Multi-Agent Systems for Urban Traffic Control

Traffic represents a great problem for large cities. In recent years, the solutions based on the artificial intelligent have been successful in finding results to some of these problems. The area of Multiagent Systems has been showing good results in the past years. This project attempts to use Mult...

Descripción completa

Detalles Bibliográficos
Autor: Amezcua-García, Francisco J.
Tipo de recurso: tesis de maestría
Estado:Versión publicada
Fecha de publicación:2017
País:México
Institución:Instituto Tecnológico y de Estudios Superiores de Occidente
Repositorio:Repositorio Institucional del ITESO
Idioma:inglés
OAI Identifier:oai:rei.iteso.mx:11117/5120
Acceso en línea:http://hdl.handle.net/11117/5120
Access Level:acceso abierto
Palabra clave:Multi-Agent Systems
Urban Traffic
Traffic Control
Descripción
Sumario:Traffic represents a great problem for large cities. In recent years, the solutions based on the artificial intelligent have been successful in finding results to some of these problems. The area of Multiagent Systems has been showing good results in the past years. This project attempts to use Multiagent Systems technology, such as the JADE framework, to investigate solutions to traffic jam in street intersections. In the proposed approach, the agents use a negotiation mechanism to influence the regular traffic light cycle. The implementations use the SUMO simulator and trasMAPI middleware to communicate with the JADE agents. The hypothesis is that using this negotiation table the traffic flow can be improved compared with static traffic lights schemes. The simulations show promissory results that in some cases are like those using static lights. However, the table could be optimized to generate better results accordingly to the specific requirements of a particular application scenario.