Path planning is a critical aspect of autonomous driving. Traditional methods have excelled in urban environments but struggle off-road due to unpredictable conditions. This paper introduces a Deep Reinforcement Learning-based off-road path planning approach called PPOAC by training the agent in a low-dimensional simulator built by Occupancy Grid Maps (OGMs). A self-supervised auxiliary task is proposed to help the agent to learn environmental knowledge. Moreover, an adaptive curriculum learning method is introduced to enhance the agent's training efficiency and generalization ability. The agent is trained and evaluated in real-world data, and experimental results demonstrate that it can obtain traversable and safe paths while generalizing effectively to unknown environments.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Reinforcement Learning-Based Off-Road Path Planning via Low-Dimensional Simulation


    Beteiligte:
    Wang, Xu (Autor:in) / Shang, Erke (Autor:in) / Dai, Bin (Autor:in) / Miao, Qiguang (Autor:in) / Nie, Yiming (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.09.2024


    Format / Umfang :

    5314320 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Reinforcement Learning-Based UAV Path Planning Algorithm

    Wang, Kunfu / Hui, Ma / Hou, Jiajun et al. | IEEE | 2024



    Multi-Obstacle Path Planning using Deep Reinforcement Learning

    Morgan, Brandon / Trigg, Lena / Stringer, Alexander et al. | IEEE | 2024


    Unmanned Aerial Vehicles Path Planning Based on Deep Reinforcement Learning

    Wang, Guoqiu / Zheng, Xuanyu / Zhao, Haitong et al. | Springer Verlag | 2019


    Deep Reinforcement Learning-Based Local Path Planning with Memory-Guided

    Wang, Xu / Xu, Xiaobin / Lin, Shiyao et al. | Springer Verlag | 2025