A multi-agent simulation platform applied to the study of urban traffic lights
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
Institute for Systems and Technologies of Information, Control and Communication (INSTICC)Date
2011Citation
10.5220/0003509701540159
6th International Conference on Software and Data Technologies, ICSOFT 2011. INSTICC 2011. 154-159
DOI
10.5220/0003509701540159Funded by
This work has been partially supported by the Spanish Ministry of Science and Innovation under grant TIN2010-19872 and by Jobssy.com.Project
Gobierno de España. TIN2010-19872Editor's Version
http://dx.doi.org/10.5220/0003509701540159Subjects
Distributed system; Software engineering; Swarm computing; InformáticaNote
Proceedings of 6th International Conference on Software and Data Technologies, ICSOFT 2011Rights
© 2011 - INSTICC and/or its suppliers. All rights reservedAbstract
The Multi-Agent system paradigm allows the development of complex software platforms to be used in a wide range of real-world scenarios. One of the most successful areas these technologies have been applied are in the simulation and optimization of complex systems. Traffic simulation/optimization problems are a specially suitable target for such a platform. This paper proposes a new Multi-Agent simulation platform, where agents are based on a Swarm model (lightweight agents with very low autonomy or proactivity). Using this framework, simulation designers are free to configure road networks of arbitrary complexity, by customizing road width, geometry and intersection with other roads. To simulate different traffic flow scenarios, vehicle trajectories can be defined by choosing start and end locations and providing traffic generation functions for each one trajectory defined. Finally, how many vehicles are generated at each time step can be determined by a time series function. The domain of traffic simulation has been selected to investigate the effect of traffic light configuration on the flow of vehicles in a road network. The experimental results from this platform show a strong correlation between traffic light behavior and the flow of traffic through the network that affects the congestion of the road.
Files in this item
Google Scholar:Cajías Hostos, Raúl
-
González-Pardo, Antonio
-
Camacho, David
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.
-
A multi-agent traffic simulation framework for evaluating the impact of traffic lights
Cajías Hostos, Raúl; González-Pardo, Antonio; Camacho, David
2011 -
A case study on grammatical-based representation for regular expression evolution
González-Pardo, Antonio; Barrero, David F.; Camacho, David; R-Moreno, María Dolores
2010 -
An empirical study on collective intelligence algorithms for video games problem-solving
González-Pardo, Antonio; Palero, Fernando; Camacho, David
2015