Automated vehicles require rigorous evaluation to ensure safety before being available. Scenario-based accelerated evaluation methods using importance sampling are promising approaches whose core problem is constructing a high-efficiency importance sampling distribution. Typical methods for constructing the importance sampling distribution are prone to fall into local optima with low evaluation efficiency due to the increased search space when solving for high-dimensional parameters. In this study, an accelerated evaluation framework integrating prior knowledge that constrains the search space is proposed. The original distributions of scenario variables and the importance of scenario variables to the occurrence of rare events are taken as prior knowledge. The prior knowledge is used to constrain the search space to candidate distributions with high evaluation efficiency. The candidate distribution with the highest evaluation efficiency is used as the importance sampling distribution to accelerate the safety evaluation of automated vehicles. The proposed framework is validated using the HighD naturalistic driving dataset in cut-in scenarios. Simulation results show that the proposed framework can improve the evaluation efficiency by three orders of magnitude compared to the crude Monte Carlo, demonstrating that prior knowledge can be successfully used to constrain the search space for constructing a high-efficiency importance sampling distribution.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Accelerated Evaluation Framework Integrating Prior Knowledge for Automated Vehicle Safety


    Weitere Titelangaben:

    Lect.Notes Mechanical Engineering


    Beteiligte:
    Huang, Wei (Herausgeber:in) / Ahmadian, Mehdi (Herausgeber:in) / Chen, Shanshi (Autor:in) / Zhang, Xinjie (Autor:in) / Lv, Xiaoxing (Autor:in) / Guo, Konghui (Autor:in) / Ding, Haitao (Autor:in) / Kong, Deyu (Autor:in)

    Kongress:

    The IAVSD International Symposium on Dynamics of Vehicles on Roads and Tracks ; 2023 ; Ottawa, ON, Canada August 21, 2023 - August 25, 2023



    Erscheinungsdatum :

    13.10.2024


    Format / Umfang :

    11 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    A Proposed Safety Case Framework for Automated Vehicle Safety Evaluation

    Wishart, Jeffrey / Zhao, Junfeng / Woodard, Braeden et al. | IEEE | 2023


    Measuring automated vehicle safety : forging a framework

    Fraade-Blanar, Laura / Blumenthal, Marjory S. / Anderson, James M. et al. | TIBKAT | 2018


    Integrating Naturalistic Insights in Objective Multi-Vehicle Safety Framework

    Del Re, Enrico / Aghanouri, Amirhesam / Olaverri-Monreal, Cristina | IEEE | 2024


    Integrating Naturalistic Insights in Objective Multi-Vehicle Safety Framework

    Del Re, Enrico / Aghanouri, Amirhesam / Olaverri-Monreal, Cristina | ArXiv | 2024

    Freier Zugriff