Automated vehicles require carefully designed cost functions, which are challenging to specify due to the complexity of the behavior they need to cover. Inverse reinforcement learning is a principled methodology for deriving cost functions, but it requires high-quality expert demonstrations, which are expensive to obtain. Recently, scenario-based testing has emerged as a promising approach for validation of driving behavior. In this paper, we introduce a novel methodology that circumvents the need for costly expert driving demonstrations by harnessing scenario-based testing. Our Test-Driven Inverse Reinforcement Learning approach leverages Bayesian inference, utilizing the outcomes of scenario tests as observations to infer cost functions. We rigorously evaluate our method on simulated and real-world scenarios and demonstrate its ability to learn cost functions that successfully pass the respective scenario tests. We also show that the learned cost function generalizes well by also passing scenario tests from an unseen validation set and illustrate that few scenario tests are sufficient to learn meaningful cost functions. This innovative framework not only streamlines the cost function specification process but also offers a cost-effective and practical solution for advancing automated driving systems.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Test-Driven Inverse Reinforcement Learning Using Scenario-Based Testing


    Contributors:


    Publication date :

    2024-06-02


    Size :

    1235870 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Making a failure scenario using adversarial reinforcement learning background

    WACHI AKIFUMI | European Patent Office | 2022

    Free access

    Scenario-Based Thermal Management Parametrization Through Deep Reinforcement Learning

    Rudolf, Thomas / Muhl, Philip / Hohmann, Soren et al. | IEEE | 2024


    Automated reinforcement learning scenario variation and impact penalties

    LINSCOTT GARY / PASTERNAK ANDREAS / PACKER JEFFERSON BRADFIELD et al. | European Patent Office | 2024

    Free access

    Rule creation using MDP and inverse reinforcement learning

    KOSEKI AKIRA / MORIMURA TETSURO / TAKASE TOSHIRO et al. | European Patent Office | 2021

    Free access

    Rule creation using MDP and inverse reinforcement learning

    KOSEKI AKIRA / MORIMURA TETSURO / TAKASE TOSHIRO et al. | European Patent Office | 2021

    Free access