An agent-based computational approach for urban traffic regulation

This paper proposes a bimodal urban traffic control strategy based on a multi-agent model. We call bimodal traffic, a traffic which takes into account both private vehicles and public vehicles such as buses. The objective of this research is to improve global traffic, to reduce bus delays and to improve bus regularity in congested areas of the network. In our agent-based approach, traffic regulation is obtained thanks to communication, collaboration and negotiation between heterogeneous agents. An important feature of our system is that it allows regulation at two levels: macroscopic and microscopic levels. To model in depth regulation procedures, we have introduced special features such as priority levels for buses, computation and update of traffic signal plans, urgency index of intersection stages depending on the level of congestion on the arcs. We have tested our strategy on a small network of six intersections, using the JADE platform. The simulation is described and preliminary results are presented. They show that our MAS strategy improves bus travel time while improving also private vehicles' travel time, decreases bus delays and improves its regularity compared to a classical strategy called fixed-time control strategy.