Put forward a new UAV motion and trajectory planning method for alpine forest environment, the method using agent reinforcement learning, from random initial state such as UAV position, speed and direction, using reward, state representation function, deep training deterministic policy gradient agent framework, considering the kinematics and dynamic constraints, to achieve any target state, realize effective optimization of UAV trajectory planning. The studied agent reinforcement learning agent is not only able to handle continuous state space, but also to adapt to UAV acceleration and steering angles for continuous action, and verifies the effectiveness of the method in realizing UAV trajectory planning in a simulated environment.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on Unmanned Aerial Vehicle Trajectory Planning Based on Agent Reinforcement Learning in Alpine Forest Environment


    Beteiligte:
    Liu, Shaogang (Autor:in) / Wu, Ming (Autor:in) / Hong, Guihua (Autor:in) / Cao, Lizhu (Autor:in) / Yang, Min (Autor:in) / Li, Hongli (Autor:in)


    Erscheinungsdatum :

    01.09.2022


    Format / Umfang :

    257906 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch