The explainability of complex machine-learning models is becoming increasingly significant in safety-critical domains such as autonomous driving. In this context, counterfactual explanation (CE), as an effective explainability method in explainable artificial intelligence, plays an important role. It aims to identify minimal alterations to input that can change the model’s output, thereby revealing key factors influencing model decisions. However, generating counterfactual samples might involve manually selecting input features, potentially leading to suboptimal and biased explanations. This study introduces a feature contribution guided CE generation framework to address this issue. Our method utilizes feature contributions based on Shapley values to guide the model’s focus on the most influential features. This enables end-users to quickly pinpoint the search direction in generating CEs (e.g., prioritizing the most critical features) and producing representative CEs. To comprehensively evaluate our method, we conducted experimental validation on two representative machine learning models: autonomous driving decision-making using Deep Q-Network and lane-changing prediction using deep learning. In addition, we conducted a user-centered study to evaluate the practical applicability of the SVCE in autonomous driving scenarios, which serves as a crucial validation of the presented SVCE. The results show that SVCE can help users understand and diagnose the model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SVCE: Shapley Value Guided Counterfactual Explanation for Machine Learning-Based Autonomous Driving


    Beteiligte:
    Li, Meng (Autor:in) / Sun, Hengyang (Autor:in) / Huang, Yanjun (Autor:in) / Chen, Hong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2024


    Format / Umfang :

    2361975 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SAFETY MEASUREMENT FOR A COUNTERFACTUAL RISK IN AUTONOMOUS VEHICLE DRIVING

    CHI-JOHNSTON GEOFFREY LOUIS / FREEMAN LAURA ATHENA / ROLAND CHRISTOPHER BRIAN et al. | Europäisches Patentamt | 2023

    Freier Zugriff


    Deep Learning Model for Crash Injury Severity Analysis Using Shapley Additive Explanation Values

    Kang, Yashu / Khattak, Aemal J. | Transportation Research Record | 2022


    CASAD-GPS: Causal Shapley Additive Explanation for GPS Spoofing Attacks Detection

    Fan, Zhengyang / Tian, Xin / Pham, Khanh et al. | IEEE | 2024