Traffic congestion on highways causes decreased efficiency in road operation and increased energy consumption and environmental pollution. Various measures for traffic control have been considered for easing traffic congestion. In this paper, we propose the use of ramp metering control by introducing the reinforcement learning model in artificial intelligence, which is then combined with a dynamic micro traffic style simulation. Numerical simulation showed that when effective Reinforcement Learning ramp metering control is completed in the on-ramp section, traffic confusion can be prevented in advance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement Learning Control for On-Ramp Metering Based on Traffic Simulation


    Beteiligte:
    Wang, Xingju (Autor:in) / Liu, Bohang (Autor:in) / Niu, Xueqin (Autor:in) / Miyagi, Toshihiko (Autor:in)

    Kongress:

    Ninth International Conference of Chinese Transportation Professionals (ICCTP) ; 2009 ; Harbin, China


    Erschienen in:

    Erscheinungsdatum :

    23.07.2009




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Reinforcement Learning Control for On-Ramp Metering Based on Traffic Simulation

    Wang, X. / Liu, B. / Niu, X. et al. | British Library Conference Proceedings | 2009


    Reinforcement Learning Ramp Metering Based on Traffic Simulation Model with Desired Speed

    Wang, Xingju / Bao, Jingang / Wang, Mingsheng et al. | ASCE | 2009


    Reinforcement Learning Ramp Metering Based on Traffic Simulation Model with Desired Speed

    Wang, X. / Bao, J. / Wang, M. et al. | British Library Conference Proceedings | 2009


    Ramp metering traffic control system

    Barney, A.F. | Engineering Index Backfile | 1969


    A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data

    Liu, Bing / Tang, Yu / Ji, Yuxiong et al. | ArXiv | 2020

    Freier Zugriff