基于群体意志统一的无人机协同围捕策略

刘峰; 魏瑞轩; 周凯; 丁超

doi:10.13700/j.bh.1001-5965.2021.0109

基于群体意志统一的无人机协同围捕策略

doi: 10.13700/j.bh.1001-5965.2021.0109

刘峰¹,
魏瑞轩^1, ,,
周凯^{1, 2},
丁超¹

1.
空军工程大学航空工程学院, 西安 710051
2.
空军航空大学, 长春 130000

基金项目:

科技部2030"新一代人工智能"重大项目 2018AAA0102403

详细信息

通讯作者:
魏瑞轩, E-mail: ruixuanWei123@163.com

中图分类号: TP391.9
计量
- 文章访问数: 461
- HTML全文浏览量: 108
- PDF下载量: 73
- 被引次数: 0
出版历程
- 收稿日期: 2021-03-05
- 录用日期: 2021-04-09
- 网络出版日期: 2021-04-20
- 整期出版日期: 2022-11-20

Multi-UAV round up strategy based on unity of group will

LIU Feng¹,
WEI Ruixuan^{1
, ,},
ZHOU Kai^{1, 2},
DING Chao¹

1.
College of Aeronautical Engineering, Air Force Engineering University, Xi'an 710051, China
2.
Air Force Aviation University, Changchun 130000, China

Funds:

Science and Technology Innovation 2030-Key Project of " New Generation Artificial Intelligence" 2018AAA0102403

More Information

Corresponding author: WEI Ruixuan, E-mail: ruixuanWei123@163.com

摘要

摘要:
针对无人机(UAV)协同围捕问题, 提出一种基于群体意志统一的围捕策略。受人类在协作任务中的认知机理启发, 引入“群体意志”定义无人机的协作认知, 并构建双回路认知模型, 借助图卷积网络对围捕无人机获取的局部态势进行融合认知, 有效减轻无人机系统的计算负载。依靠变分推断原理和生成式自动编码器对围捕无人机进行群体意志趋同学习, 依据Apollonius圆实现协同围捕, 使无人机集群涌现出更加智能化的围捕效果。通过对比仿真验证了所提策略的有效性和智能性。
- 协同围捕 /
- 群体意志统一 /
- 融合认知 /
- 趋同学习 /
- Apollonius圆
Abstract:
To solve the problem of unmanned aerial vehicle (UAV) coordinated rounding up, a strategy was proposed based on the unity of group will. Inspired by the cognitive mechanism of human beings in collaborative tasks, this paper introduces "group will" to define the collaborative cognition of UAVs, builds a double-loop cognitive model, and integrates the cognition of the local situation acquired by the rounded up UAVs with the help of the graph convolutional network, so as to effectively reduce the computing load of UAVs. On the basis of the variational inference principle and generative autoencoder, the group will convergence learning is carried out on the UAV, and the coordinated rounding up is realized on the basis of the Apollonius circle so that the UAV cluster emerges a more intelligent rounding up effect. The simulation results show the effectiveness and intelligence of the designed rounding up strategy.
- cooperative rounding up /
- unity of group will /
- fusion cognition /
- convergent learning /
- Apollonius round

HTML全文

图 1 N个无人机围捕单个目标

Figure 1. N drones rounded up a single target

下载: 全尺寸图片幻灯片

图 2 无人机航向变化示意图

Figure 2. Diagram of course change of UAV

下载: 全尺寸图片幻灯片

图 3 围捕无人机决策静态示意图

Figure 3. Static schematic of a roundup UAV decision making

下载: 全尺寸图片幻灯片

图 4 双回路认知模型示意图

Figure 4. Schematic diagram of double-loop cognitive model

下载: 全尺寸图片幻灯片

图 5 融合认知模型结构示意图

Figure 5. Schematic diagram of fusion cognitive model

下载: 全尺寸图片幻灯片

图 6 统一群体意志统一构造示意图

Figure 6. Schematic diagram of unified structure of group will

下载: 全尺寸图片幻灯片

图 7 用于群体意志趋同学习的生成式自动编码器结构

Figure 7. Generative autoencoder for group will convergence learning

下载: 全尺寸图片幻灯片

图 8 协作认知模块的神经网络结构

Figure 8. Neural network structure of cooperative cognition module

下载: 全尺寸图片幻灯片

图 9 仿真流程

Figure 9. Simulation flow chart

下载: 全尺寸图片幻灯片

图 10 训练实时奖励

Figure 10. Training real-time rewards

下载: 全尺寸图片幻灯片

图 11 实验组围捕过程

Figure 11. Experimental group round up process

下载: 全尺寸图片幻灯片

图 12 对照组围捕过程

Figure 12. Control group round up process

下载: 全尺寸图片幻灯片

表 1 无人机参数设定

Table 1. UAV parameter setting

无人机类型	速度/(km·s^-1)	固定物理防守半径/km
围捕无人机U₁	0.15	3
围捕无人机U₂	0.12	2
围捕无人机U₃	0.12	2
围捕无人机U₄	0.12	2
目标无人机T	0.18

下载: 导出CSV

参考文献(19)

