Deep learning-enhanced smart ground robotic system for automated structural damage inspection and mapping
Bibliographic record
Abstract
Ground robotic systems are essential for structural inspection, enhancing mobility, efficiency, and safety while minimizing risks in manual inspections. These systems automate 3D mapping and defect assessment in aging. However, current robotic platforms often require the integration of various sensors and complex parameter tuning, raising costs and limiting efficiency. This paper proposes a streamlined unmanned ground vehicle-based inspection platform, integrating only LiDAR and a low-cost monocular camera. Operated via the Robot Operating System, the platform deploys efficient instance segmentation, Simultaneous Localization and Mapping, and fusion algorithms, eliminating complex tuning across environments. A self-attention-enhanced YOLOv7 algorithm is proposed for accurate damage segmentation with limited datasets, while an enhanced KISS-ICP (Keep It Small and Simple-Iterative Closest Point) algorithm is developed to optimize point cloud odometry for efficient mapping and localization. By introducing camera-LiDAR information fusion, the proposed platform achieves structural mapping, damage localization, quantification, and 3D visualization. Laboratory and full-scale bridge tests demonstrated its high accuracy, efficiency, and robustness. • Robust UGV-based automated inspection platform for the assessment of structural damage. • Efficient framework solely uses LiDAR and a camera to achieve damage localization, quantification and visualization. • Improved YOLOv7 for enhanced instance segmentation minimizes need for custom datasets. • An approach derived from the state-of-the-art odometry strategy is proposed for SLAM. • Verification through rigorous laboratory and full-scale bridge experimentations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".