I-Corps: Translation potential of a Light Detection and Ranging (LiDAR)-based bridge monitoring and inspection support technology

Award ID: 2628068

This I-Corps project is based on the development of a bridge inspection technology that creates three-dimensional (3D) digital models to evaluate aging infrastructure. Currently, there are more than 600,000 bridges in the U.S. that require routine inspections every 2 years, yet current methods rely heavily on visual assessments, limited measurements, and inconsistent documentation, making it difficult to track deterioration or detect subtle structural changes over time. This leads to costly outcomes, including unnecessary repairs when damage is overestimated and increased risk when deterioration is underestimated. This technology provides rapid, field data collection combined with automated analysis to deliver objective, repeatable, and quantifiable information about structural conditions. It may be used to detect changes in geometry, surface condition, and structural response, which may improve decision making and reduce uncertainty. This technology could be used by transportation agencies, engineering firms, and asset managers seeking more reliable inspection data, streamlined workflows, and enhanced long-term monitoring to improve infrastructure safety and reduce maintenance costs. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of a Light Detection and Ranging (LiDAR)-based inspection and monitoring platform for bridges. The technology integrates semantic segmentation, computer vision, and temporal point cloud comparison to characterize bridge condition. It can process millions of three-dimensional (3D) points and colorized images to automatically identify structural components, classify element types, and detect changes such as deflection, settlement, section loss, or surface deterioration. It uses point cloud analytics, including transformer-based segmentation and geometry aware classification, enabling more accurate interpretation of complex structural environments compared with traditional manual or photo-based methods. Proof-of-concept results show that the technology can be used to extract bridge dimensions, track temporal changes, and generate digital baselines suitable for structural assessment. Users may benefit from improved reliability, reduced subjectivity, and the ability to perform quantitative comparisons across inspection cycles. In addition, data-driven infrastructure evaluation may support the translation of emerging sensing technologies into monitoring tools that improve safety and reduce costs. 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