In this paper, we develop a motion planner for on-road autonomous swerve maneuvers that is capable of learning passengers' individual driving styles. It uses a hybrid planning approach that combines sampling-based graph search and vehicle model-based evaluation to obtain a smooth trajectory plan. To automate the parameter tuning process, as well as to reflect individual driving styles, we further adapt inverse reinforcement learning techniques to distill human driving patterns from maneuver demonstrations collected from different individuals. We found that the proposed swerve planner and its learning routine can approximate a good variety of maneuver demonstrations. However, due to the underlying stochastic nature of human driving, more data are needed in order to obtain a more generative swerve model.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Human-like planning of swerve maneuvers for autonomous vehicles


    Contributors:
    Gu, Tianyu (author) / Dolan, John M. (author) / Lee, Jin-Woo (author)


    Publication date :

    2016-06-01


    Size :

    1059961 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    HUMAN-LIKE PLANNING OF SWERVE MANEUVERS FOR AUTONOMOUS VEHICLES

    Gu, Tianyu / Dolan, John M. / Lee, Jin-Woo | British Library Conference Proceedings | 2016


    Safe Swerve Maneuvers for Autonomous Driving

    de Iaco, Ryan / Smith, Stephen L. / Czarnecki, Krzysztof | IEEE | 2020


    SWERVE-DRIVE ROBOT

    HALLER KEVIN NICOLAS / MEYERS WILLIAM MICHAEL / BIERSACK JOSEPH MICHAEL et al. | European Patent Office | 2024

    Free access

    Swerve Drive Autonomous Robot for Tiles Thermographic Inspection

    Rodríguez, Humberto / Pérez, Víctor / Echeverría, Octavio | Springer Verlag | 2024


    Differential Swerve Drive

    RABSON GIDEON LOUIS | European Patent Office | 2023

    Free access