Representing relevant information of a traffic scene and understanding its environment is crucial for the success of autonomous driving. Modeling the surrounding of an autonomous car using semantic relations, i.e., how different traffic participants relate in the context of traffic rule based behaviors, is hardly been considered in previous work. This stems from the fact that these relations are hard to extract from real-world traffic scenes. In this work, we model traffic scenes in a form of spatial semantic scene graphs for various different predictions about the traffic participants, e.g., acceleration and deceleration. Our learning and inference approach uses Graph Neural Networks (GNNs) and shows that incorporating explicit information about the spatial semantic relations between traffic participants improves the predicdtion results. Specifically, the acceleration prediction of traffic participants is improved by up to 12% compared to the baselines, which do not exploit this explicit information. Furthermore, by including additional information about previous scenes, we achieve 73% improvements.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Relation-based Motion Prediction using Traffic Scene Graphs


    Beteiligte:
    Zipfl, Maximilian (Autor:in) / Hertlein, Felix (Autor:in) / Rettinger, Achim (Autor:in) / Thoma, Steffen (Autor:in) / Halilaj, Lavdim (Autor:in) / Luettin, Juergen (Autor:in) / Schmid, Stefan (Autor:in) / Henson, Cory (Autor:in)


    Erscheinungsdatum :

    08.10.2022


    Format / Umfang :

    569492 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SCENE TOKENIZATION FOR MOTION PREDICTION

    ZHOU YIN / JI JINGWEI / YANG ZHENPEI et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    Top-down scene prediction based on object motion

    MORALES MORALES ANGEL GUADALUPE / KOBILAROV MARIN / GARIMELLA GIANNI et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Top-down scene prediction based on motion data

    GARIMELLA GIANNI / KOBILAROV MARIN / MORALES MORALES ANGEL GUADALUPE et al. | Europäisches Patentamt | 2022

    Freier Zugriff


    A Framework for Probabilistic Generic Traffic Scene Prediction

    Hu, Yeping / Zhan, Wei / Tomizuka, Masayoshi | IEEE | 2018