• Kripal Sp
• Muhammad Zain P M
• Muhammed Irfan
• Vivek KrishnanT
• Mrs. Smitha M

In This project focuses on building and simulating an AI-based traffic management system to help improve traffic flow in cities. The system uses live video input to detect how many vehicles are at an intersection and then uses machine learning to decide how long each signal should stay green. Instead of using fixed timers, the system adjusts signal timings based on actual traffic, which helps reduce waiting time and congestion. We evaluated the model in a simulated setting to determine how well it operates under several traffic scenarios. The core components of the system involve detecting vehicles through computer vision, analyzing traffic congestion levels, and making decisions using reinforcement learning techniques. The AI continuously improves by learning from both real-time and historical data. To evaluate how well the system performs, we focused on metrics such as the average wait time, the length of traffic queues, and the number of vehicles moving through each intersection. All things considered, this initiative demonstrates how artificial intelligence may be applied to improve traffic lights’ intelligence and reactivity.

AI traffic system, smart city, machine learning, traffic simulation, adaptive signals, computer vision.

"AI POWERED TRAFFIC MANAGENENT SYSTEM USING SIMULATION: A SURVEY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.549-552, July-2025, Available :http://www.jetir.org/papers/JETIRGX06106.pdf

"AI POWERED TRAFFIC MANAGENENT SYSTEM USING SIMULATION: A SURVEY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp549-552, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06106.pdf