Real-time road estimation is important for dynamic path planning of autonomous driving, especially when construction sites or accidents occur along the road. Among the existing practices, main pain points are strongly dependent on lane markings and brightness. In addition, roads with a variable number of lanes are difficult to predict. To address these issues, we fuse the data sampled from camera, lidar, radar and predict the lanes 90m ahead of the ego vehicle in the top-view perspective by using a deep neural network. Our method is evaluated on real urban and highway scenes under good and bad weather conditions at different daytime, the results showed that our approach can handle roads with a variable number of lanes or roads with small T-intersections. Furthermore, the method can also deal with incomplete or missing lane markings at 166.66 fps.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-time long-range road estimation in unknown environments


    Contributors:
    Yuan, Jenny (author) / Lu, Gary (author) / Friedrich, Philipp (author) / Xu, Yixin (author)


    Publication date :

    2020-10-19


    Size :

    2364677 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ROAD COURSE ESTIMATION IN UNKNOWN, STRUCTURED ENVIRONMENTS

    Tanzmeister, G. / Friedl, M. / Lawitzky, A. et al. | British Library Conference Proceedings | 2013


    Road course estimation in unknown, structured environments

    Tanzmeister, Georg / Friedl, Martin / Lawitzky, Andreas et al. | IEEE | 2013


    Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans

    Lu, F. / Milios, E. E. / Institute of Electrical and Electronics Engineers; Computer Society | British Library Conference Proceedings | 1994



    Real-time estimation of the road bank and grade angles with unknown input observers

    Hashemi, Ehsan / Zarringhalam, Reza / Khajepour, Amir et al. | Taylor & Francis Verlag | 2017