Proposal of a Pheromone Based Traffic Information Interpolation System

Abstract

Traffic congestion has become one of the social problems in today’s society, so research into appropriate traffic signal control is actively underway. Installing sensors at a vast number of intersections is necessary for more precise and real-time adaptive control, but this is unrealistic from the viewpoint of cost. Therefore, we propose a pheromone-based methodology that interpolates traffic information in the intersections without sensors in real-time. The results show that the proposed methodology has an excellent interpolation performance for heavy traffic flows compared to statistical studies and machine learning methods and can adapt and interpolate to situations where traffic flow changes suddenly. The pheromone-based traffic information interpolation method loses its interpolation accuracy at intersections where traffic flows merge. In this paper, we propose a pheromone-based interpolation method that is adaptable to merging traffic flows.