Autonomous driving is one of the current cutting edge technologies. For autonomous cars, their driving actions and trajectories should not only achieve autonomy and safety, but also obey human drivers’ behavior patterns, when sharing the roads with other human drivers on the highway. Traditional methods, though robust and interpretable, demands much human labor in engineering the complex mapping from current driving situation to vehicle’s future control. For newly developed deep-learning methods, though they can automatically learn such complex mapping from data and demands fewer humans’ engineering, they mostly act like black-box, and are less interpretable. We proposed a new combined method based on inverse reinforcement learning to harness the advantages of both. Experimental validations on lane-change prediction and human-like trajectory planning show that the proposed method approximates the state-of-the-art performance in modeling human trajectories, and is both interpretable and data-driven.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Human-like Highway Trajectory Modeling based on Inverse Reinforcement Learning


    Beteiligte:
    Sun, Ruoyu (Autor:in) / Hu, Shaochi (Autor:in) / Zhao, Huijing (Autor:in) / Moze, Mathieu (Autor:in) / Aioun, Francois (Autor:in) / Guillemard, Franck (Autor:in)


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    1341775 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    IRLSOT: Inverse reinforcement learning for scene‐oriented trajectory prediction

    He, Caizhen / Chen, Lanping / Xu, Liming et al. | Wiley | 2022

    Freier Zugriff

    Unmanned vehicle trajectory prediction method based on fuzzy inverse reinforcement learning

    LIU JING / HAN YONG / HOU RONGBIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff


    Predicting Driver Behavior on the Highway with Multi-Agent Adversarial Inverse Reinforcement Learning

    Radtke, Henrik / Bey, Henrik / Sackmann, Moritz et al. | IEEE | 2023