This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent. We construct a model, given camera images as input, that is capable of learning and predicting the dynamics of obstacles, cars and pedestrians, and train our policy using this model. Two policies that control both braking and steering are compared against a baseline where the only action taken is (conventional) braking in a straight line. The two policies are trained using two distinct reward structures, one where any and all collisions incur a fixed penalty, and a second one where the penalty is calculated based on already established delta-v models of injury severity. The results show that both policies exceed the performance of the baseline, with the policy trained using injury models having the highest performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Imminent Collision Mitigation with Reinforcement Learning and Vision


    Contributors:
    Porav, Horia (author) / Newman, Paul (author)


    Publication date :

    2018-11-01


    Size :

    576583 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Collision imminent detection

    FASOLA JUAN / LO EUGENE / ZHOU XIAOYU et al. | European Patent Office | 2025

    Free access

    COLLISION IMMINENT DETECTION

    FASOLA JUAN / LO EUGENE / ZHOU XIAOYU et al. | European Patent Office | 2023

    Free access

    Stereo-based vision system for automotive imminent collision detection

    Peng Chang, / Camus, T. / Mandelbaum, R. | IEEE | 2004


    Stereo-Based Vision System for Automotive Imminent Collision Detection

    Chang, P. / Camus, T. / Mandelbaum, R. et al. | British Library Conference Proceedings | 2004


    Collision Imminent Steering Control Systems and Methods

    STEIN JEFFREY L / ERSAL TULGA / WURTS JOHN | European Patent Office | 2019

    Free access