NSF Award
2431246
Right-of-way closures, i.e., the closing of streets, bike lanes, sidewalks, and roads, frequently occur in urban areas due to construction projects, cargo delivery, and special events. Dynamic construction schedules, lack of compliance, and potentially outdated technological systems hinder the ability of city transportation authorities to effectively issue, monitor, and inspect permits, leading to compliance violations and traffic disruptions. The rate of permit violations is exceptionally high in urban areas, and the cost of these violations and the resulting inspections is staggering: Nashville Department of Transportation (NDOT) currently loses an estimated $2 million from the unpaid permit fees alone and pays external contractors an estimated $5 million annually for inspection. Most importantly, road closures (particularly illegal closures and violations) harm traffic, commuter safety, and local businesses. This problem is not restricted to Nashville alone; urban areas across the USA face challenges with enforcing and monitoring right-of-way closures. This project is a collaboration between Vanderbilt University, NDOT, the Metropolitan Government of Nashville, and Nashville Metropolitan Information Technology Services (ITS) to tackle these challenges through fundamental and civic-engaged research. Specifically, this project will design and develop data-driven artificial intelligence models that will 1) automate the detection of permit violations and 2) estimate the effects of right-of-way closures to optimize future permit issuance. <br/><br/>Our goal of automating the detection of right-of-way closures and estimating the impact of future closures requires fundamental advances in data science, machine learning, and software engineering. Specifically, the intellectual merit of our project lies in 1) the design and implementation of novel neural network architectures to automatically detect road closures; 2) the design and implementation of a data-driven approach to infer locations of road closures from heterogeneous and noisy crowdsourced data; 3) the development of an urban digital twin to estimate the effect of road closures in Nashville; 4) the development of an optimization engine for the issuance of right-of-way permits; and 5) system and data integration to deploy the proposed technology in Nashville. The resulting technical framework will be available for other urban areas, and it will apply to problems beyond right-of-way monitoring, e.g., emergency response and traffic management, and generally to the broader problem of monitoring societal-scale cyber-physical systems.<br/><br/>This project is in response to the Civic Innovation Challenge program’s Track B. Bridging the gap between essential resources and services & community needs and is a collaboration between NSF, the Department of Homeland Security, and the Department of Energy.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
