Safety-critical Autonomous Systems require trustworthy and transparent decision-making process to be deployable in the real world. The advancement of Machine Learning introduces high performance but largely through black-box algorithms. In this position paper, we focus the discussion of explainability specifically with Autonomous Vehicles (AVs). As a safety-critical system, AVs provide the unique opportunity to utilize cutting-edge Machine Learning techniques while requiring transparency in decision making. Interpretability in every action the AV takes becomes crucial in post-hoc analysis where blame assignment might be necessary. In this paper, we provide positioning on how researchers could consider incorporating explainability and interpretability into design and optimization of separate Autonomous Vehicle modules including Perception, Planning, and Control.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Towards Explainability in Modular Autonomous System Software


    Beteiligte:
    Zheng, Hongrui (Autor:in) / Zang, Zirui (Autor:in) / Yang, Shuo (Autor:in) / Mangharam, Rahul (Autor:in)


    Erscheinungsdatum :

    2023-06-04


    Format / Umfang :

    7631146 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Explainability of Autonomous Vehicle Decision Making

    WRAY KYLE HOLLINS / BENTAHAR OMAR / VAGADIA ASTHA et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Explainability of autonomous vehicle decision making

    WRAY KYLE HOLLINS / BENTAHAR OMAR / VAGADIA ASTHA et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Improving the Explainability of Autonomous and Intelligent Systems with Conversational Interfaces

    Hochgeschwender, Nico | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019

    Freier Zugriff

    Improving the Explainability of Autonomous and Intelligent Systems with Conversational Interfaces

    Hochgeschwender, Nico | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2019

    Freier Zugriff

    Towards Grad-CAM Based Explainability in a Legal Text Processing Pipeline

    Górski, Łukasz / Ramakrishna, Shashishekar / Nowosielski, Jędrzej M. | TIBKAT | 2020

    Freier Zugriff