With the rapid development of drone technology, the application of drones in military and civilian fields is becoming increasingly widespread. However, accurately controlling the flight attitude of drones during takeoff on a moving platform has always been a challenging problem. This paper takes a vehicle-mounted UAV as an example and proposes a drone flight control technique based on reinforcement learning. Introducing the Proximal Policy Optimization (PPO) algorithm to improve the control method based on the traditional PID control aims to enhance the accuracy and performance of attitude control. Experimental results show that this algorithm can effectively enhance the attitude stability and control accuracy of drones during takeoff on a moving platform, enabling the drone to maintain posture stability during the takeoff process at a speed of 20 km/h.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on the optimization of flight control technology for UAVs based on reinforcement learning on moving platform


    Beteiligte:
    Yu, Xunfei (Autor:in) / Hu, Weijun (Autor:in) / Quan, Jiale (Autor:in) / Wang, Ruichang (Autor:in)


    Erscheinungsdatum :

    2023-12-13


    Format / Umfang :

    4929703 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Validation of Reliability-based Flight Control Optimization for UAVs

    Liscouët, Jonathan / Uwantare, Ishimwe / Remoundos, Andrew et al. | AIAA | 2024


    Reinforcement Learning Based Coverage Planning for UAVs Fleets

    Bromo, Cosimo / Godio, Simone / Guglieri, Giorgio | TIBKAT | 2023


    Reinforcement Learning based Coverage Planning for UAVs Fleets

    Bromo, Cosimo / Godio, Simone / Guglieri, Giorgio | AIAA | 2023


    Deep Reinforcement Learning Attitude Control of Fixed-Wing UAVs

    Zhen, Yan / Hao, Mingrui / Sun, Wendi | IEEE | 2020


    Deep reinforcement learning as control method for autonomous UAVs

    Kersandt, Kjell | BASE | 2018

    Freier Zugriff