In this paper, we propose a novel autonomous lane keeping system (LKS) based on a road lane model using a deep convolutional neural network (DCNN). The DCNN was trained by a dataset which consists of reliable road coefficients from the vision system mounted on the test vehicle driven by a human, and images captured by another camera. Then the proposed system was validated with a dataset which was not used for training the DCNN. We confirmed that there were good agreements between the steering wheel angles by the human driver and those given by the proposed LKS. Furthermore, we observed that the proposed system can provide the road coefficients necessary for implementing the LKS even either when there is no lane marker and/or when the vehicle is maneuvered for turning at an intersection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Autonomous Lane Keeping Control System Based on Road Lane Model Using Deep Convolutional Neural Networks *


    Contributors:


    Publication date :

    2019-10-01


    Size :

    1159562 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lane keeping method, lane keeping control device and lane keeping system

    MORITA MITSUHIKO / SHAO JUNQIAO | European Patent Office | 2022

    Free access


    Lane keeping for autonomous vehicles

    HARDA PETER / WESTLUND MATHIAS | European Patent Office | 2021

    Free access

    LANE KEEPING FOR AUTONOMOUS VEHICLES

    HARDÅ PETER / WESTLUND MATHIAS | European Patent Office | 2021

    Free access

    Lane keeping controller, vehicle system and lane keeping control method

    BAEK WOON-TAE | European Patent Office | 2022

    Free access