The ability to accurately predict feasible multi-modal future trajectories of surrounding traffic participants is crucial for behavior planning in autonomous vehicles. The Motion Transformer (MTR), a state-of-the-art motion prediction method, alleviated mode collapse and instability during training and enhanced overall prediction performance by replacing conventional dense future endpoints with a small set of fixed prior motion intention points. However, the fixed prior intention points make the MTR multi-modal prediction distribution over-scattered and infeasible in many scenarios. In this paper, we propose the ControlMTR framework to tackle the aforementioned issues by generating scene-compliant intention points and additionally predicting driving control commands, which are then converted into trajectories by a simple kinematic model with soft constraints. These control-generated trajectories will guide the directly predicted trajectories by an auxiliary loss function. Together with our proposed scene-compliant intention points, they can effectively restrict the prediction distribution within the road boundaries and suppress infeasible off-road predictions while enhancing prediction performance. Remarkably, without resorting to additional model ensemble techniques, our method surpasses the baseline MTR model across all performance metrics, achieving notable improvements of 5.22% in SoftmAP and a 4.15% reduction in MissRate. Our approach notably results in a 41.51% reduction in the cross-boundary rate of the MTR, effectively ensuring that the prediction distribution is confined within the drivable area.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    ControlMTR: Control-Guided Motion Transformer with Scene-Compliant Intention Points for Feasible Motion Prediction


    Beteiligte:
    Sun, Jiawei (Autor:in) / Yuan, Chengran (Autor:in) / Sun, Shuo (Autor:in) / Wang, Shanze (Autor:in) / Han, Yuhang (Autor:in) / Ma, Shuailei (Autor:in) / Huang, Zefan (Autor:in) / Wong, Anthony (Autor:in) / Tee, Keng Peng (Autor:in) / Ang, Marcelo H. (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    3424389 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



    Probabilistic Prediction of Vehicle Semantic Intention and Motion

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

    Freier Zugriff

    Probabilistic Prediction of Vehicle Semantic Intention and Motion

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