ARTIFICIAL INTELLIGENCE FOR URBAN TRANSPORTATION MANAGEMENT: DIGITAL TWINS, SIMULATION, AND OPTIMIZATION USING AI, GENAI, AND GAME THEORY

Abstract

As cities get more crowded, transportation management is getting tougher. This research proposes a new framework using Artificial Intelligence (AI), Generative AI (GenAI) and Game Theory to build intelligent digital twins for urban transportation. We combine real-time data from multiple sources to create a digital copy of the transportation network so we can simulate, predict and optimise. By using AI and GenAI we can forecast traffic, find congestion hotspots and design control strategies. Game-theoretic approaches are used to model the interactions between different stakeholders and optimise decision making. Our framework aims to boost traffic productivity, cut down on congestion, and make roads safer leading the transportation scene towards what's best for society. This study shows how AI-powered digital twins can shake up city transport management. We want to gather look into, and uncover travel habits from big data using different kinds of traffic sensors, including devices that track individuals. We'll use this info to help us model and predict changes in altered transport systems. In the end, we hope to help those in charge grasp the changes coming their way and get them ready to plan and run next-gen transport systems.