The invention relates to a regional traffic signal timing method and system based on reinforcement learning, and belongs to the technical field of traffic signal timing processing. According to the method, after regional traffic environment data and vehicle track data are subjected to data extraction to obtain intersection and signal lamp composition elements, a regional traffic signal timing task is determined based on the intersection and signal lamp composition elements, then a regional traffic waiting model is constructed based on the regional traffic signal timing task, and finally, the regional traffic waiting model is constructed. A multi-agent reinforcement learning algorithm is adopted to learn and train a regional traffic waiting model, an optimized strategy-based NAC algorithm is combined to complete a coordinated optimization process of each agent strategy in a region, and an RNN recurrent neural network is introduced to process an optimization coordination result generated in the coordinated optimization process to obtain a regional traffic signal timing scheme. And therefore, the problem of dimension disaster in the existing traffic signal timing process can be solved.

    本发明涉及一种基于强化学习的区域交通信号配时方法及系统,属于交通信号配时处理技术领域。本发明在对区域交通环境数据和车辆轨迹数据进行数据抽取得到路口和信号灯构成元素后,基于路口和信号灯构成元素确定区域交通信号配时任务,然后,基于区域交通信号配时任务构建区域交通等待模型,最后,采用多智能体强化学习算法学习训练区域交通等待模型,结合优化后的基于策略的NAC算法完成区域中各智能体策略的协调优化过程,并引入RNN循环神经网络对协调优化过程中产生的优化协调结果进行处理得到区域交通信号配时方案,进而解决现有交通信号配时过程中存在的维度灾难问题。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Regional traffic signal timing method and system based on reinforcement learning


    Weitere Titelangaben:

    一种基于强化学习的区域交通信号配时方法及系统


    Beteiligte:
    WANG HAIQUAN (Autor:in) / FEI YUNFAN (Autor:in)

    Erscheinungsdatum :

    2023-03-03


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Traffic Signal Timing via Parallel Reinforcement Learning

    Zhao, Qian / Xu, Cheng / jin, Sheng | Springer Verlag | 2019


    Adaptive Optimization of Traffic Signal Timing via Deep Reinforcement Learning

    Zibo Ma / Tongchao Cui / Wenxing Deng et al. | DOAJ | 2021

    Freier Zugriff


    METHOD AND APPARATUS FOR CONTROLLING TRAFFIC SIGNAL TIMING BASED ON REINFORCEMENT LEARNING

    LIM YU JIN / JOO HYUN JIN | Europäisches Patentamt | 2021

    Freier Zugriff

    Traffic signal lamp control system and method based on reinforcement learning and dynamic timing

    LIU BINGYI / SONG BIN / WU PENGCHUN et al. | Europäisches Patentamt | 2021

    Freier Zugriff