The detection of lane layout in the surroundings of the ego-vehicle is a key issue for modern ADAS and autonomous driving. Most modern systems rely on annotated spatial maps to provide lane information. However, these maps are not available everywhere, and thus have to be often supported by direct detection systems (e.g. cameras, lasers). Such systems detect lane boundaries by directly observing lane markings or sensing curbstones and pavements. However, well defined boundaries are not always there, or they can be difficult to detect, especially in rural or inner city roads. Furthermore, other traffic participants in the surroundings can significantly limit the field of view of the ego-vehicle. In order to help lane detection in this kind of scenario, indirect cues, such as the behavior of the other vehicles, can be a useful resource. In this paper we propose a grid-based approach, that works on a road terrain representation and assigns a lane and a driving direction to each patch of road. Our approach segments the road terrain into multiple lanes based on geometrical considerations and prior knowledge, and then assigns a driving direction to each lane, taking into account the observed and predicted motion of the other vehicles in the scene. The road terrain is provided by a system we proposed in a previous work, which combines direct and indirect cues to build a probabilistic road representation grid. This new approach constitutes an additional layer to our representation, providing more awareness about the road regulations to motion control systems and allowing them to plan safer trajectories.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Enriching a spatial road representation with lanes and driving directions


    Contributors:


    Publication date :

    2016-11-01


    Size :

    984899 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Road curb and lanes detection for autonomous driving on urban scenarios

    Fernandez, C. / Izquierdo, R. / Llorca, D. F. et al. | IEEE | 2014


    Method of representing road lanes

    WEILAND MICHAEL / NYCZAK GREGORY / MCDONOUGH WILLIAM et al. | European Patent Office | 2017

    Free access

    Method of representing road lanes

    WEILAND MICHAEL / NYCZAK GREGORY / MCDONOUGH WILLIAM et al. | European Patent Office | 2019

    Free access

    Method of representing road lanes

    WEILAND MICHAEL / NYCZAK GREGORY / MCDONOUGH WILLIAM et al. | European Patent Office | 2016

    Free access