In this paper a concept for a Hybrid Environment Model is proposed which aims at fulfilling the requirements of future ADAS functions. As model based tracking is not sufficient to provide innovative ADAS functions and automated driving with sufficient information about the static environment of a vehicle. Therefore, new solutions for environment modeling have to be established. The proposed model solves the requirements in a scalable and efficient way by adding an Occupancy Grid to the model-based tracking. The resulting hybrid environment model forms a sensor independent and extensible data basis which also is an abstraction layer between sensorics and functions and fosters modularization and re-usability. One reason often stated against the Occupancy Grid is its high demand for CPU, memory and bandwidth resources. It was shown that using data compression by a reduced quantization, run length encoding or a quad tree the resource demand can be reduced enough to make a deployment on standard automotive hardware feasible. Ongoing research is a further investigation of the compression methods applied. Additionally, for future assistance and automation in urban scenarios, the environmental model is complemented by a part which can represent typical urban information like curbstones or traffic lights in an efficient manner.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An efficient environmental model for automated driving


    Beteiligte:
    Grewe, Ralph (Autor:in) / Hohm, Andree (Autor:in) / Lueke, Stefan (Autor:in)


    Erscheinungsdatum :

    2013


    Format / Umfang :

    14 Seiten, Bilder, 28 Quellen



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch