice[J]. Physical Review E, 1998, 58(1): 69-73. doi: 10.1103/PhysRevE.58.69 URL
[28]	ZHANG J L, ZHU Y Y, CHEN Z Q. Evolutionary game dynamics of multiagent systems on multiple community networks[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2018, 50(11):4513-4529. doi: 10.1109/TSMC.6221021 URL
[29]	NORTH M J, TATARA E, COLLIER N T, et al. Visual agent-based model development with repast simphony[C] //Proceedings of Agent Conference on Complex Interaction & Social Emergence.Evanston, IL, US:Department of Energy: Argonne National Laboratory, 2007:1-20.
[30]	纪广, 郝建国, 张振伟. 面向无人机作战的虚拟孪生系统设计方案[J]. 兵工学报, 2022, 43(8): 1902-1912.
	JI G, HAO J G, ZHANG Z W. Design scheme of virtual twin system for UAV combat[J]. Acta Armamentarii, 2022, 43(8): 1902-1912. (in Chinese) doi: 10.12382/bgxb.2021.0408