Interaction-aware planning for autonomous driving requires an exploration of a combinatorial solution space when using conventional search- or optimization-based motion planners. With Deep Reinforcement Learning, optimal driving strategies for such problems can be derived also for higher-dimensional problems. However, these methods guarantee optimality of the resulting policy only in a statistical sense, which impedes their usage in safety critical systems, such as autonomous vehicles. Thus, we propose the Experience-Based-Heuristic-Search algorithm, which overcomes the statistical failure rate of a Deep-reinforcement-Iearning-based planner and still benefits computationally from the pre-learned optimal policy. Specifically, we show how experiences in the form of a Deep Q-Network can be integrated as heuristic into a heuristic search algorithm. We benchmark our algorithm in the field of path planning in semi-structured valet parking scenarios. There, we analyze the accuracy of such estimates and demonstrate the computational advantages and robustness of our method. Our method may encourage further investigation of the applicability of reinforcement-learning-based planning in the field of self-driving vehicles.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Experience-Based Heuristic Search: Robust Motion Planning with Deep Q-Learning


    Contributors:


    Publication date :

    2018-11-01


    Size :

    650793 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Heuristic algorithms for motion planning

    Eldershaw, C | BASE | 2016

    Free access


    Motion Planning under Perception and Control Uncertainties with Space Exploration Guided Heuristic Search

    Chen, Chao / Rickert, Markus / Knoll, Alois | British Library Conference Proceedings | 2017


    A TRAFFIC KNOWLEDGE AIDED VEHICLE MOTION PLANNING ENGINE BASED ON SPACE EXPLORATION GUIDED HEURISTIC SEARCH

    Chen, C. / Rickert, M. / Knoll, A. et al. | British Library Conference Proceedings | 2014