Pavement management systems (PMS) are essential for optimizing maintenance budgets and scheduling effective treatments for pavement networks. Traditionally, PMS rely on manual pavement distress data collection, a process that is both costly and time-consuming. This study explores the use of unmanned aircraft systems (UAS), commonly known as drones, as an alternative for collecting pavement surface distress data. The study focused on 13 truck weigh stations managed by the Virginia Department of Transportation and the Virginia Department of Motor Vehicles in the U.S. A drone was utilized to capture detailed images of pavement sections, which were then analyzed using an artificial intelligence model to generate pavement surface evaluation and rating (PASER) scores. These drone-derived PASER scores were compared with those obtained through traditional manual inspections. The results demonstrate that the PASER values from drone imagery and manual surveys align closely, with statistical analyses showing no significant differences overall. However, discrepancies were noted for Portland cement concrete sections, where the drone technology analysis method missed certain distresses such as joint seal damage. This limitation highlights the need for improvements in drone imaging or additional technologies to fully capture and analyze all distress types. Moreover, challenges such as weather dependency, regulatory constraints, and site conditions must be addressed to optimize drone use in pavement management.
Zalghout et al. (Fri,) studied this question.