APPLICATION OF FUZZY LOGIC IN DECISION-MAKING SYSTEMS FOR URBAN TRAFFIC MANAGEMENT

Abstract

The rapid growth of urban populations and increased vehicular traffic have intensified congestion, pollution, and travel delays in cities. Traditional traffic management systems, often based on fixed-time signal control, fail to adapt to dynamic traffic conditions, necessitating more intelligent solutions. This study explores the application of Fuzzy Logic in urban traffic management, demonstrating its potential for optimizing real-time traffic signal control. Fuzzy Logic, an extension of classical logic, effectively handles uncertainties and imprecise data, making it particularly suitable for traffic environments where variables such as traffic volume, waiting time, and weather conditions fluctuate continuously. By employing Fuzzy Logic, traffic light controllers can dynamically adjust signal durations to optimize vehicle flow. The system utilizes input variables such as real-time traffic volume, accumulated waiting time, and environmental factors to determine optimal signal timings through a fuzzy inference engine. This adaptive approach enhances mobility, reduces congestion, minimizes fuel consumption, and improves road safety. Simulation results and case studies indicate that Fuzzy Logic-based traffic management significantly outperforms fixed-time signal control by reducing average waiting times and improving overall traffic efficiency. Furthermore, integrating reinforcement learning and game theory into Fuzzy Logic models shows promising results in cooperative multi-agent decision-making for large-scale urban traffic networks. Despite challenges related to data collection and implementation, the use of intelligent traffic control systems can play a pivotal role in achieving sustainable urban mobility