We present a novel hybrid learning method, named HyLEAR, for solving the collision-free navigation problem for self-driving cars in POMDPs. HyLEAR leverages interposed learning to embed knowledge of a hybrid planner into a deep reinforcement learner to faster determine safe and comfortable driving policies of the car. In particular, the hybrid planner combines pedestrian path prediction and risk-aware path planning with driving-behavior rule-based reasoning such that the determined safe trajectories also take into account, whenever possible, the ride comfort and a given set of driving-behavior rules. Our experimental performance analysis over the CARLA-CTS benchmark of critical traffic scenarios revealed that HyLEAR can significantly outperform the selected baselines in terms of safety and ride comfort.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    HyLEAR: Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving


    Contributors:


    Publication date :

    2023-06-04


    Size :

    3771999 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning

    Kamran, Danial / Engelgeh, Tizian / Busch, Marvin et al. | DataCite | 2021

    Free access



    Safe and Comfortable Motion Planning for Bumpy Road Driving

    Zhang, Jiajie / Xiao, Bin / Tang, Binbin et al. | IEEE | 2023