Forecasting accurate and consistent future states of traffic participants within the knowledge of uncertainty is imperative for enhancing the social synergies and driving safety in autonomous driving system, particularly under interactive scenarios. Tackling multimodality through direct estimation or regressions remains the major challenge, primarily due to the need to balance the granularity of uncertainties with the sparsity of positive training samples to be updated for respective decoding modes. This work introduces GTR, a multimodal motion prediction framework with a group-wise modal allocation scheme for Transformer-enabled trajectory decoding. Our approach includes several key steps to tackle this challenge. Firstly, we introduced the group-wise allocation strategy, a plugged-in decoding initialization for each modality, thereby densely increase training diversity of positive queries for respective modality. Additionally, a missrate optimization pipeline is instantiated which further maximize the discriminated margins for positive decoding queries. This neat decoding strategy achieved compelling prediction accuracy, social consistency, and outstanding performance across primary metrics in the Waymo Open Motion Dataset (WOMD) leaderboard.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Modal Motion Prediction with Group-Wise Modal Assignment Transformer for Autonomous Driving


    Contributors:
    Liu, Haochen (author) / Huang, Zhiyu (author) / Mo, Xiaoyu (author) / Lv, Chen (author)


    Publication date :

    2024-09-24


    Size :

    326875 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    M2DA: Multi-Modal Fusion Transformer Incorporating Driver Attention for Autonomous Driving

    Xu, Dongyang / Li, Haokun / Wang, Qingfan et al. | ArXiv | 2024

    Free access


    Multi-Modal Motion Prediction with Graphormers

    Wonsak, Shimon / Al-Rifai, Mohammad / Nolting, Michael et al. | IEEE | 2022