Ensuring the structural integrity of constructed facilities through regular inspections is essential for public safety; however, conventional practices are time-consuming and often inconsistent. Although unmanned aerial vehicles (UAVs) offer automation, current methods remain limited by arbitrary flight distances and a lack of standardized validation linked to defect-detection requirements. This study addresses these gaps by presenting a novel, standardized, resolution-driven UAV inspection framework that tightly integrates building information modeling, ground sampling distance (GSD) optimization, and a specialized hybrid genetic algorithm (HGA) for intelligent flight-path planning. The framework establishes a resolution-driven planning approach where GSD calibration links flight distance directly to minimum defect-detection thresholds, specifically confirming the required distance for reliably detecting 0.5 mm cracks. The HGA strategically combines boustrophedon coverage paths for individual surfaces of a constructed facility with a genetic algorithm to optimize the intersurface visiting sequence, ensuring coverage efficiency. Validation through a real-world case study on a four-floor building demonstrated the system’s robustness, achieving submeter three-dimensional positional consistency (median error of 0.75 m and root mean square error of 0.88 m). The results confirm that the proposed method significantly enhances data reliability, inspection repeatability, and operational efficiency, providing a scalable, standardized solution for practitioners and advancing the field of facility performance assessment and structural health monitoring by providing the high-resolution data necessary for engineering-grade condition surveys.
Benshaaban et al. (Mon,) studied this question.