计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220700031-7.doi: 10.11896/jsjkx.220700031
蔺向阳1, 邢清华2, 邢怀玺2
LIN Xiangyang1, XING Qinghua2, XING Huaixi2
摘要： 基于未来现代化作战需求,构建作战想定,研究在此想定条件下,使用强化学习解决关于红蓝双方无人机编队空中拦截任务的多目标智能决策问题。根据作战模式和应用需求,选择多智能体确定性梯度算法,并对算法原理进行简要介绍;按照想定,编程搭建了完备的模拟作战训练平台;设计智能体网络模型、网络参数和训练方法;经过训练,初步达到预期效果。实验证明了所选用算法能够有效地解决该类问题,不仅为该类问题的现实应用提供了技术支撑,也为更复杂作战场景和作战任务条件下智能决策的研究提供了理论基础和实验参考。
中图分类号:
| [1]ZHENG Q,WU H,LIANG R P,et al.Intelligent warfare and itsdemand for intelligent command and control technology[J].Fire Control & Command Control,2022,47(2):1-6. [2]JIANG G S,HAN Z Q,WANG F.Analysis of the application status and development prospect of foreign military artificial intelligence[C]//Unmanned Systems Summit Forum 2021(USS 2021).2021. [3]SUN Q,ZHANG B C.Russia:Prioritizing AI research and development[J].Prosecutorial View,2021(24):56-57. [4]FU X,YE Y K,ZHANG P,et al.Research on Characteristics of air Combat capability for military intelligence[J].Winged Missiles Journal,2021(9):73-79. [5]WANG C,LI S,JIANG H B,et al.Study on intelligent battlefield Situation Estimation of air defense and missile defense[J].Fire Control & Command Control,2020,45(3):7-13. [6]LIN X Y,XING Q H,LIU F X.Research on Optimization of Combat Force for Key Air Defense Model[J].Systems Engineering and Electronics,2022,44(3):921-928. [7]FANG X,ZENG B,SONG X X,et al.Warship air threat behavior modeling based on deep reinforcement learning[J].Modern Defense Technology,2020,48(5):59-66. [8]LIU Y J,ZHANG Y.Intelligent Thinking of Naval Gun Weapons[J].Armory Automation,2022,41(3):21-24. [9]LI G Y,KUANG S Y,JIANG G,et al.Discussion on the development path of intelligent Electronic warfare equipment[J].Journal of China Academy of Electronics.2022,17(1):7-11. [10]HUANG W,HE X Z,WANG B X.Application of artificial intelligence technology in Army electronic countermeasures equipment[J].Defense Science and Technology,2022,43(1):26-31. [11]ZHAO W,YE J,WANG B.Intelligent Command Decision and control based on artificial intelligence[J].Information Security and Communication Confidentiality,2022(2):2-8. [12]DING Z L,LIU G L,XIE Y,et al.Dynamic target assignment algorithm based on reinforcement learning and Neural network[J].Electronic Design Engineering,2020,28(13):54-60. [13]DONG K S,HU W B,SHEN Y M,et al.Intelligent Development of Unmanned Aerial Combat Equipment of American Army and its Enlightenment[J].Modern Defense Technology,2022,50(4):28-37. [14]ZHENG K Y.Research on UAV Track Planning Algorithm Based on Intelligent Cognition[D].Harbin:Harbin Engineering University,2021. [15]LI B,YUE K Q,GAN Z G,et al.Multi-uav cooperative mission Decision making based on MADDPG[J].Journal of Astronautics,2021,42(6):757-765. [16]GALAN J,CARRASCO R,LATORRE A.Military Applications of Machine Learning:A Bibliometric Perspective[J].Mathematics,2022,10(9):1397. [17]SHARMA P,SARMA K K,MASTORAKIS N E.Artificial Intelligence Aided Electronic Warfare Systems-Recent Trends and Evolving Applications[J].IEEE Access,2020,8(99):1. [18]LEI L.Automatic driving technology using artificial intelligence[J].Agro Food Industry Hi Tech,2017,28(1):570-574. [19]HODICK J,PROCHÁZKA D,BAXA F,et al.Computer Assisted Wargame for Military Capability-Based Planning[J].Entropy,2020,22(8):861. [20]LOWE R,WU Y,TAMAR A,et al.Multi-Agent Actor-Critic forMixed Cooperative-Competitive Environments[J].arXiv:1706.02275,2017. [21]LILLICRAP T P,HUNT J J,PRITZEL A,et al.Continuous control with deep reinforcement learning[J].arXiv:1509.02971,2015. [22]DEGRIS T,WHITE M,SUTTON R S.Off-Policy Actor-Critic[J].arXiv:1205.4839,2012. [23]SUTTON R S,MCALLESTER D,SINGH S,et al.Policy Gradient Methods for Reinforcement Learning with Function Approximation[J].Submitted to Advances in Neural Information Processing Systems,1999,12. [24]VOLODYMYR M,KORAY K,DAVID S,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533. [25]LIN X,XING Q,LIU F.Choice of discount rate in reinforcementlearning with long-delay rewards[J].Systems Engineering and Electronics,2022,33(2):12. |
|
||
首页