Strategies and Implementation Methods for Artificial Intelligence-Assisted Real-Time Traffic Management

Abstract

This thesis explores the integration of artificial intelligence (AI) technologies into real-time traffic management systems, focusing on how AI can enhance urban mobility, efficiency, and sustainability. It systematically reviews key algorithmic approaches—including machine learning, deep learning, reinforcement learning, and swarm intelligence—and evaluates their effectiveness in tasks such as traffic signal control, flow forecasting, and route optimisation. Through comparative case studies from cities like Los Angeles, Singapore, Shenzhen, and London, the research highlights both the practical successes and governance challenges of AI implementation. The study also examines ethical, policy, and social dimensions, emphasising the need for transparency, fairness, and data privacy in intelligent transport systems. Overall, the thesis contributes both theoretical insights and practical guidance for developing sustainable, AI-driven urban traffic solutions.