With the rapid development of technology, the deployment of modern theater three-dimensional air defense systems is becoming increasingly rigorous. How to control the unmanned aerial vehicle (UAV) to quickly fly out of a high safety penetration trajectory under the threat of a tight ground air defense system is core of the penetration problem. Therefore, this paper proposes a TD3 algorithm based on LSTM target prediction for trajectory control of UAV in complex penetration environments. Firstly, the process of UAV penetration was analyzed and briefly described. Then, models of the UAV and threats were established separately. A target prediction method based on LSTM was designed to address the issue of errors in using the current target state iteration method. Using LSTM to extract and analyze the spatial features of the target during the penetration process to achieve accurate estimation of future situational rewards, and introducing it into the TD3 algorithm. The simulation results show that the TD3 penetration trajectory autonomous control algorithm based on LSTM target prediction is superior to other reinforcement learning algorithms. It can effectively control the trajectory of UAV and avoid ground threats, efficiently reach the vicinity of the target, and has certain application value.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Autonomous Penetration Trajectory Control for Unmanned Aerial Vehicle Based on Reinforcement Learning


    Contributors:
    Liu, Yufei (author) / Yang, Zhen (author) / Chai, Shiyuan (author) / Wang, Xingyu (author) / Zhou, Yin (author) / Zhou, Deyun (author)


    Publication date :

    2024-12-20


    Size :

    1648871 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Autonomous Navigation of Unmanned Aerial Vehicle Using Reinforcement Learning

    Bansal, Payal / Joshi, Jyotsna / Hans, Surender et al. | Wiley | 2024



    Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review

    AlMahamid, Fadi / Grolinger, Katarina | ArXiv | 2022

    Free access

    SYSTEM FOR AUTONOMOUS UNMANNED AERIAL VEHICLE TRAJECTORY CONFLICT RESOLUTION

    TAM WILLIAM / PRAKASH SAHITHYA M / LI MAX Z et al. | European Patent Office | 2020

    Free access