Growing urbanization and the rapid increase in vehicles have made traffic congestion, air pollution, and delayed emergency response serious problems in today’s cities. Most existing traffic control systems still depend on fixed or partially adaptive signal timings, which are not capable of handling real-time traffic variations, environmental impacts, or emergency situations effectively. To overcome these limitations, this project presents an AI-Powered Eco Traffic Management and Simulation System that brings together artificial intelligence, IoT, wireless communication, and renewable energy into a single, practical solution.

The proposed system is designed around four key components. First, an AI-based traffic signal control module uses reinforcement learning to adjust signal timings dynamically according to real- time traffic density, queue length, and past traffic patterns, helping to reduce congestion and vehicle waiting time. Second, an ESP-NOW-based ambulance detection system using ESP32 controllers provides instant, low-latency communication within a 15-meter range, allowing traffic signals to automatically give priority to emergency vehicles. Third, a CO₂ and pollution filtration duct system, equipped with activated carbon and HEPA filters, actively removes harmful vehicular emissions at busy intersections, improving local air quality. Finally, the entire system is powered by solar energy, ensuring reliable operation while reducing dependence on conventional grid power.

The system is evaluated using traffic simulations in SUMO combined with Python-based AI models, followed by prototype-level testing. A centralized dashboard enables real-time monitoring of traffic flow, pollution levels, and emergency vehicle movement. Results from simulations and experiments show smoother traffic flow, reduced congestion and emissions, and faster ambulance response times.

In summary, this project offers a practical, scalable, and environmentally friendly approach to smart traffic management. By combining AI-driven decision making, IoT-based sensing, and renewable energy, the system effectively connects academic research with real-world application and contributes toward building safer, cleaner, and more efficient smart cities.