Maneuvering Decision-making Method of UAV Based on Approximate Dynamic Programming
-
摘要: 针对空战机动决策时出现的“维数爆炸”问题，该文提出一种基于近似动态规划的群智能空战机动决策方法。首先建立无人机空气动力学模型和空战态势优势指标函数。其次，利用近似动态规划的思想，将空战过程按时间域划分为多个规划时域，在每个规划时域内，提出人工势场引导下的改进蚁狮优化算法快速逼近最优控制量，有效裁减搜索空间。通过与专家系统法进行仿真对比，表明所提方法解决高动态、实时性强的无人机机动决策问题的有效性和可行性。Abstract: To solve the problem of dimension disaster when solving air combat maneuvering decision-making by dynamic programming, a swarm intelligence maneuvering decision-making method based on the approximate dynamic programming is proposed. Firstly, the Unmanned Aerial Vehicle (UAV) dynamic model and advantage functions of situation are established. On this basis, air combat process is divided into several stages according to dynamic programming thought. In order to reduce the search space, an Artificial Potential Field (APF) Guiding Ant Lion Optimizer (ALO) approximate optimal control amount is adopted in each programming stage. Finally, by comparing expert system, the experiment result indicates that the high dynamic and real-time air combat maneuvering decision can be solved by the proposed method effectively.
-
表 1 仿真实验初始参数
类型 x(m) y(m) z(m) v(m/s) $\theta $(°) $\psi $(°) 优势态势 无人机 5000 15000 5000 300 15 6 敌机 8000 10000 5000 270 10 20 劣势态势 无人机 6000 1000 6000 300 22 –15 敌机 2000 10000 6000 300 –9 12 
下载: 导出CSV
-
VIRTANEN K and RAIVIO T. Modeling pilot’s sequential maneuvering decisions by a multistage influence diagram[J]. Journal of Guidance, Control, and Dynamics, 2012, 27(4): 665–677 doi: 10.2514/1.11167 CASBEER D W, GARCIA E, and PACHTER M. The target differential game with two defenders[J]. Journal of Intelligent and Robotic Systems, 2017, 89: 87–106 doi: 10.1007/s10846-017-0563-0 SEO J and KIM Y. Differential geometry based collision avoidance guidance for multiple UAVs[J]. IFAC Proceedings Volumes, 2013, 46(19): 113–118 doi: 10.3182/20130902-5-DE-2040.00061 傅莉, 王晓光. 无人战机近距空战微分对策建模研究[J]. 兵工学报, 2012, 10(10): 1210–1216FU Li and WANG Xiaoguang. Research on close air combat modeling of differential games for unmanned combat air vehicles[J].Acta Armamentarii, 2012, 10(10): 1210–1216 傅莉, 谢怀福. 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 doi: 10.13700/j.bn.1001-5965.2014.0756FU Li and XIE Huaifu. 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 doi: 10.13700/j.bn.1001-5965.2014.0756 XIAO Lizhi, SUN Dexiang, and LIU Yuwei. A combined method based on expert system and BP neural network for UAV systems fault diagnosis[C]. 2010 International Conference on Artificial Intelligence and Computational Intelligence, Piscataway, USA, 2010: 3–6. doi: 10.1109/AICI.2010.242. 张涛, 于雷. 基于混合算法的空战机动决策[J]. 系统工程与电子技术, 2013, 35(7): 1445–1450ZHANG Tao and YU Lei. Decision-making for air combat maneuvering based on hybrid algorithm[J]. Systems Engineering and Electronics, 2013, 35(7): 1445–1450 NICHOLAS E, DAVID C, COREY S, et al. Genetic fuzzy based artificial intelligence for unmanned combat aerial vehicle control in simulated air combat missions[J]. Journal of Defense Management, 2016, 6(1): 1–7 doi: 10.4172/2167-0374.1000144 周思羽, 吴文海, 孔繁峨, 等. 基于随机决策准则的改进多级影响图机动决策方法[J]. 北京理工大学学报, 2013, 33(3): 296–301 doi: 10.3969/j.issn.1001-0645.2013.03.017ZHOU Siyu, WU Wenhai, and KONG Fane, et al. Improved multistage influence diagram maneuvering decision method based on stochastic decision criterions[J]. Transaction of Beijing Institute of Technology, 2013, 33(3): 296–301 doi: 10.3969/j.issn.1001-0645.2013.03.017 KAI V and RAIVIO T. An influence diagram approach to one on one air combat[J]. International Symposium on Differential Games and Applications, 2002, 14(26): 8–11 doi: 10.3182/2002-0902-5-2300.00061 MCGREW J S and HOW J P. Air-combat strategy using approximate dynamic programming[J]. Journal of Guidance, Control, and Dynamics, 2010, 33(5): 1641–1654 doi: 10.2514/1.46815 MESMER B L and BLOEBAUM C L. Modeling decision and game theory based pedestrian velocity vector decisions with interacting individuals[J]. Safety Science, 2016, 87: 116–130 doi: 10.1016/j.ssci.2016.03.018 BREITNER M H, PESCH H J, and GRIMM W. Complex differential games of pursuit- evasion type with stateconstraints, part2: Numerical computation of optimal open-loop strategies[J]. Journal of Optimization Theory and Applications, 1993, 78(3): 419–441 doi: 10.1007/BF00939876 DIETTERICH T G. Hierarchical reinforcement learning with the MAXQ value function decomposition[J]. Journal of Artificial Intelligence Research, 1999, 13(1): 227–303 doi: 10.3685/CS1999-03 ANDREY P and TAL S. Cooperative differential games strategies for active aircraft protection from a homing missile[J]. Journal of Guidance, Control, and Dynamics, 2015, 34(3): 761–773 doi: 10.2514/1.51611 张煜, 王楠, 陈璟. 空地多目标攻击中制导炸弹可投放区计算研究[J]. 兵工学报, 2011, 32(12): 1474–1480ZHANG Yu, WANG Nan, and CHEN Jing. Research on launch acceptable region for guided boms in air to ground multi target attack[J]. Acta Armamentarii, 2011, 32(12): 1474–1480 MIRJALILI S. The ant lion optimizer[J]. Advance Engineering Software, 2015, 83(C): 80–98 doi: 10.1016/j.advengsoft.2015.01.010 -
下载:
图(3) / 表(1)
计量
- 文章访问数: 2027
- HTML全文浏览量: 889
- PDF下载量: 114
- 被引次数: 0
