JSAI2022

Presentation information

General Session

General Session » GS-10 AI application

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

Thu. Jun 16, 2022 1:30 PM - 3:10 PM Room K (Room K)

座長:藤井 秀樹(東京大学)[現地]

1:30 PM - 1:50 PM

[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.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password