SBIR Phase II: Use of Robotic Inspection and Data Analytics to Localize and Visualize the Structural Defects of Civil Infrastructure

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project seeks to produce two robotic systems for ground survey applications and inspection of vertical surfaces to detect and visualize both surface flaws and subsurface embedment in concrete structures using a camera and a ground penetrating radar (GPR). The instrumentation may reduce the time, difficulty, and cost to layout gridlines in civil infrastructure and make it possible to automate data collection at difficult-to-access locations with minimum human intervention. The use of the robotic inspection systems may allow the evaluation and inspection tasks to be performed faster, more thoroughly, with minimal safety risks to workers, and at a lower cost by eliminating the need for scaffolding and blocking traffic. The proposed research and development may advance the state-of-the-art robotic technology and produce climbing machines, vision-based accurate positioning, and 3D Ground Penetrating Radar (GPR) imaging software as a holistic solution to improve the way GPR data is collected, interpreted, and visualized. The solution can be extended to other non-destructive testing (NDT) applications and may help make the national infrastructure (e.g., bridges, tunnels, dams, and buildings) more secure.This Small Business Innovation Research (SBIR) Phase II project seeks to improve the accuracy and robustness of vision-based positioning and 3D GPR imaging algorithms while developing new software functions and integrating them into two robotic systems deployed to inspect both ground surfaces (e.g., bridge decks and highway pavement) and vertical surfaces (e.g., building facades and bridge foundations). The intellectual merit of this project is the automated 3D GPR data collection and imaging method that combines robotic control and vision-based accurate positioning with GPR signal processing for locating the subsurface defects and embedment (rebar, pipes, fractures, voids, delamination, etc.) in concrete structures. This method enables the robots to scan the surfaces in arbitrary and irregular trajectories rather than along gridlines to locate subsurface targets and discover the areas of delamination. Tagging the GPR measurements with accurate position information in a synchronized way at each sampling step enables high-resolution 3D GPR imaging.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.