Automated driving has arisen more and more attention both in traditional automobile industries and in IT companies. Rapid development and significant results have been achieved. However, there are few effective and satisfying methods to prove that Highly Automated Driving (HAD) is currently at least as safe as a human driver. In this paper, a novel validation method named Virtual Assessment of Automation in Field Operation (VAAFO) is introduced in detail. In VAAFO, HAD system has no access to actuators but runs in parallel while human driver drives the vehicle. Behavior comparison between human-driven vehicle and HAD in same scenario is a main new feature in VAAFO to validate automated driving and find out potential critical scenarios. Combined with correction of world model and criticality metrics, potential critical scenarios are filtered further to identify real critical scenarios. Different modules of VAAFO are explained elaborately based on these working principles. In principle, the proposed method could accelerate testing and validation of HAD a lot without bringing additional risks. Moreover, critical scenarios will be identified as well.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Overcoming Challenges of Validation Automated Driving and Identification of Critical Scenarios


    Beteiligte:
    Wang, Cheng (Autor:in) / Winner, Hermann (Autor:in)


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    461560 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Learning Critical Scenarios in Feedback Control Systems for Automated Driving

    Zhu, Mengjia / Bemporad, Alberto / Kneissl, Maximilian et al. | IEEE | 2023


    Semantic Classification of Pedestrian Traffic Scenarios for the Validation of Automated Driving

    Hartjen, Lukas / Schuldt, Fabian / Friedrich, Bernhard | IEEE | 2019