• Deepika Poojari
• Asst. Prof. Gauri Shirsat

Urban traffic management has a significant relevance in dealing concerning congestion and increasing avenue safety in more than nearly every efforts including police operatives and signs towards the commotion and concentration with busy intersections. Conventional design junction traffic management systems have shown an inability and in most cases stagnation to general changes whenever traffic conditions change strategically understudying the main objective traffic performance improvement, delays, and increase. This paper presents a new technological development – an AI-controlled system of traffic regulation that addresses these issues by constant specifying the traffic light schedule to the actual traffic situation. The machine implements technologies of different architectures such as Reinforcement Learning (RL) and Deep Learning (DL) to resolve the problem where traffic information is gathered from multiple sensors camera. The traffic light schedule is controlled such that it is continuously updated fired to the control system towards repetitive achievement of the optimal flow, minimum superiority aid traffic congestion, and increase safety on the road. Further, the solution has been tested via extensive simulations coupled with an implementation of the pilot in a high traffic located city area to determine its effectiveness. The lower waiting time and reasonable reductions in general performance improvement, indicate all improvements traffic flow relative measureable compared with steady state fixed reaction traffic control systems. The current study helps in improving the smart city infrastructure by showcasing how AI-enhanced site visitors management could change the way urban mobility is experienced. The efficient management of traffic is necessary to reduce the excessive build-up of traffic and to improve road safety in urban areas, particularly at busy junctions where traffic is coming in from many directions. General traffic light systems, especially the ones at intersections, usually have problems when called upon to adjust to traffic dynamics resulting in attrition traffic flow and enhanced waiting time. The effectiveness of the proposed solution is tested through a canoe simulation, as well as the pilot conducting in a heavy traffic metropolitan center.

Smart Traffic Management, Artificial Intelligence (AI), Heavy Traffic Routes, Real-time Traffic Data, Adaptive Traffic Signal Control, Intelligent Transportation Systems, Traffic Congestion Mitigation, Urban Traffic Management, Scalable and Flexible Traffic Systems, AI-based Traffic Optimization, etc.

"Smart AI-Based Traffic Management System for Heavy Traffic Routes", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 9, page no.g106-g111, September-2024, Available :http://www.jetir.org/papers/JETIR2409607.pdf

"Smart AI-Based Traffic Management System for Heavy Traffic Routes", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 9, page no. ppg106-g111, September-2024, Available at : http://www.jetir.org/papers/JETIR2409607.pdf