Intersection is one of the most complex and accident-prone urban traffic scenarios for autonomous driving wherein making safe and computationally efficient decisions with high-density traffic flow is usually non-trivial. Current rule-based methods decompose the decision-making task into several serial sub-modules, resulting in long computation time at complex scenarios for on-board computing devices. In this paper, we formulate the decision-making and control problem under intersections as a process of optimal path selection and tracking, where the former selects a path with the best safety measure from a set generated only considering static information, while the latter then considers dynamic obstacles and solve a tracking problem with safety constraints using the chosen path. To avoid the heavy computation introduced by that, we develop a reinforcement learning algorithm called generalized exterior point (GEP) to find a neural network (NN) solution offline. It first constructs a multi-task problem involving all the candidate paths and transforms it into an unconstrained problem with a penalty on safety violations. Afterward, the approximate feasible optimal control policy is obtained by alternatively performing gradient descent and enlarging the penalty. As an exterior point type method, GEP permits control policy to violate inequality constraints during the iterations. To verify the effectiveness of our method, we carried out experiments both in simulation and in a real road test. Results demonstrate that the learned policy can realize collision-free driving under different traffic conditions while reducing the computation time by a large margin.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learn collision-free self-driving skills at urban intersections with model-based reinforcement learning


    Beteiligte:
    Guan, Yang (Autor:in) / Ren, Yangang (Autor:in) / Ma, Haitong (Autor:in) / Li, Shengbo Eben (Autor:in) / Sun, Qi (Autor:in) / Dai, Yifan (Autor:in) / Cheng, Bo (Autor:in)


    Erscheinungsdatum :

    2021-09-19


    Format / Umfang :

    2250001 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Model-free Deep Reinforcement Learning for Urban Autonomous Driving

    Chen, Jianyu / Yuan, Bodi / Tomizuka, Masayoshi | IEEE | 2019


    Pedestrian Collision Prediction Models for Urban Intersections

    Lyon, Craig / Persaud, Bhagwant | Transportation Research Record | 2002


    Eco-driving at signalized intersections: a parameterized reinforcement learning approach

    Jiang, Xia / Zhang, Jian / Li, Dan | Taylor & Francis Verlag | 2023



    Pedestrian Collision Prediction Models for Urban Intersections

    Lyon, C. / Persaud, B. / Transportation Research Board | British Library Conference Proceedings | 2002