AI-Driven Traffic Management Planning for Construction Zones

Abstract: Effective construction zone management is crucial for ensuring both worker and public safety, maintaining smooth traffic flow, and minimizing disruptions in urban mobility. Poor management can result in project delays, increased risk of accidents, and unplanned road closures that exacerbate congestion and economic impacts. While AI has shown potential in optimizing various aspects of urban planning and infrastructure management, its application in automating the development of transportation management plans (TMPs) for construction zones remains underexplored. In this study, we examine the ability of AI to autonomously generate comprehensive TMPs for construction zones, guided by real-world standards and practical examples. Specifically, we utilize the Maryland State Highway Administration (MSHA) Work Zone Analysis Guide, which outlines eight common scenarios for TMP development and alternatives. By leveraging AI techniques, we aim to identify to what extent that AI can address the complexity of coordinating safety protocols, traffic control measures, and resource allocation in TMP for various construction zone types. Our research demonstrates the role AI could play in enhancing decision-making processes, streamlining planning, and mitigating risks associated with human error. This investigation contributes to the broader understanding of integrating AI for proactive management of transportation in construction zones to improve efficiency and safety outcomes