Deep neural networks (DNNs) have advanced autonomous driving, but their lack of transparency remains a major obstacle to real-world application. Attribution methods, which aim to explain DNN decisions, offer a potential solution. However, existing methods, primarily designed for image classification models, often suffer from performance degradation and require specialized algorithmic adjustments when applied to the diverse models in autonomous driving. To address this challenge, we introduce a universally applicable representation of traffic scenes, forming the basis for our unified attribution method. Specifically, we leverage the first-order Taylor expansion at a specific hidden layer, i.e., the product of gradients and feature maps, to represent abstract traffic scene information. This representation guides both the optimization of attribution path generation and the attribution computation, enabling consistent and effective attributions for both lane-change prediction and vision-based control models. Experiments on two distinct autonomous driving models demonstrate that our approach outperforms state-of-the-art methods in explanation accuracy and robustness, advancing the interpretability of DNN-based autonomous driving models.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic Scene-Informed Attribution of Autonomous Driving Decisions


    Contributors:
    Shi, Rui (author) / Li, Tianxing (author) / Yamaguchi, Yasushi (author) / Zhang, Liguo (author)


    Publication date :

    2025-07-01


    Size :

    4065775 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Action Recognition Framework in Traffic Scene for Autonomous Driving System

    Xu, Feiyi / Xu, Feng / Xie, Jiucheng et al. | IEEE | 2022


    Understanding Decision-Making of Autonomous Driving via Semantic Attribution

    Shi, Rui / Li, Tianxing / Yamaguchi, Yasushi et al. | IEEE | 2025


    PHYSICS-INFORMED OPTIMIZATION FOR AUTONOMOUS DRIVING SYSTEMS

    SMITH DAVID / YOON KEVIN | European Patent Office | 2024

    Free access

    PHYSICS-INFORMED OPTIMIZATION FOR AUTONOMOUS DRIVING SYSTEMS

    SMITH DAVID / YOON KEVIN | European Patent Office | 2022

    Free access

    Exploring Decision Shifts in Autonomous Driving With Attribution-Guided Visualization

    Shi, Rui / Li, Tianxing / Yamaguchi, Yasushi et al. | IEEE | 2025