The opacity of decision-making in autonomous vehicles, rooted in the use of accurate yet complex AI models, has created barriers to their societal trust and regulatory acceptance, raising the need for explainability. We propose a post-hoc, model-agnostic solution to provide teleological expla-nations of vehicle behaviour in urban environments. Based on an existing explainability method called Intention-aware Policy Graphs, our approach enables the extraction of interpretable and reliable explanations of vehicle behaviour in the nuScenes dataset from global and local perspectives. We demonstrate how these explanations can be used to verify whether the vehicle operates within acceptable legal boundaries and to reveal potential vulnerabilities in autonomous driving datasets and models.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intention-aware Policy Graphs for Explainable Autonomous Driving


    Contributors:


    Publication date :

    2025-06-22


    Size :

    868784 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Explaining Autonomous Vehicles with Intention-aware Policy Graphs

    Montese, Sara / Gimenez-Abalos, Victor / Cortés, Atia et al. | ArXiv | 2025

    Free access

    An Intention-aware and Online Driving Style Estimation Based Personalized Autonomous Driving Strategy

    Sun, Bohua / Deng, Weiwen / Wu, Jian et al. | Springer Verlag | 2020


    Trusting Explainable Autonomous Driving: Simulated Studies

    Goldman, Claudia V. / Bustin, Ronit | IEEE | 2022



    Intention-aware Decision Making in Urban Lane Change Scenario for Autonomous Driving

    Song, Weilong / Su, Bo / Xiong, Guangming et al. | IEEE | 2018