As autonomous vehicles (AVs) take on growing Operational Design Domains (ODDs), they need to go through a systematic, transparent, and scalable evaluation process to demonstrate their benefits to society. Current scenario sampling techniques for AV performance evaluation usually focus on a specific functionality, such as lane changing, and do not accommodate a transfer of information about an AV system from one ODD to the next. In this paper, we reformulate the scenario sampling problem across ODDs and functionalities as a submodular optimization problem. To do so, we abstract AV performance as a Bayesian Hierarchical Model, which we use to infer information gained by revealing performance in new scenarios. We propose the information gain as a measure of scenario relevance and evaluation progress. Furthermore, we leverage the submodularity, or diminishing returns, property of the information gain not only to find a near-optimal scenario set, but also to propose a stopping criterion for an AV performance evaluation campaign. We find that we only need to explore about 7.5% of the scenario space to meet this criterion, a 23% improvement over Latin Hypercube Sampling.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Plane and Sample: Maximizing Information about Autonomous Vehicle Performance using Submodular Optimization


    Beteiligte:


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    3032800 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Heterogeneous Measurement Selection for Vehicle Tracking using Submodular Optimization

    Kirchner, Matthew R. / Hespanha, Joao P. / Garagic, Denis | IEEE | 2020


    Autonomous vehicle performance optimization system

    ROSS WILLIAM PAYNE / BROWNING BRETT | Europäisches Patentamt | 2018

    Freier Zugriff

    Autonomous vehicle performance optimization system

    ROSS WILLIAM PAYNE / BROWNING BRETT | Europäisches Patentamt | 2019

    Freier Zugriff

    AUTONOMOUS VEHICLE PERFORMANCE OPTIMIZATION SYSTEM

    ROSS WILLIAM PAYNE / BROWNING BRETT | Europäisches Patentamt | 2018

    Freier Zugriff

    On Maximizing Lateral Clearance of an Autonomous Vehicle in Urban Environments

    Seccamonte, Francesco / Kabzan, Juraj / Frazzoli, Emilio | IEEE | 2019