This paper proposes a novel deep learning framework for multi-modal motion prediction. The framework consists of three parts: recurrent neural network to process target agent's motion process, convolutional neural network to process the rasterized environment representation, and distance-based attention mechanism to process the interactions among different agents. We validate the proposed framework on a large-scale real-world driving dataset, Waymo open motion dataset, and compare its performance against other methods on the standard testing benchmark. The qualitative results manifest that the predicted trajectories given by our model are accurate, diverse, and in accordance with the road structure. The quantitative results on the standard benchmark reveal that our model outperforms other baseline methods in terms of prediction accuracy and other evaluation metrics. The proposed framework is the second-place winner of the 2021 Waymo open dataset motion prediction challenge.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    ReCoAt: A Deep Learning-based Framework for Multi-Modal Motion Prediction in Autonomous Driving Application


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


    Publication date :

    2022-10-08


    Size :

    647412 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Cure and Recoat Mechanism of 2K Polyurethane Topcoats

    McGinness, J. D. / SAE | British Library Conference Proceedings | 1995


    Cure and Recoat Mechanism of 2K Polyurethane Topcoats

    McGinness, James D. | SAE Technical Papers | 1995


    Cure and recoat mechanism of 2K polyurethane topcoats

    McGinness,J.D. / Red Spot Paint and Varnish,US | Automotive engineering | 1995


    A Generic Framework for Motion Prediction in Autonomous Driving

    Karle, Phillip Jonathan | TIBKAT | 2024

    Free access