Achieving excellent generalization on perceiving real traffic scenarios with diversity is the long-term goal for building robust autonomous driving systems. In this paper, we propose to discover potential shortness of certain perception module by analyzing its worst-scenario performance. However, with the benchmark datasets growing huge and tremendous, exhaustive searching for the worst perception scenario (WPS) seems to be time consuming and unnecessary. To address, we present an automatic searching scheme empowered by reinforcement learning. In this case, worst scenario mining is formulated as a discrete search problem. A single layer recurrent neural network with LSTM neurons is employed to predict WPS according to the searching reward, which is optimized by a vanilla policy gradient method. Moreover, to deal with the imbalanced distribution of real traffic scenarios, a KNN-like retrieval is utilized for searching the closest scenario samples. Effective yet efficient, the proposed method has been validated by finding the most challenging scenarios for various vehicle detectors on KITTI, BDD100k and our own benchmark set EVB. Further experiments reveal that detection networks with structural similarity share the similar WPS.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Worst Perception Scenario Search for Autonomous Driving


    Beteiligte:
    Xu, Liheng (Autor:in) / Zhang, Chi (Autor:in) / Liu, Yuehu (Autor:in) / Wang, Le (Autor:in) / Li, Li (Autor:in)


    Erscheinungsdatum :

    2020-10-19


    Format / Umfang :

    2821279 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    SCENARIO IDENTIFICATION IN AUTONOMOUS DRIVING ENVIRONMENTS

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | Europäisches Patentamt | 2022

    Freier Zugriff

    SCENARIO IDENTIFICATION IN AUTONOMOUS DRIVING ENVIRONMENTS

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | Europäisches Patentamt | 2022

    Freier Zugriff

    PERCEPTION FIELDS FOR AUTONOMOUS DRIVING

    RAICHELGAUZ IGAL / ENGELSOY JULIUS | Europäisches Patentamt | 2024

    Freier Zugriff

    SCENARIO BASED CONTROL OF AUTONOMOUS DRIVING VEHICLE

    JIANG SHU / LUO QI / MIAO JINGHAO et al. | Europäisches Patentamt | 2021

    Freier Zugriff