Safe autonomous driving in urban areas requires robust algorithms to avoid collisions with other traffic participants with limited perception ability. Current deployed approaches relying on Autonomous Emergency Braking (AEB) systems are often overly conservative. In this work, we formulate the problem as a partially observable Markov decision process (POMDP), to derive a policy robust to uncertainty in the pedestrian location. We investigate how to integrate such a policy with an AEB system that operates only when a collision is unavoidable. In addition, we propose a rigorous evaluation methodology on a set of well-defined scenarios. We show that combining the two approaches provides a robust autonomous braking system that reduces unnecessary braking caused by using the AEB system on its own.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Pedestrian Collision Avoidance System for Scenarios with Occlusions


    Beteiligte:


    Erscheinungsdatum :

    01.06.2019


    Format / Umfang :

    576562 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    PEDESTRIAN COLLISION AVOIDANCE SYSTEM FOR SCENARIOS WITH OCCLUSIONS

    Schraner, Markus / Bouton, Maxime / Kochenderfer, Mykel J. et al. | British Library Conference Proceedings | 2019


    Study on Pedestrian Collision Avoidance System Considering Occlusions

    Matsumi, R. / Raksincharoensak, P. / Nagai, M. et al. | British Library Conference Proceedings | 2011


    Driving Behavior Analysis for Pedestrian Collision Avoidance Under Emergency Scenarios

    Yuan, Quan / Li, Qingkun / Wang, Wenjun | British Library Conference Proceedings | 2022


    Driving Behavior Analysis for Pedestrian Collision Avoidance Under Emergency Scenarios

    Yuan, Quan / Li, Qingkun / Wang, Wenjun | Springer Verlag | 2021


    Vehicle collision avoidance system with enhanced pedestrian avoidance

    EDO-ROS MANUEL | Europäisches Patentamt | 2018

    Freier Zugriff