The invention discloses a reinforcement learning-based traffic cooperation signal control method and system. The method comprises the steps of obtaining target traffic flow data; modeling the target traffic flow data by adopting a cellular transmission model to obtain target cellular data; constructing intersection state data of the road intersection according to the cellular state data of the target cellular data; inputting the intersection state data into a target agent value network in a target signal control agent, and outputting a target phase action corresponding to the intersection state data; the target signal control agents are constructed based on deep reinforcement learning, and one target signal control agent corresponds to one intersection signal lamp of the road intersection; and controlling an intersection signal lamp of the road intersection according to the target phase motion. The method can respond to the change of traffic flow in real time so as to make real-time adjustment according to real-time traffic conditions, improve traffic fluency, reduce traffic congestion and optimize traffic efficiency, and can be widely applied to the technical field of traffic control.
本申请公开了基于强化学习的交通协同信号控制方法和系统,方法包括:获取目标交通流数据;采用元胞传输模型对目标交通流数据进行建模,得到目标元胞数据;根据目标元胞数据的元胞状态数据构建道路交叉口的交叉口状态数据;将交叉口状态数据输入至目标信号控制智能体中的目标智能体价值网络,输出交叉口状态数据对应的目标相位动作;目标信号控制智能体基于深度强化学习构建,一个目标信号控制智能体对应道路交叉口的一个交叉口信号灯;根据目标相位动作控制道路交叉口的交叉口信号灯。能够实时响应交通流量的变化,以根据实时交通情况做出即时调整,改善交通流畅度和减少交通拥堵,优化通行效率,可广泛应用于交通控制技术领域。
Traffic cooperation signal control method and system based on reinforcement learning
基于强化学习的交通协同信号控制方法和系统
16.08.2024
Patent
Elektronische Ressource
Chinesisch
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Reinforcement learning-based traffic signal control
IEEE | 2024
|Traffic signal control method based on reinforcement learning
Europäisches Patentamt | 2023
|Deep Reinforcement Learning-based Traffic Signal Control
IEEE | 2023
|Deep Reinforcement Learning-Based Traffic Signal Control
ASCE | 2024
|