In pursuit of autonomous vehicles, achieving human-like driving behavior is vital. This study introduces adaptive autopilot (AA), a unique framework utilizing constrained-deep reinforcement learning (C-DRL). AA aims to safely emulate human driving to reduce the necessity for driver intervention. Focusing on the car-following scenario, the process involves (i) extracting data from the highD natural driving study and categorizing it into three driving styles using a rule-based classifier; (ii) employing deep neural network (DNN) regressors to predict human-like acceleration across styles; and (iii) using C-DRL, specifically the soft actor-critic Lagrangian technique, to learn human-like safe driving policies. Results indicate effectiveness in each step, with the rule-based classifier distinguishing driving styles, the regressor model accurately predicting acceleration, outperforming traditional car-following models, and C-DRL agents learning optimal policies for humanlike driving across styles.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Adaptive Autopilot: Constrained Drl for Diverse Driving Behaviors




    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    1436310 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Adaptive Autopilot: Constrained DRL for Diverse Driving Behaviors

    Selvaraj, Dinesh Cyril / Vitale, Christian / Panayiotou, Tania et al. | ArXiv | 2024

    Freier Zugriff

    LQG adaptive ship autopilot

    Katebi, M.R. / Byrne, J.C. | Tema Archiv | 1988


    Adaptive Autopilot Design for Unmanned Airship

    Kim, B. M. / Kim, B. S. / Nanjing hang kong hang tian da xue | British Library Conference Proceedings | 2004


    Expendable Launch Vehicle Adaptive Autopilot Design

    Plaisted, C. / Leonessa, A. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 2008


    Batch Adaptive Yaw-Roll Controllable Autopilot

    Park, J. S. / Ohtsu, K. / International Federation of Automatic Control | British Library Conference Proceedings | 1999