This study describes an AI-powered smart transportation system that optimizes real-time vehicle routes, transforming transportation networks. The technique creates a road network graph using real-time traffic data from many sources. The graph weights road risk and crowding. It employs heuristics to calculate the shortest route for an automobile while adapting to traffic circumstances. The technology responds to collisions and road closures by predicting what will happen, ensuring vehicles follow the shortest routes. The proposed technique outperforms six existing models in traffic flow efficiency, route planning, system latency, and energy use. The proposed system is excellent at real-time decision-making, vehicle communication, growth, and error handling. Thus, it is a versatile and durable Internet of Vehicles solution. The findings reveal that the proposed strategy might improve transportation safety and efficiency, making it a desirable smart city option. This technology improves real-time automobile tracking and transportation network efficiency and durability.