航空学报 > 2025, Vol. 46 Issue (S1): 732215-732215   doi: 10.7527/S1000-6893.2025.32215

第二届空天前沿大会/第二十七届中国科协年会优秀论文

非完备信息下无人机近距博弈自主决策

周攀1,2, 李霓1, 黄江涛2(), 杨青林2,3, 廉云霄1   

  1. 1.西北工业大学 航空学院,西安 710072
    2.中国空气动力研究与发展中心 空天技术研究所,绵阳 621000
    3.北京航空航天大学 航空科学与工程学院,北京 100191
  • 收稿日期:2025-05-09 修回日期:2025-05-12 接受日期:2025-05-18 出版日期:2025-06-11 发布日期:2025-10-30
  • 通讯作者: 黄江涛 E-mail:hjtcyfx@163.com
  • 基金资助:
    国家自然科学基金(52372398)

Autonomous decision-making in close-range game under imperfect information for unmanned aerial vehicles

Pan ZHOU1,2, Ni LI1, Jiangtao HUANG2(), Qinglin YANG2,3, Yunxiao LIAN1   

  1. 1.School of Aeronautics,Northwestern Polytechnical University,Xi’an 710072,China
    2.Institute of Space Technology,China Aerodynamics Research and Development Center,Mianyang 621000,China
    3.School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China
  • Received:2025-05-09 Revised:2025-05-12 Accepted:2025-05-18 Online:2025-06-11 Published:2025-10-30
  • Contact: Jiangtao HUANG E-mail:hjtcyfx@163.com
  • Supported by:
    National Natural Science Foundation of China(52372398)

摘要:

随着计算机科学、自动控制理论、飞行器设计等学科的融合发展,无人机近距博弈自主决策成为当前无人机领域关键性技术难题之一。针对非完备信息下的无人机近距博弈自主决策问题,提出了一种基于预训练Efficientero算法的无人机近距博弈自主决策方法。首先,实现了一种基于四元数理论的无人机三自由度动力学模型求解方法,并根据该方法建立了三自由度无人机近距博弈环境模型。其次,基于深度神经网络建立了面向多维连续状态输入、多维离散动作输出的无人机近距博弈自主决策模型。在此基础上,提出了一种基于预训练EfficientZero算法的近距博弈决策模型优化方法。然后,建立了非完备信息下目标机动轨迹预测模型。最后,开展了无人机近距博弈仿真试验。

关键词: 无人机, 非完备信息, 自主决策, 态势预测, 人工智能

Abstract:

With the development of computer science, automatic control theory, aircraft design and other disciplines, autonomous decision-making of Unmanned Aerial Vehicle (UAV) in close-range game has become one of the key technical problems in the field of UAV. Aimed at the autonomous decision-making problem of UAV in close-range game under incomplete information, this paper proposes an autonomous decision-making method of UAV in close-range game based on pre-trained EfficientZero algorithm. Firstly, a three-degree-of-freedom dynamic model of UAV based on quaternion theory is implemented, and a three-degree-of-freedom close-range game environment model of UAV is established according to this method. Secondly, based on deep neural network, an autonomous decision-making model of UAV close-range game for multi-dimensional continuous state input and multi-dimensional discrete action output is established. On this basis, an optimization method of close-range game decision model based on pre-trained EfficientZero algorithm is proposed. Then, the prediction model of target maneuvering trajectory under incomplete information is established. Finally, the close-range game simulation experiment of UAV is carried out.

Key words: unmanned aerial vehicles, imperfect information, autonomous decision-making, situation prediction, artificial intelligence

中图分类号: