One big challenge regarding the development of highly automated driving (HAD) functions is validation and, in particular, providing proof of the desired functionality in any given scenario. Especially, corner cases, representing atypical, rare scenarios such as unexpected object movements are of high interest and thus must be detected to treat them with special attention. First, this paper presents a taxonomy for corner cases (CC) with focus on HAD. Specifically, so-called systemic corner cases (SCC) are introduced. Next, a feasibility study is presented on how these SCCs can be detected using different Machine Learning (ML) approaches for anomaly detection. We propose to use a hybrid ensemble of a One-Class Support Vector Machine (OCSVM) and a Clustering-Based Local Outlier Factor (CBLOF) incorporating domain knowledge to account for the nature of corner cases in timely correlated scenarios. The underlying data are unlabeled multivariate time series of HAD-system internal variables. Our experiments on both, synthetically generated and representative real-world CC, show that the hybrid ensemble can detect a variety of real corner cases, which allows for promising validation support of HAD functions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    On Why the System Makes the Corner Case: AI-based Holistic Anomaly Detection for Autonomous Driving


    Beteiligte:
    Pfeil, Jerg (Autor:in) / Wieland, Jochen (Autor:in) / Michalke, Thomas (Autor:in) / Theissler, Andreas (Autor:in)


    Erscheinungsdatum :

    05.06.2022


    Format / Umfang :

    2544998 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Towards Corner Case Detection for Autonomous Driving

    Bolte, Jan-Aike / Bar, Andreas / Lipinski, Daniel et al. | IEEE | 2019


    TOWARDS CORNER CASE DETECTION FOR AUTONOMOUS DRIVING

    Bolte, Jan-Aike / Bar, Andreas / Lipinski, Daniel et al. | British Library Conference Proceedings | 2019


    PERCEPTION ANOMALY DETECTION FOR AUTONOMOUS DRIVING

    SHA LONG / ZHANG JUNLIANG / GE RUNDONG et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    Free space detection - a corner stone of autonomous driving

    Neumann, L. / Vanholme, B. / Gressmann, M. et al. | British Library Conference Proceedings | 2015


    A Text Prompt-Based Approach for Zero-Shot Corner Case Object Detection in Autonomous Driving

    Liu, Tianqi / Zhang, Shanghang / Qin, Yanjun et al. | IEEE | 2023