A Hybrid Fuzzy-Genetic Controller for a multi-agent intersection control system

Over the years, traffic congestion has grown into one of today's global problems. Intersections are a major cause of this problem. Thus proper management of the intersections, will reduce congestion consequently. In this study, an intelligent Intersection Control System (ICS) is proposed to control traffic flow in intersections. Treating the problem as a Multi-Agent System (MAS), two types of agents inhibit this environment. The Intersection Manager Agent (IMA) is responsible for vehicles coordination in the intersection. The Driver Agent (DA) is implemented on each vehicle to control it. Through predicting the trajectories of the vehicles, minimizing their travel times is possible while avoiding any predicted collision. A Hybrid Fuzzy-Genetic controller is implemented in the ICS. The Fuzzy Logic Controller (FLC) is responsible for evaluating the appropriate action for each vehicle. While the Genetic Algorithm (GA) tunes the parameters of the FLC output fuzzy sets. Using the optimized hybrid controller, the intersection performance under different traffic capacities is studied. The results are compared with the existing traffic-light system, and the un-optimized FLC. Results obtained significantly improved the intersection utilization, increasing its throughput by 91%, while decreasing the vehicles' Average and Maximum delay times by 62% and 72% respectively.