Design of a Multiagent System for Real-Time Traffic Control

• Type: Another Publication in an International Scientific Journal
• Date: 2016

Authors

Cristina Vilarinho (Author) Other; José Pedro Tavares (Author) FEUP; Rosaldo J. F. Rossetti (Author) FEUP

Journal

Title: IEEE Intelligent Systems

Vol. 31

Pages: 68-80

ISSN: 1541-1672

Publisher: IEEE

Indexing

ISI Web of Knowledge - 7 Citations

Scopus - 10 Citations

Other information

Authenticus ID: P-00K-VGS

DOI: 10.1109/MIS.2016.66

Abstract (EN): This article describes the various steps to analyze and design a multiagent system for real-time traffic control at isolated intersections. The control strategies for traffic signals are important because they impact the economy, environment, and society and also affect freight transport, which many researchers have studied over the years. The research community has focused on the optimization of traffic signal plans. Although these efforts have been relatively successful, the strategies lack flexibility, which limits their effectiveness. In addition to defining the best traffic plan at the design phase, researchers must aim to maintain the system optimized during the operation phase. In this way, the research target is to develop an approach for controlling traffic signals that relies on flexibility and maximum freedom in control, in which the system is updated frequently to meet traffic demand, taking into account different traffic users. This study's main outcome is a conceptual model of a novel perspective of a multiagent system for real-time traffic control at isolated intersections. This model, which was based on the Gaia methodology, introduces a new perspective in which each isolated intersection is itself a multiagent system. The many agents designed for isolated intersections create, manage, and evolve their own traffic signal plans. Therefore, this proposed multiagent control brings the benefit of staged designs and sequences being formed as needed instead of being established a priori. © 2016 IEEE.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 13