The simulation of real-world traffic is a challenging task that can be accelerated by imitation learning. Recent approaches based on neural network policies were able to present promising results in generating human-like driving behavior. However, one drawback is that certain behaviors, such as avoiding accidents, cannot be guaranteed with such policies. Therefore, we propose to combine recent imitation learning methods like GAIL with a rule-based safety framework to avoid collisions during training and testing. Our method is evaluated on highway driving scenes where all vehicles are controlled by our driving policies trained on the real-world driving dataset highD. In this setup, our method is compared to a standard neural network policy trained with GAIL. Agents using our method were able to match GAIL performance while additionally guaranteeing collision-free driving.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning to Drive from Observations while Staying Safe


    Contributors:


    Publication date :

    2021-07-11


    Size :

    1450671 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Staying Safe during Behavior Consultations

    Shaw, J.K. | British Library Conference Proceedings | 2007


    Threat Matrix: Staying Alive While Operating Abroad

    Esler, D. | British Library Online Contents | 2004


    Staying safe is a top priority

    British Library Online Contents | 2017


    Staying safe when working with pumps

    Hodgkinson, Kristin | Online Contents | 2014


    European Aviation Safety Seminar; Staying safe in times of change

    Flight Safety Foundation; European Regions Airline Association; Avions Marcel Dassault Breguet aviation | British Library Conference Proceedings | 2007