Neurofuzzy Control to Actuated-Coordinated System at Closely-Spaced Intersections

Abstract

This paper presents a neurofuzzy signal control system to improve the efficiency at closely-spaced signalized intersections. Building on the conventional actuated-coordinated control system, the neurofuzzy controller establishes a “secondary coordination” between the upstream coordinated phase and the downstream non-coordinated phase based on real-time traffic demand. Under the neurofuzzy signal control, the traffic from the upstream intersection can arrive and join the queue at the downstream left turn lane and be served, and therefore reduce the possibility of being delayed at the downstream intersection. The membership functions in the fuzzy controller are calibrated to further the performance. The simulation results indicate that the neurofuzzy signal control consistently outperformed to the conventional actuated-coordinated controller, in terms of reduction in system-wide average delay and average number of stops per vehicle, under a wide range of traffic volumes, especially under higher demand conditions.