Urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization

Sie sind hier: Homepage > Suche

Urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization

Freier Zugriff

CHEN MING / WEI PING / LIN JIAHE / YU YANG / XU CHEN / FENG YUANJING / LI YONGQIANG

The invention relates to an urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization, and the method comprises the steps: obtaining the physical feature information of an intersection through a surveying and mapping method in combination with satellite map data for the field investigation and survey of the intersection which is seriously jammed in a city; the method comprises the following steps of: counting traffic flow information of each lane in each time period every day through an intersection monitoring camera for an intersection which is seriously congested in a city; establishing an intersection simulation model on a microscopic simulation platform according to the intersection physical feature information, and intercepting traffic flow data in a congestion time period according to the traffic flow information of the lane; building a deep neural network model, training a traffic signal lamp phase switching strategy pi theta in the built simulation model based on a Hesse matrix assisted gradient optimization algorithm, and updating a parameter theta of the neural network at the same time; and finally obtaining a training model, wherein the finally obtained signal lamp phase switching strategy is the required signal lamp control strategy. According to the invention, the congestion condition of the intersection is effectively relieved.

一种黑塞矩阵协助梯度优化的城市交叉口交通信号实时控制方法,对于城市中拥堵较为严重的交叉口实地调研，采用测绘方法，结合卫星地图数据，获取得到交叉口的物理特征信息；对于城市中拥堵较为严重的交叉口，通过交叉口监控摄像头，统计每天的各个时间段各个车道的车流量信息；根据交叉口物理特征信息，在微观仿真平台上搭建该交叉口仿真模型，并根据车道的车流量信息，截取拥堵时间段的车流量数据；搭建深度神经网络模型，基于黑塞矩阵协助梯度优化算法，在搭建的仿真模型中训练交通信号灯相位切换策略πθ，同时更新神经网络的参数θ；最终得到训练模型，最终得到的信号灯相位切换策略即为所需的信号灯控制策略。本发明有效缓解交叉口的拥堵情况。

Zugriff

Download

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

Urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization

Weitere Titelangaben:

黑塞矩阵协助梯度优化的城市交叉口交通信号实时控制方法

Beteiligte:

CHEN MING (Autor:in) / WEI PING (Autor:in) / LIN JIAHE (Autor:in) / YU YANG (Autor:in) / XU CHEN (Autor:in) / FENG YUANJING (Autor:in) / LI YONGQIANG (Autor:in)

Erscheinungsdatum :

2024-01-05

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

Urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization

Urban intersection traffic signal real-time control method based on Hesse matrix assisted gradient optimization

Zugriff

Exportieren, teilen und zitieren

Dokumentinformationen

Ähnliche Titel

Zugriff

Seitennavigation

Exportieren, teilen und zitieren