This research introduces an advanced flight control system for optimizing autonomous aircraft performance, leveraging deep reinforcement learning (DRL) to address the complexities of nonlinear flight dynamics. Using a six-degree-of-freedom (6-DoF) rigid aircraft flight dynamics model, we develop a Deep Deterministic Policy Gradient (DDPG) controller tailored for waypoint navigation and attitude stabilization tasks. A custom reward framework and extensive hyperparameter tuning enable effective training within a high-fidelity MATLAB/Simulink environment, achieving high rewards and precise control. Although computationally intensive, the simulations demonstrate robust performance across diverse flight conditions, with potential for real-world applications and future extensions to multi-agent scenarios.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement Learning Based Optimization of Autonomous Aircraft Performance


    Beteiligte:
    Sari, Metin (Autor:in) / Caliskan, Fikret (Autor:in)


    Erscheinungsdatum :

    24.02.2025


    Format / Umfang :

    1157028 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Reinforcement Learning for Autonomous Aircraft Avoidance

    Keong, Choo Wai / Shin, Hyo-Sang / Tsourdos, Antonios | IEEE | 2019


    DUAL AGENT REINFORCEMENT LEARNING BASED SYSTEM FOR AUTONOMOUS OPERATION OF AIRCRAFT

    KUMAR PRABHAT | Europäisches Patentamt | 2023

    Freier Zugriff

    Dual agent reinforcement learning based system for autonomous operation of aircraft

    KUMAR PRABHAT | Europäisches Patentamt | 2025

    Freier Zugriff


    Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning

    Julian, Kyle D. / Kochenderfer, Mykel J. | ArXiv | 2018

    Freier Zugriff