[1]	段海滨, 申燕凯, 赵彦杰, 等. 2019年无人机热点回眸[J]. 科技导报, 2020, 38(1): 170-187. https://www.cnki.com.cn/Article/CJFDTOTAL-KJDB202001018.htm DUAN H B, SHEN Y K, ZHAO Y J, et al. Review of technological hotspots of unmanned aerial vehicle in 2019[J]. Science Technology Review, 2020, 38(1): 170-187(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-KJDB202001018.htm
[2]	段海滨, 张岱峰, 范彦铭, 等. 从狼群智能到无人机集群协同决策[J]. 中国科学: 信息科学, 2019, 49(1): 112-118. https://www.cnki.com.cn/Article/CJFDTOTAL-PZKX201901008.htm DUAN H B, ZHANG D F, FAN Y M, et al. From wolf pack intelligence to UAV swarm cooperative decisionmaking[J]. Scientia Sinica: Informationis, 2019, 49(1): 112-118(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-PZKX201901008.htm
[3]	ALEXOPOULOS A, SCHMIDT T, BADREDDIN E. A pursuit-evasion game between unmanned aerial vehicles[C]//2014 11th International Conference on Informatics in Control, Automation and Robotics (ICINCO). Piscataway: IEEE Press, 2014: 74-81.
[4]	吴子沉, 胡斌. 基于态势认知的无人机集群围捕方法[J]. 北京航空航天大学学报, 2021, 47(2): 424-430. https://www.cnki.com.cn/Article/CJFDTOTAL-BJHK202102029.htm WU Z C, HU B. Swarm rounding up method of UAV based on situation cognition[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47(2): 424-430(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-BJHK202102029.htm
[5]	YASUYUKI S, HIROFUMI O, TADASHI M, et al. Cooperative capture by multi-agent using reinforcement learning application for security patrol systems[C]//2015 10th Asian Control Conference (ASCC). Piscataway: IEEE Press, 2015: 1-6.
[6]	陈志鹏, 李健. 基于动物集群行为的无人机群目标围捕策略[J]. 现代计算机, 2018(2): 11-14. https://www.cnki.com.cn/Article/CJFDTOTAL-XDJS201806004.htm CHEN Z P, LI J. Cluster UAVs hunting strategy based on biological collective behaviors[J]. Modern Computer, 2018(2): 11-14(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XDJS201806004.htm
[7]	蔡云飞, 唐振民, 张浩峰. 基于Cross-EKF定位的多机器人协作围捕策略研究[J]. 控制与决策, 2010, 25(9): 1313-1317. https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201009008.htm CAI Y F, TANG Z M, ZHANG H F. Multi-robots cooperative hunting strategy based on Cross-EKF localization[J]. Control and Decision, 2010, 25(9): 1313-1317(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-KZYC201009008.htm
[8]	黄天云, 陈雪波, 徐望宝, 等. 基于松散偏好规则的群体机器人系统自组织协作围捕[J]. 自动化学报, 2013, 39(1): 57-68. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201301008.htm HUANG T Y, CHEN X B, XU W B, et al. A self-organizing cooperative hunting by swarm robotic systems based on loose-preference rule[J]. Acta Automatica Sinica, 2013, 39(1): 57-68(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201301008.htm
[9]	李瑞珍, 杨惠珍, 萧丛杉. 基于动态围捕点的多机器人协同策略[J]. 控制工程, 2019, 26(3): 510-514. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201903017.htm LI R Z, YANG H Z, XIAO C S. Cooperative hunting strategy for multi-mobile robot systems based on dynamic hunting points[J]. Control Engineering of China, 2019, 26(3): 510-514(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF201903017.htm
[10]	裴惠琴, 陈世明, 孙红伟. 动态环境下可扩展移动机器人群体的围捕控制[J]. 信息与控制, 2009, 38(4): 437-443. https://www.cnki.com.cn/Article/CJFDTOTAL-XXYK200904009.htm PEI H Q, CHEN S M, SUN H W. Pursuit control of scalable swarm system of mobile robots in dynamic environment[J]. Information and Control, 2009, 38(4): 437-443(in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XXYK200904009.htm
[11]	MURO C, ESCOBEDO R, SPECTOR L, et al. Wolf-pack (Canis lupus) hunting strategies emerge from simple rules in computational simulations[J]. Behavioural Processes, 2011, 88(3): 192-197.
[12]	LOWE R, WU Y, TAMAR A, et al. Multi-agent actor-critic for mixed cooperative-competitive environments[EB/OL]. (2017-06-07)[2021-02-14]. https://arxiv.org/abs/1706.02275v1.
[13]	MAO H Y, LIU W L, HAO J Y, et al. Neighborhood cognition consistent multi-agent reinforcement learning[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 7219-7226.
[14]	LIANG L, DENG F, PENG Z H, et al. A differential game for cooperative target defense[J]. Automatica, 2019, 102: 58-71.
[15]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//International Conference on Learning Representations (ICLR 2017), 2017: 1-14.
[16]	IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning, 2015, 37: 448-456.
[17]	WU Z, PAN S, CHEN F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[18]	BLEI D M, KUCUKELBIR A, MCAULIFFE J D. Variational inference: A review for statisticians[J]. Journal of the American Statistical Association, 2017, 112(518): 859-877.
[19]	NAIR A, PONG V, DALAL M, et al. Visual reinforcement learning with imagined goals[EB/OL]. (2018-07-12)[2020-12-04]. https://arxiv.org/abs/1807.04742.