[3K3-GS-10] AI application: trafic

[3K3-GS-10-01] Traffic Signal Split Control Method for Traffic Flow Facilitation

〇Ken Hayashi¹, Ryu Fujimori¹, Satoshi Suga¹, Yuji Yamada¹, Fumito Ihara¹, Daiki Takamura¹, Satoshi Kurihara² (1. Graduate School of Science and Technology,Keio University, 2. Faculty of Science and Technology,Keio University)

Keywords:ITS, Multi-Agent System, Intelligent Control

Currently, traffic congestion is a serious problem in urban areas around the world because it causes various problems such as economic loss, air pollution, and an increase in traffic accidents. In order to solve this problem, research on the operation of traffic signals using appropriate parameters at intersections, which are considered to be one of the causes of traffic congestion, has been actively conducted. In Japan, traffic signals are currently controlled by using predetermined control parameters or by using a centralized control system called a traffic control system. In particular, one of the latter methods, MODERATO, has been introduced at major intersections, but this method has some problems such as a lack of flexibility in expanding and contracting the control area and a lack of quick response in a dynamic environment. In this paper, a split control method for traffic signals using a spring model and an autonomous decentralized control method based on the spring model are used to smooth traffic flow. The spring model models the relationship between traffic flow and splits based on the spring balance equation. The results show that the proposed method can appropriately control intersections with various shapes and has a superior traffic flow smoothing effect compared to the current control method.