The invention discloses a reinforcement learning traffic signal control method based on safety consciousness aggregation. The method comprises the following steps: constructing a model; the method for training the model comprises the following steps of: 1, acquiring historical state information; 2, updating a first module, wherein the first module comprises a state encoder, an action-state encoder, an overflow encoder and a waiting encoder; 3, updating a second module, wherein the second module comprises an actor network, a reward criminator network, an overflow cost criminator network and a waiting time criminator network; 4, repeating the step 1 to the step 3 until a preset number of times is exceeded, and obtaining a trained model; and obtaining observation information at the current moment, and inputting the observation information at the current moment into the trained actor network to obtain a current action so as to control a traffic signal. According to the method, the safety is integrated into three aspects of environment interaction, state representation and strategy learning, so that the traffic safety is improved.

    本发明公开了一种基于安全意识聚集的强化学习交通信号控制方法,包括:构建模型;训练所述模型,包括:步骤一:获取历史状态信息;步骤二:更新第一模块,所述第一模块包括状态编码器、动作‑状态编码器、溢流编码器和等待编码器;步骤三:更新第二模块,所述第二模块包括行动者网络、奖励批评者网络、溢流代价批评者网络和等待时间批评者网络;步骤四:重复步骤一至步骤三,直至超过预设次数,得到训练后的模型;获取当前时刻的观测信息,将当前时刻的观测信息输入至训练后的行动者网络中,得到当前动作以控制交通信号。本发明将安全性融入到环境交互、状态表征以及策略学习三方面,提高交通的安全性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement learning traffic signal control method based on safety consciousness aggregation


    Weitere Titelangaben:

    一种基于安全意识聚集的强化学习交通信号控制方法


    Beteiligte:
    REN YILONG (Autor:in) / FU XIANG (Autor:in) / YU HAIYANG (Autor:in) / JIANG HAN (Autor:in)

    Erscheinungsdatum :

    28.01.2025


    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 control method and system based on safety reinforcement learning

    REN YILONG / FU XIANG / YU HAIYANG et al. | Europäisches Patentamt | 2025

    Freier Zugriff

    Reinforcement learning-based traffic signal control

    Sheng, Liu Tian / Azman, Afizan Bin / Khan, Navid Ali et al. | IEEE | 2024


    Deep Reinforcement Learning-Based Traffic Signal Control

    Hu, Penghui / Zhang, Xinran / Hu, Jianming | ASCE | 2024


    Traffic signal control method based on reinforcement learning

    LONG SHUI / YU JIADI | Europäisches Patentamt | 2023

    Freier Zugriff

    Deep Reinforcement Learning-based Traffic Signal Control

    Ruan, Junyun / Tang, Jinzhuo / Gao, Ge et al. | IEEE | 2023