The Stadtpilot project aims at fully automated driving on Braunschweig's inner city ring road. The TU Braunschweig's research vehicle “Leonie” is one of the first vehicles having the ability of fully automated driving in real urban traffic scenarios. This paper shows our decision making approach for performing lane changes while driving fully automated in urban environments. We apply an online Partially Observable Markov Decision Process (POMDP) to accommodate inevitable sensor noise to be faced in urban traffic scenarios. In this paper we propose a two step algorithm to keep the complexity of the POMDP low enough for real-time decision making while driving. The presented approach has been integrated in our vehicle and was evaluated in real urban traffic.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Probabilistic online POMDP decision making for lane changes in fully automated driving


    Beteiligte:
    Ulbrich, Simon (Autor:in) / Maurer, Markus (Autor:in)


    Erscheinungsdatum :

    2013-10-01


    Format / Umfang :

    2174023 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Situation-aware decision making for autonomous driving on urban road using online POMDP

    Liu, Wei / Kim, Seong-Woo / Pendleton, Scott et al. | IEEE | 2015


    Tutorial on Sampling-based POMDP-planning for Automated Driving

    Bey, Henrik / Tratz, Maximilian / Sackmann, Moritz et al. | TIBKAT | 2020


    Improving Automated Driving Through POMDP Planning With Human Internal States

    Sunberg, Zachary / Kochenderfer, Mykel J. | IEEE | 2022


    An IMM-based POMDP decision algorithm using collision-risk function in mandatory lane change

    Huang, Yunfeng / Zhao, Wanzhong / Xu, Can et al. | SAGE Publications | 2022


    HYBRID ONLINE POMDP PLANNING AND DEEP REINFORCEMENT LEARNING FOR SAFER SELF-DRIVING CARS

    Pusse, Florian / Klusch, Matthias | British Library Conference Proceedings | 2019