A systematic review of technologies and methodologies for automated bridge inspection

Bridges are critical components of transportation infrastructure, yet traditional inspection methods remain labour-intensive, hazardous, and limited in accuracy and scalability. This study addresses the need for safer and more efficient inspection practices by systematically reviewing 92 peer-reviewed journal articles and state Department of Transportation (DOT) reports published between 2014 and 2025. The objective is to evaluate the adoption, effectiveness, and integration of sensor carriers (e.g. Unmanned Aerial Vehicles-UAVs, stationary systems), sensors (photogrammetry, LiDAR, and thermal imagers), data types (2D imagery, 3D point clouds, thermal maps), and data-processing methods (image segmentation, 2D convolutional neural networks, 3D neural architectures) in bridge inspection workflows. Using a PRISMA-guided systematic review and mixed-methods content analysis, the study categorises technologies by application scope, technical function, and implementation challenges. Three major challenge domains are identified: data and computational limitations, environmental and operational constraints, and labour and accessibility issues. Findings show that UAVs and LiDAR significantly improve inspection efficiency and defect detection accuracy compared to conventional methods, yet full automation in data interpretation and regulatory challenges remain barriers to large-scale implementation. By synthesising academic and DOT-level evidence, this review advances understanding of current capabilities and provides a foundation for developing scalable and resilient bridge inspection systems.