This paper describes an algorithm for making short-term route predictions for vehicle drivers. It uses a simple Markov model to make probabilistic predictions by looking at a driver's just-driven path. The model is trained from the driver's long term trip history from GPS data. We envision applications including driver warnings, anticipatory information delivery, and various automatic vehicle behaviors. The algorithm is based on discrete road segments, whose average length is 237.5 meters. In one instantiation, the algorithm can predict the next road segment with 90% accuracy. We explore variations of the algorithm and find one that is both simple and accurate.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Markov Model for Driver Turn Prediction


    Additional title:

    Sae Technical Papers


    Contributors:
    Krumm, John (author)

    Conference:

    SAE World Congress & Exhibition ; 2008



    Publication date :

    2008-04-14




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    A Markov Model for Driver Turn Prediction

    Krumm, J. / Society of Automotive Engineers | British Library Conference Proceedings | 2008


    A Markov model for driver turn prediction

    Krumm,J. / Microsoft Research,US | Automotive engineering | 2008


    2008-01-0195 A Markov Model for Driver Turn Prediction

    Krumm, J. | British Library Conference Proceedings | 2008


    Markov Switching Model for Driver Behavior Prediction: Use cases on Smartphones

    Zaky, Ahmed B. / Khamis, Mohamed A. / Gomaa, Walid | ArXiv | 2021

    Free access

    Enhanced Gate Driver with Variable Turn On and Turn Off Speeds

    Curuvua, Boris / Xu, Fan / Chen, Lihua | SAE Technical Papers | 2019