Despite the remarkable advancements in autonomous driving, the challenge persists in achieving interpretable action decision-making, primarily owing to the intricate and ambiguous relationship between detected agents and driving intention. In this study, we introduce an interpretable action prediction model, denoted as the Prediction-Driven Attention Network (PDANet), designed to undertake action decisions and provide corresponding interpretations cohesively. The PDANet is inspired by the perceptual mechanisms inherent in human drivers, who allocate attention according to their driving intentions. Specifically, we elaborate a prediction module to generate vehicle prospective trajectories to characterize driving intentions. Subsequently, the features of this predicted trajectory are utilized to modulate the attention distribution among agents through the top-down attention module, yielding an attention map. Finally, two distinct task tokens are applied to aggregate agent features and generate the final output according to the derived attention map. Extensive experiments conducted on the publicly available BDD-OIA and nu-AR datasets demonstrate that our proposed method outperforms all prior works in terms of both action prediction and behavior interpretation tasks. Remarkably, our method attains a noteworthy enhancement in the behavior interpretation task, surpassing the previous state-of-the-art by a substantial margin of +10.8% in terms of F1-score on the nu-AR dataset. We also validate our algorithm on Carla Town05 long in a closed-loop decision-making scenario, highlighting the generality and robustness of our approach. Furthermore, qualitative results show that the agents selected by our model are more closely aligned with human cognitive processes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Top-Down Attention-Based Mechanisms for Interpretable Autonomous Driving


    Contributors:
    Fu, Zheng (author) / Jiang, Kun (author) / Xu, Yuhang (author) / Wang, Yunlong (author) / Wen, Tuopu (author) / Gao, Hao (author) / Zhong, Zhihua (author) / Yang, Diange (author)


    Publication date :

    2025-02-01


    Size :

    3709873 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Interpretable autonomous driving system and method thereof

    MARTIN SUJITHA CATHERINE / TANG CHEN | European Patent Office | 2025

    Free access

    INTERPRETABLE AUTONOMOUS DRIVING SYSTEM AND METHOD THEREOF

    MARTIN SUJITHA CATHERINE / TANG CHEN | European Patent Office | 2021

    Free access

    Interpretable Goal-based Prediction and Planning for Autonomous Driving

    Albrecht, Stefano V. / Brewitt, Cillian / Wilhelm, John et al. | ArXiv | 2020

    Free access

    Interpretable Autonomous Driving Model Based on Cognitive Reinforcement Learning

    Li, Yijia / Qi, Hao / Zhu, Fenghua et al. | IEEE | 2024


    Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving

    Teng, Siyu / Chen, Long / Ai, Yunfeng et al. | IEEE | 2023