Adaptive Two-stage Fuzzy Logic Controllers for Urban Traffic Signals at Isolated Intersections

This paper presents two optimal approaches of two-stage fuzzy controller for traffic signals at isolated intersections. Firstly, in the light that traffic status variables in two-stage controller leads to the inefficiency of traffic status weakening under low traffic flow, a two-stage combination fuzzy controller is designed from the perspective of structural optimization; this controller introduces 0-1 combination and determines the variables of fuzzy controller’s inputs according to real-time traffic status identification. Secondly, aiming at the problems of fuzzy controller parameter empirical settings and functional disability of learning, a two-stage fuzzy logic traffic signal controller with online optimization is proposed; this controller introduces the rolling horizon framework and optimizes parameters of membership functions and controller rules by an improved hybrid genetic algorithm. The performance of the two proposed models is validated via online Paramics-based simulation platform, and extensive relative simulation tests have demonstrated the potential of the proposed controllers for adaptive traffic signal control.