Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation driven methods such as Adaptive Stress Testing (AST) have been proposed to aid in validation. AST formulates the problem of finding the most likely failure scenarios as a Markov decision process, which can be solved using reinforcement learning. In practice, AST tends to find scenarios where failure is unavoidable and tends to repeatedly discover the same types of failures of a system. This work addresses these issues by encoding domain relevant information into the search procedure. With this modification, the AST method discovers a larger and more expressive subset of the failure space when compared to the original AST formulation. We show that our approach is able to identify useful failure scenarios of an autonomous vehicle policy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validatio


    Contributors:


    Publication date :

    2019-10-01


    Size :

    1338921 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic control method and apparatus with autonomous vehicle based on adaptive reward

    KWON MIN HAE / EOM CHAN IN / LEE DONG SU | European Patent Office | 2025

    Free access

    TRAFFIC CONTROL METHOD AND APPARATUS WITH AUTONOMOUS VEHICLE BASED ON ADAPTIVE REWARD

    KWON MIN HAE / EOM CHAN IN / LEE DONG SU | European Patent Office | 2025

    Free access

    Autonomous vehicle operated with safety augmentation

    HO JUSTIN / ZYCH NOAH | European Patent Office | 2024

    Free access

    Autonomous Vehicle Operated with Safety Augmentation

    HO JUSTIN / ZYCH NOAH | European Patent Office | 2025

    Free access

    Autonomous vehicle operated with safety augmentation

    HO JUSTIN WAYNE / ZYCH NOAH | European Patent Office | 2021

    Free access