Abstract

In this paper we will discuss a traffic light controller based on a Fuzzy Inference System (FIS) that can control multiple traffic intersections. The controller can adjust adaptively the phase lengths and phase sequences to optimize the movement of vehicles that will move straight or that will turn right. The
Fuzzy System consists of three main modules namely the Green Phase Module, the Red Phase Module and the Decision Module. This system will determine which path will get the green phase and how long the green phase is given. A simulator for the intersection group has been developed to test the performance of the controller. The proposed controller is compared with two other traffic light controllers namely preset-cycle times (PCT) and vehicle-actuated (VA) controllers. The average delay time is used as the performance index. The results of simulation show good performances of proposed contoller over the PCT and AV controller. But in heavy traffic conditions, only a small improvement can be made.