Benchmarking Unmanned Aerial Systems-Assisted Inspection of Steel Bridges for Fatigue Cracks

Abstract

Inspection agencies have been increasingly implementing unmanned aerial systems (UAS) for bridge inspections. Currently, UAS are typically used for long-range monitoring and surveillance tasks, but bridge managers are hopeful that they may be utilized for detailed inspection, such as condition assessments and the inspection of fracture critical members (FCMs) in the near future. As an assistive tool for visual inspections, the accuracy of UAS-assisted inspections is unknown. This study investigates the relationship between the characteristics of the individual inspectors and a set of performance metrics associated with UAS-assisted FCM inspections. Four bridge inspectors used a UAS to inspect a series of full-sized bridge specimens with known fatigue cracks. The inspection videos were later shared with 19 bridge inspectors for a desk review. The performance of each inspector was evaluated and compared with the results from 30 hands-on inspections of the same specimens. The results showed that an inspector’s past experience with UAS, licensure, and academic degree could have a significant influence on one or more of the three defined performance metrics. The comparison between the results of the UAS-assisted inspections and the hands-on inspections revealed that crack detection was comparable. However, the hands-on inspections were more accurate.