SYSTEMATIC REVIEW ON THE IMPACT OF AI-ENHANCED TRAFFIC SIMULATION ON U.S. URBAN MOBILITY AND SAFETY

Abstract

The rapid growth of urban populations in the United States has intensified challenges related to traffic congestion, safety, and sustainable mobility. Artificial Intelligence (AI)-enhanced traffic simulation has emerged as a transformative tool to address these issues by integrating advanced data analytics, predictive modeling, and real-time decision-making into traditional traffic management systems. This systematic review evaluates the impact of AI-enhanced traffic simulation on U.S. urban mobility and safety, synthesizing findings from peer-reviewed studies, transportation reports, and government publications published over the past two decades. The review highlights how machine learning algorithms, reinforcement learning, and deep learning frameworks are applied to optimize signal control, predict traffic flow, and improve incident response times. Evidence suggests that AI-driven simulations significantly reduce travel delays, fuel consumption, and emissions while enhancing pedestrian and vehicular safety through proactive risk detection and adaptive traffic control. Furthermore, case studies from major U.S. metropolitan areas demonstrate the potential of AI systems to integrate with smart infrastructure and connected vehicles, enabling dynamic rerouting and congestion mitigation strategies. However, challenges remain in terms of data standardization, model scalability, cybersecurity, and equitable deployment across diverse urban contexts. By systematically analyzing the strengths, limitations, and emerging trends of AI-based simulations, this review provides insights for policymakers, urban planners, and transportation engineers seeking to foster safer, more efficient, and resilient mobility systems. Ultimately, AI-enhanced traffic simulation offers a promising pathway toward advancing sustainable urban transportation in the United States.