In recent years, artificial intelligence technology has performed outstandingly in game confrontation tasks. Based on the characteristics of UAV interception and confrontation process, this paper constructs an interception maneuver strategy learning and training environment based on reinforcement learning methods, including UAV model construction, maneuver decision-making space construction, reward and punishment signal design, enemy UAV strategy design. In order to effectively improve the exploration efficiency of the algorithm, this paper uses expert knowledge as heuristic information and proposes an improved heuristic strategy to avoid initial blind exploration while retaining the optimization ability of the greedy strategy. And completed the simulation verification under the set three-dimensional scene.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    UAV Interception and Confrontation Maneuver Decision-Making Based on Reinforcement Learning


    Contributors:
    Deng, Lin (author) / Wang, Yabo (author) / Yang, Zongyuan (author) / Yang, Yi (author) / Yu, Zhiqiang (author)


    Publication date :

    2023-11-17


    Size :

    920284 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    UAVs Maneuver Decision-Making Method Based on Transfer Reinforcement Learning

    Jindong Zhu / Xiaowei Fu / Zhe Qiao | DOAJ | 2022

    Free access

    Loitering Munition Interception Decision-Making Technology Based on Deep Reinforcement Learning

    Qi, Qingxi / Cai, Zhirong / Sun, Xinke et al. | Springer Verlag | 2025


    Decision-making and confrontation in close-range air combat based on reinforcement learning

    YANG, Mengchao / SHAN, Shengzhe / ZHANG, Weiwei | Elsevier | 2025

    Free access