Towards a Framework for Intelligent Urban Traffic Routing

Abstract

Intelligent traffic routing is one of the key techniques that can be used to optimise traffic, especially in urban areas. Deliberative reasoning techniques such as Automated Planning have shown their potential since they can take a global and longer-term perspective on the traffic situations. Such techniques have to be embedded in a urban traffic control framework such that they can generate and assign routes to the vehicles on the fly while considering the current traffic situation in the area.

This paper presents an ongoing work on a framework that, in a nutshell, integrates an automated planning component, responsible for intelligent traffic routing, in the well known SUMO simulator in order to evaluate and study its impact in realistic traffic settings. In particular, the framework has to simplify the representation of the road network provided by SUMO, translate it into PDDL, a language for describing planning problems, and then interpret plans and fed them in form of vehicle routes into SUMO.