UAV bridge inspection requires centimeter-level global positioning in the engineering coordinate frame to associate detected defects with BIM component IDs and mileage stakes. Intermittent GNSS outages beneath beams, inside box girders, and in pier-dense regions cause conventional navigation methods to accumulate drift or produce discontinuous pose estimates. This paper presents BCEF-Nav, a BIM-constrained elastic fusion navigation framework for UAV bridge inspection. The framework adaptively adjusts GNSS constraints according to signal availability and replaces degraded GNSS references with semantic–geometric constraints from a high-precision as-built BIM model within a sliding-window optimizer. Semantic-guided feature matching suppresses false correspondences in repetitive bridge structures. BCEF-Nav uses only low-cost commercial sensors and is compatible with mainstream inspection UAVs. Digital twin simulations and field experiments achieved an ATE RMSE of 5.7 cm after 120 s of complete GNSS occlusion and a 100% positioning success rate with positioning errors below 10 cm, outperforming seven recent state-of-the-art baselines.
Abstract. Navigating Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments requires reliable autonomous localization techniques. This study proposes a vision-based localization framework utilizing satellite true orthophotos and Digital Surface Models (DSMs) as absolute geospatial references. The algorithmic pipeline integrates deep learning architectures—specifically SuperPoint and LightGlue—to establish robust image-to-map feature correspondences. The matched correspondences are used to estimate camera exterior orientation parameters through collinearity-based spatial resection with an Iteratively Reweighted Least Squares (IRLS) approach. To validate the proposed methodology, a multi-altitude dataset (100–250 m) was acquired across structurally diverse terrains, including dense building, high vegetation, and bare ground areas. Experimental evaluations demonstrate that the framework achieves meter-level absolute positioning accuracy and stable pose estimation. Analyses further reveal that matching robustness and localization success rates depend heavily on terrain texture and flight altitude; geometrically structured urban scenes at moderate-to-high altitudes consistently yield reliable correspondences, whereas low-texture environments and lower flight altitudes present persistent challenges for continuous visual tracking.
Tai-Cyuan Wang, Lai-Han Tsou, J. Jhan et al.· The International Archives o...· 0 citations
Wind turbine towers in coastal environments are exposed to geometric misalignment and surface corrosion, yet these condition indicators are commonly assessed separately and without a consistent reference across inspection epochs. This study develops a reference-consistent structural health monitoring framework that integrates total-station surveying and multi-temporal unmanned aerial vehicle imagery for concurrent monitoring of view-dependent image-space inclination indicators and visible corrosion. A baseline lower-segment reference axis is established in a fixed geodetic coordinate system. The geodetically controlled baseline image configuration is transferred to subsequent epochs through covariance-weighted control-image constraints, while RTK-GNSS and inertial observations support exterior-orientation estimation. The angular difference between the projected reference axis and an image-derived visual symmetry axis defines the inclination indicator. The combined single-view standard uncertainty is 0.041°, the expanded uncertainty is 0.082°, and the engineering monitoring threshold is 0.098°. Five UAV epochs acquired between October 2024 and June 2025 yield first-to-final angular-change magnitudes of 0.030° to 0.074° across eight fixed viewing directions. These values remain below the single-view expanded-uncertainty reference magnitude and are therefore interpreted as monitoring-level observations rather than statistically confirmed structural deformation. An independent total-station re-survey at the final epoch yields validation residuals from −0.032° to +0.044°, with a mean absolute residual of 0.017° and a root-mean-square residual of 0.023°, supporting monitoring-level consistency between the UAV-derived and projected total-station changes. Visible corrosion is segmented using YOLO11-seg and normalized with respect to the valid, observable tower-surface region. The independent test set yields a precision of 79.6%, a recall of 88.0%, and an F1 score of 0.84. The visible corrosion extent index increases from 0.04 to 0.12%, corresponding to a descriptive transition from ASTM D610 grade 8 to grade 7. The framework provides a reference-consistent and uncertainty-aware basis for maintenance-oriented monitoring of slender tubular towers.
T. Chuang, Po-Yen Chen· Structural Health Monitoring· 0 citations
Repeated non-equidistant unmanned aerial vehicle (UAV) inspections of slope-road cracks require measurements from different distances, poses, and image scales to remain comparable and sufficiently precise for engineering-state decisions. Existing studies rarely integrate cross-view physical conversion, measurement uncertainty, and a project-defined minimum detectable change. We develop an engineering-detectability framework that defines cross-period criteria for crack width and displacement and derives equivalent widths for ideal, representative non-standard, and arbitrary viewpoints. First-order error propagation and reliability allocation convert the minimum detectable change into accuracy requirements for range, field of view, and normalized image coordinates. Crack-boundary coordinates and localization uncertainties provide a common interface for interchangeable detection and photogrammetric modules. Validation combines a controlled fixed-camera sequence with a close-range field-camera multiview test of seven physical openings under local coplanarity. All six determinate stages in the controlled sequence agreed with the digital image correlation (DIC) comparison, while one borderline stage required review. Across the seven openings, the four-view means gave a mean absolute error (MAE) of 0.196 mm and a root mean square error (RMSE) of 0.270 mm, with cross-view coefficients of variation (CVs) of 0.33–4.93%. An illustrative error budget demonstrates reverse screening of system configurations from project thresholds. The framework therefore connects viewpoint-equivalent measurements, uncertainty constraints, and engineering-state decisions in an auditable chain.
