Accurately forecasting the future motions of road participants is essential for proactive hazard avoidance and safety planning of autonomous vehicles. Existing methods for motion prediction based on probabilistic generative models are limited to low-accuracy likelihood calculations and relatively finite mode distributions. Recent studies show that score-based models can naturally overcome these limitations. In this work, we present a novel paradigm of conditional score-based models for vehicle motion prediction, called Motion-CSM. First, we model scene contextual representations of interaction regions at the feature level via graph convolutional networks. We then interpolate these representations as conditions into the solution process of the continuous-time reverse stochastic differential equation (SDE) to guide trajectory generation, which progressively converts the known prior distributions into multimodal trajectories including the ground truth modes. The designed stacked Transformer structure with dual control conditions is adopted to learn the score function approximation of the Gaussian perturbation kernel. Finally, we develop multiple consistency constraints to align the inference results of Motion-CSM in reverse SDE solving to improve the self-consistency and stability of multimodal trajectory generation. Experimental results on the real-world motion dataset demonstrate that the multimodal forecasting accuracy of Motion-CSM outperforms state-of-the-art methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicular Multimodal Motion Forecasting via Conditional Score-based Modeling


    Beteiligte:
    Wang, Zhangyun (Autor:in) / Ning, Nianwen (Autor:in) / Tian, Shihan (Autor:in) / Lu, Ning (Autor:in) / Cheng, Nan (Autor:in) / Zhou, Yi (Autor:in)


    Erscheinungsdatum :

    10.10.2023


    Format / Umfang :

    3708779 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Score-Based Multimodal Autoencoder

    Wesego, Daniel / Rooshenas, Pedram | ArXiv | 2023

    Freier Zugriff

    CONDITIONAL AVAILABILITY OF VEHICULAR MIXED-REALITY

    NOWAKOWSKI CHRISTOPHER STEVEN / KUOCH SIAV-KUONG / GARNAULT ALEXANDRE JACQUES et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Conditional availability of vehicular mixed-reality

    NOWAKOWSKI CHRISTOPHER STEVEN / KUOCH SIAV-KUONG / GARNAULT ALEXANDRE JACQUES et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Blockchain-Enabled Conditional Decentralized Vehicular Crowdsensing System

    Zhao, Pincan / Li, Changle / Fu, Yuchuan et al. | IEEE | 2022


    VEHICULAR MOTION CONTROL METHOD AND VEHICULAR MOTION CONTROL APPARATUS

    NEMOTO HIDEAKI | Europäisches Patentamt | 2018

    Freier Zugriff