Lane keeping is an important feature for self-driving cars. This paper presents an end-to-end learning approach to obtain the proper steering angle to maintain the car in the lane. The convolutional neural network (CNN) model takes raw image frames as input and outputs the steering angles accordingly. The model is trained and evaluated using the comma.ai dataset, which contains the front view image frames and the steering angle data captured when driving on the road. Unlike the traditional approach that manually decomposes the autonomous driving problem into technical components such as lane detection, path planning and steering control, the end-to-end model can directly steer the vehicle from the front view camera data after training. It learns how to keep in lane from human driving data. Further discussion of this end-to-end approach and its limitation are also provided.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    End-to-end learning for lane keeping of self-driving cars


    Beteiligte:
    Chen, Zhilu (Autor:in) / Huang, Xinming (Autor:in)


    Erscheinungsdatum :

    01.06.2017


    Format / Umfang :

    592387 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    End-To-End Learning for Lane Keeping of Self-Driving Cars

    Chen, Zhilu / Huang, Xinming | British Library Conference Proceedings | 2017


    Lane Line Detection for Self Driving Cars

    Mahajan, Semal / Kriplani, Lokesh / Dhanraj, Vishal Kumar et al. | IEEE | 2022


    Lane Detection for Self-Driving Cars Using AI

    Banerjee, Pallab / Thakur, Kanika / Ambikesh et al. | IEEE | 2023


    A self-learning lane keeping algorithm

    Zhang, Ben / Xu, Chuan / Su, Yan et al. | VDE-Verlag | 2022


    GPU Implementation for Automatic Lane Tracking in Self-Driving Cars

    Yusuf, Ayomide / Alawneh, Shadi | SAE Technical Papers | 2019