Explainability is essential for autonomous vehicles and other robotics systems interacting with humans and other objects during operation. Humans need to understand and anticipate the actions taken by machines for trustful and safe cooperation. In this work, we aim to develop an explainable model that generates explanations consistent with both human domain knowledge and the model’s inherent causal relation. In particular, we focus on an essential building block of autonomous driving—multi-agent interaction modeling. We propose Grounded Relational Inference (GRI). It models an interactive system’s underlying dynamics by inferring an interaction graph representing the agents’ relations. We ensure a semantically meaningful interaction graph by grounding the relational latent space into semantic interactive behaviors defined with expert domain knowledge. We demonstrate that it can model interactive traffic scenarios under both simulation and real-world settings and generate semantic graphs explaining the vehicle’s behavior through their interactions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving


    Beteiligte:
    Tang, Chen (Autor:in) / Srishankar, Nishan (Autor:in) / Martin, Sujitha (Autor:in) / Tomizuka, Masayoshi (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.09.2024


    Format / Umfang :

    3112556 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Trusting Explainable Autonomous Driving: Simulated Studies

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


    Image transformer for explainable autonomous driving system

    Dong, Jiqian / Chen, Sikai / Zong, Shuya et al. | IEEE | 2021




    Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review

    Kuznietsov, Anton / Gyevnar, Balint / Wang, Cheng et al. | IEEE | 2024