This paper focuses on safety performance testing and characterization of black-box highly automated vehicles (HAV). Existing testing approaches typically deploy the HAV into a specific testing environment involving various passively defined testing strategies presented by other traffic participants such as (i) a naturalistic driving policy learned from human drivers, (ii) extracted concrete scenarios from real-world driving data, and (iii) model-based or data-driven adversarial testing methodologies focusing on forcing safety-critical events. The safety performance of the HAV is further characterized by analyzing the obtained testing outcomes with a particular selected measure, such as the observed collision risk. These testing practices suffer from the scarcity of safety-critical events, have limited operational design domain (ODD) coverage, or are biased toward long-tail unsafe cases. This paper presents a novel and informative testing strategy that differs from these existing practices. The proposal is inspired by the intuition that a relatively safer HAV driving policy would allow the traffic vehicles to exhibit a higher level of aggressiveness to achieve a certain fixed level of an overall safety outcome metric. One can specifically characterize such an HAV and traffic interaction strategy and use it as a safety performance indicator for the HAV. Under the proposed testing scheme, the HAV is evaluated under its full ODD with a reward function that represents a trade-off between safety and adversity in generating safety-critical events. The proposed methodology is demonstrated in simulation with various HAV designs under different operational design domains.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Training Adversarial Yet Safe Agent to Characterize the Safety Performance of Highly Automated Vehicles


    Beteiligte:
    Zhu, Minghao (Autor:in) / Sidhu, Anmol (Autor:in) / Redmill, Keith A. (Autor:in)


    Erscheinungsdatum :

    22.10.2024


    Format / Umfang :

    1861400 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles

    Zhu, Minghao / Sidhu, Anmol / Redmill, Keith A. | ArXiv | 2024

    Freier Zugriff

    Automated vehicles: multi-agent safety

    Pimentel, Juan R. | SLUB | 2020


    Automated vehicles: multi-agent safety

    Pimentel, Juan R. | TIBKAT | 2020


    Safe Cooperation of Automated Vehicles

    Heß, Daniel / Löper, Christian / Hesse, Tobias | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2017

    Freier Zugriff