A method is for predicting movement of at least one traffic-related object based on observations of the surroundings of the object. The method includes mapping an observation of the surroundings at a first time by a trained encoder network to a representation with reduced dimensionality. The method also includes, based on a first action performed by the object at the first time and the representation, using at least one trained prediction network to determine a first representation prediction of the representation to which a future observation is likely to be mapped by the trained encoder network at a first future time, and/or determine a first action prediction of a second action that the object is likely to perform at the first future time. The method also includes determining a first dynamic state prediction for a dynamic state of the object at the first future time.


    Access

    Download


    Export, share and cite



    Title :

    Movement Prediction for Road Users


    Contributors:
    JANJOS FARIS (author) / DOLGOV MAXIM (author)

    Publication date :

    2024-08-22


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06V / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS




    PREDICTION OF NEAR-FUTURE BEHAVIOR OF ROAD USERS

    LIU DAPENG / FU JUNSHENG | European Patent Office | 2023

    Free access

    PREDICTION OF NEAR-FUTURE BEHAVIOR OF ROAD USERS

    LIU DAPENG / FU JUNSHENG | European Patent Office | 2023

    Free access

    ROAD USERS AND ROAD DESIGN

    Rothengatter, J. A. / Transport Research Laboratory | British Library Conference Proceedings | 1999


    SLHP: Short-/Long-term Hybrid Prediction for Road Users

    Takei, Shoichi / Tanaka, Shinya / Yamaguchi, Shotaro et al. | IEEE | 2020