Unstructured environments challenge unmanned ground vehicle (UGV) navigation with complex terrain and open-set obstacles. Existing inertial-aided navigation using external odometry suffers from localization errors in rugged off-road conditions, while sparse LiDAR point clouds degrade traversability prediction. The purpose of this study is to address these limitations by developing a robust autonomous navigation framework that integrates SLAM-assisted normal distributions transform (SANDT) and divergence-guided temporal point cloud fusion.
First, the authors replace conventional vehicle odometry with inertial data maintained by a LiDAR-based SLAM method, supplying a continuous and stable coarse guess for NDT registration to improve localization. Second, voxel-wise NDT representations of adjacent point clouds are computed; key historical frames are selected via Jensen-Shannon divergence and fused to densify the current point cloud and improve traversability estimation. Finally, the authors integrate these components into an autonomous navigation framework and validate it in real-world scenarios.
Experiments demonstrate that the authors’ framework achieves accurate localization and seamless indoor-to-outdoor navigation, outperforming baseline methods in traversability prediction, navigation success rate and obstacle avoidance.
This paper presents a robust autonomous navigation framework for unstructured environments. SANDT enables cross-scene navigation in complex terrains, and global divergence-based temporal fusion pioneers LiDAR-based traversability estimation. Further details on localization, traversability prediction and real-world navigation are provided in the supplementary video.
Yuenan Zhao, Ziming Zhang, Ruifeng Wang et al.· Robotic Intelligence and Aut...· 0 citations
The flatness of bearing pads directly affects structural load transfer safety. However, conventional total station-based inspection methods suffer from limited spatial sampling, low inspection efficiency, and high safety risks associated with working at height. To address these limitations, this paper proposes UAV-FIBP (Unmanned Aerial Vehicle-based Flatness Inspection for Bridge Pads), an automated and intelligent method for pad flatness assessment utilizing UAV-based 3D reconstruction. By designing a close-range, multi-orbit circumnavigational UAV flight path and acquiring high-overlap imagery (85% forward and 80% side overlap), a millimeter-accurate 3D model is generated via photogrammetry, achieving a high-density point cloud of ≥200 points/cm2 on the pad surface. Following point cloud denoising and region-of-interest segmentation using the Random Sample Consensus (RANSAC) algorithm, Principal Component Analysis (PCA) is employed to fit a reference plane. A dual-parameter evaluation framework is subsequently introduced: the root mean square (RMS) deviation quantifies local surface roughness, while the maximum elevation difference is derived from the angle between the normal vectors of the fitted plane and the horizontal plane, thereby enabling a comprehensive assessment of global inclination. Validation experiments conducted on laboratory-scale setups and real construction sites (involving four bridge pads) demonstrate that the proposed method achieves deviations ≤ 2 mm compared to total station measurements, satisfying the requirements stipulated in the Standards for Quality Inspection and Verification of Highways (JTG F80/1-2017). Results indicate that UAV-FIBP enables non-contact, full-coverage, and automated flatness inspection, significantly improving inspection efficiency and construction safety. This work establishes a scalable technical pathway for intelligent bridge construction.
Yuchi Xupan, Yu Ling, Hua Liu et al.· Buildings· 0 citations
Accurate and continuous train localization is critical for modern intelligent railway systems. However, it remains a significant challenge to achieve seamless navigation in global navigation satellite systems (GNSS) challenged environments, such as long tunnels, deep valleys, and canopies. During prolonged GNSS outages, conventional systems struggle to constrain unbounded inertial drift, while traditional magnetic matching methods suffer from spatial ambiguity and dynamic distortions in time-domain sequence. To address these limitations, this paper proposes a tightly-coupled GNSS/inertial navigation system (INS)/Magnetic fusion method based on a kinematics-assisted spatial sequence matching algorithm. By leveraging high-frequency INS velocity estimates, temporal magnetic data are resampled into the spatial domain. A localized scale compensation strategy is proposed to correct INS integration errors, and the resulting high-confidence spatial updates are seamlessly incorporated into an extended Kalman filter. Extensive field tests conducted on a diesel locomotive over a 6 km railway trajectory demonstrate that the proposed method effectively suppresses trajectory oscillations and achieves a positioning root mean square error of 2.03 m. Furthermore, the system exhibits robust performance even with heavily sparsified magnetic maps at a sampling interval of up to 10 m, substantially reducing map storage overhead and highlighting its strong potential for large-scale engineering deployment.
Lihui Yuan, Tuan Li, Bing Han et al.· Measurement science and tech...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
