Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and anticipatory driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by multiple factors. In this paper, we thoroughly analyze the requirements on pedestrian behavior prediction for automated driving via a system-level approach. To this end we investigate real-world pedestrian-vehicle interactions with human drivers. Based on human driving behavior we then derive appropriate reaction patterns of an automated vehicle and determine requirements for the prediction of pedestrians. This includes a novel metric tailored to measure prediction performance from a system-level perspective. The proposed metric is evaluated on a large-scale dataset comprising thousands of real-world pedestrian-vehicle interactions. We furthermore conduct an ablation study to evaluate the importance of different contextual cues and compare these results to ones obtained using established performance metrics for pedestrian prediction. Our results highlight the importance of a system-level approach to pedestrian behavior prediction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pedestrian Behavior Prediction for Automated Driving: Requirements, Metrics, and Relevant Features


    Beteiligte:
    Herman, Michael (Autor:in) / Wagner, Jorg (Autor:in) / Prabhakaran, Vishnu (Autor:in) / Moser, Nicolas (Autor:in) / Ziesche, Hanna (Autor:in) / Ahmed, Waleed (Autor:in) / Burkle, Lutz (Autor:in) / Kloppenburg, Ernst (Autor:in) / Glaser, Claudius (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-09-01


    Format / Umfang :

    5018257 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Pedestrian Environment Model for Automated Driving

    Holzbock, Adrian / Tsaregorodtsev, Alexander / Belagiannis, Vasileios | IEEE | 2023


    Analysing pedestrian-vehicle interaction to derive implications for automated driving

    Ackermann, Claudia / Technische Universität Chemnitz | TIBKAT | 2019

    Freier Zugriff


    Gear Design Relevant Cleanness Metrics

    Damm, E. / Glaws, P. | TIBKAT | 2016


    Modeling of Pedestrian Behavior in Crossing Urban Road for Risk Prediction Driving Assistance System

    Nagai, Masao / Hayashi, Ryuzo / Aoyagi, Soichiro | SAE Technical Papers | 2011