Presentation 2001/11/8
Multi Agent-based Traffic signal Control for the Decrease of Stop Conditions
Tadanobu MISAWA, Tsuyoshi KODAKE, Haruhiko KIMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In modern society, traffic jams and accidents are increasing. One of the schemes of improvement is to control traffic signals. Multi-agent system is applied to traffic signal control problem in many studies. However, evoluational methods is different in each study. In this study, a evoluational method is the number of stop conditions. We think that the decrease of stop conditions will contribute not only to ease traffic jams but also to decrease of exhaust fumes. In this paper, we propose a multi-agent system which guess stop conditions and adapts environment by learning. We simulate this system and show the usefulness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) traffic signal control / multi-agent system / reinforcement learning / cooperation
Paper # AI2001-33
Date of Issue

Conference Information
Committee AI
Conference Date 2001/11/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Multi Agent-based Traffic signal Control for the Decrease of Stop Conditions
Sub Title (in English)
Keyword(1) traffic signal control
Keyword(2) multi-agent system
Keyword(3) reinforcement learning
Keyword(4) cooperation
1st Author's Name Tadanobu MISAWA
1st Author's Affiliation Faculty of Engineering, Kanazawa University()
2nd Author's Name Tsuyoshi KODAKE
2nd Author's Affiliation Faculty of Engineering, Kanazawa University
3rd Author's Name Haruhiko KIMURA
3rd Author's Affiliation Faculty of Engineering, Kanazawa University
Date 2001/11/8
Paper # AI2001-33
Volume (vol) vol.101
Number (no) 419
Page pp.pp.-
#Pages 6
Date of Issue