A Self-learning Traffic Signal Control Approach and Simulation
Zhaoxia Yang · Acta Simulata Systematica Sinica · 2004
This paper applies fuzzy theory and machine learning in the process of traffic signal control. It provides a fuzzy traffic signal control approach based on genetic algorithms for isolated intersection. Through fuzzy classifying the number of arrived cars, this paper puts decision schemes of signal control in different conditions of cars?arriving as rule-set into knowledge-database. It applies genetic algorithm to improve the rule-sets in the course of traffic signal controlling. After programming the simulation program of this control approach and simulating, this paper compares the control effect of this new approach with fixed-time control method and actuated control method. The result of simulating illustrates that the effect of the new approach is obviously better than the traditional ones.