RT info:eu-repo/semantics/conferenceObject
T1 Intelligent Traffic Light Management using Multi-Behavioral Agents
A1 Cruz Piris, Luis de la
A1 Rivera Pinto, Diego
A1 Marsá Maestre, Iván
A1 Hoz de la Hoz, Enrique de la
A1 Fernández Melián, Susel
K1 Multi-Agents System
K1 Intelligent Transportation Systems (ITS)
K1 Smart Cities
K1 Sensor Networks
K1 Traffic Simulations
K1 Telecomunicaciones
K1 Telecommunication
AB One of the biggest challenges in modern societies is to solve vehicular traffic problems. In this scenario, our proposal is to use a Multi-Agent Systems (MAS) composed of three types of agent: traffic light management agents, traffic jam detection agents, and agents that control the traffic lights at an intersection. This third type of agent is able to change its behaviour between what we have called a selfish mode (the agent will try to influence the other neighbour agents of its type to achieve its goal) or an altruistic mode (the agent will take into consideration the other neighbour selfish agents indications). To validate our solution, we have developed a MAS emulator which communicates with the Simulation of Urban MObility (SUMO) traffic simulator using the Traci tool to realize the experiments in a realistic environment. The obtained results show that our proposal is able to improve other existing solutions such as conventional traffic light management systems (static or dynamic) in terms of reduction of vehicle trip duration.
PB Editorial Universitat Politècnica de Valencia
SN 978-84-9048-595-8
YR 2017
FD 2017-09-27
LK http://hdl.handle.net/10017/32155
UL http://hdl.handle.net/10017/32155
LA eng
NO XIII Jornadas de Ingeniería Telemática, 27/09/2017-29/09/2017, Valencia, España.
NO Ministerio de Economía y Competitividad
DS MINDS@UW
RD 30-abr-2024