We investigate a new approach towards maneuver prediction that is based on personalization and incremental learning. The prediction accuracy is continuously improved by incorporating only the individual driving history. The study is based on a collection of commuting drivers who recorded their daily routes with a standard smart phone and GPS receiver. Prediction target is the expected maneuver on the next intersection with three classes: stop, turn, or go straight. We show that a personalized prediction based on at least one experience of a certain intersection already improves the prediction performance over an average prediction model trained on all test driver commute routes. This performance gain increases further with more personal training data.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Personalized maneuver prediction at intersections


    Beteiligte:
    Losing, Viktor (Autor:in) / Hammer, Barbara (Autor:in) / Wersing, Heiko (Autor:in)


    Erscheinungsdatum :

    01.10.2017


    Format / Umfang :

    398652 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Personalized Maneuver Prediction at Intersections

    Losing, Viktor / Hammer, Barbara / Wersing, Heiko | BASE | 2017

    Freier Zugriff

    PERSONALIZED VEHICLE LANE CHANGE MANEUVER PREDICTION

    WANG ZIRAN / HAN KYUNGTAE / GUPTA ROHIT et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Maneuver prediction at intersections using cost-to-go gradients

    von Eichhorn, Andreas / Werling, Moritz / Zahn, Peter et al. | IEEE | 2013


    Infrastructure-based vehicle maneuver estimation at urban intersections

    Schendzielorz, T. / Mathias, P. / Busch, F. | IEEE | 2013