Virtual Crowds and probabilistic planning for automatic control of traffic lights

• Grant number: 09/12690-6
• Support Opportunities: Scholarships in Brazil - Master
• Start date: March 01, 2010
• End date: August 31, 2011
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Jacques Wainer
• Grantee: Renato Schattan Pereira Coelho
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

The main goal of this project is to build a system that receives a description of a trafficnetwork and returns an optimal policy for the traffic flow control in the region. To achieve this goal the system puts together algorithms from two well developed areas in Artificial Intelligence: probabilistic planning and virtual crowds. Although both areas present good algorithms their use is limited by their reliance on specialists, whether to describe the probabilistic planning problem or to analyze the data produced by the simulations. Our approach will contribute to minimize this dependence by using the simulations output to describe the probabilistic planning problem. The solution to this problem is a reactive policy that should save time and money spent in traffic jams. Apart from its practical benefits our system advance the research of Artificial Intelligence by bringing together two areas that are normally used separately.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

COELHO, Renato Schattan Pereira. Crowd simulation and probabilistic planning for traffic light optimization. 2012. Master's Dissertation - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.