This paper proposes an improved deep reinforcement learning algorithm, which uses meta-learning pre-training and a new exploration mechanism to accelerate the convergence in large-scale trajectory planning problems. The algorithm can eliminate neural network non-convergence caused by the excessive planning range and has high portability in different flight scenarios.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    The Trajectory Planning Method for UAV in Large Airspace Based on Deep Reinforcement Learning


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Wu, Meiping (Herausgeber:in) / Niu, Yifeng (Herausgeber:in) / Gu, Mancang (Herausgeber:in) / Cheng, Jin (Herausgeber:in) / Hu, Weijun (Autor:in) / Quan, Jiale (Autor:in) / Ma, Xianlong (Autor:in) / Gao, Zhiqiang (Autor:in)

    Kongress:

    International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021



    Erscheinungsdatum :

    18.03.2022


    Format / Umfang :

    10 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    The Trajectory Planning Method for UAV in Large Airspace Based on Deep Reinforcement Learning

    Hu, Weijun / Quan, Jiale / Ma, Xianlong et al. | British Library Conference Proceedings | 2022



    Crossroad lighthouse trajectory planning method based on deep reinforcement learning

    LI BOQI / ZHANG WEIWEI / CHEN JIANG et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Aircraft Trajectory Prediction in Terminal Airspace Through Deep Learning Approaches

    Zhang, Wenxin / Payan, Alexia / Mavris, Dimitri | AIAA | 2024


    Smooth Trajectory Planning for MAVs with Airspace Restrictions

    Upadhyay, Saurabh / Ratnoo, Ashwini | AIAA | 2016