This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes convolutional neural networks (CNN) to act as a policy that is driving a vehicle. The policy is successfully learned via imitation learning using real-world data collected from human drivers and is evaluated in closed-loop simulated environments, demonstrating good driving behaviour and a robustness for domain changes. Evaluation is based on two proposed performance metrics measuring how well the vehicle is positioned in a lane and the smoothness of the driven trajectory.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Imitation learning for vision-based lane keeping assistance


    Beteiligte:


    Erscheinungsdatum :

    2017-10-01


    Format / Umfang :

    241850 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LANE KEEPING ASSISTANCE DEVICE AND LANE KEEPING ASSISTANCE METHOD

    SUZUKI TERUHIKO | Europäisches Patentamt | 2018

    Freier Zugriff

    MACHINE VISION-BASED LANE KEEPING ASSISTANCE SYSTEM AND METHOD

    LI ZHENFENG / CHENG TAO / WANG XIANG LONG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Lane keeping assistance system

    RUNGE HARTMUT / KLARNER ROBERT | Europäisches Patentamt | 2020

    Freier Zugriff

    LANE KEEPING ASSISTANCE DEVICE

    TATSUKAWA JUNPEI | Europäisches Patentamt | 2016

    Freier Zugriff

    LANE KEEPING ASSISTANCE DEVICE

    TATSUKAWA JUNPEI | Europäisches Patentamt | 2016

    Freier Zugriff