I-Corps: Automated pavement condition survey system to improve cost-effectiveness

Award ID: 2051192

The broader impact/commercial potential of this I-Corps project is the development of a more cost-effective, automated, pavement condition data collection system. In a pavement management system (PMS), accurate, precise, and reliable pavement condition data will assist pavement engineers to make sound maintenance decisions. While a manual data collection method is labor intensive, time consuming, and frequently impossible or unsafe to perform, the automated data collection methods are receiving more attention in industry and replacing manual surveys in recent years. There are problems with inaccuracy with the existing automated pavement data collection methods. The collection technology proposed in this project is designed to improve the data quality of automated pavement data collection at a sustainable cost. A successful application of the proposed technology may help maintain transportation infrastructure and the technology may be extended to other infrastructure systems such as airport runways, railroads, bridges, and dams. This I-Corps project is based on the development of a more cost-effective, automated, pavement condition data collection system. To overcome the inaccuracy problems associated with existing automated pavement data collection methods, the proposed technology is expected to use more sophisticated and smarter image processing algorithms. In addition, the proposed system seeks improvements in data quality assurance by using data analysis capabilities to screen and validate the data, locating problematic data and reducing errors in the data. The core components of this system are: 1) a cost-effective 3D image acquisition hardware system; 2) artificial intelligence-enhanced pavement image processing algorithms; and 3) systemic design and optimization-based data quality assurance. The design utilizes sensor technologies, statistical theories, 3D reconstruction models, deep learning algorithms, and synthetic ground truth data functionality in the development of this technology. 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.

NSF Program Director: Ruth Shuman