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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Worst Perception Scenario Search for Autonomous Driving


    Contributors:
    Xu, Liheng (author) / Zhang, Chi (author) / Liu, Yuehu (author) / Wang, Le (author) / Li, Li (author)


    Publication date :

    2020-10-19


    Size :

    2821279 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    WORST PERCEPTION SCENARIO SEARCH FOR AUTONOMOUS DRIVING

    Xu, Liheng / Zhang, Chi / Liu, Yuehu et al. | British Library Conference Proceedings | 2020



    AUTONOMOUS DRIVING SCENARIO OBSTACLE PREDICTION

    HUANG KAINING / KUANG RUIFENG / XIA FEI et al. | European Patent Office | 2025

    Free access

    SCENARIO IDENTIFICATION IN AUTONOMOUS DRIVING ENVIRONMENTS

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | European Patent Office | 2022

    Free access

    Scenario identification in autonomous driving environments

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | European Patent Office | 2024

    Free access