Deep learning-based obstacle-avoiding autonomous UAV for GPS-denied structures
Bibliographic record
Abstract
This thesis presents a comprehensive framework for an obstacle-avoiding autonomous unmanned aerial vehicle (UAV) system with a focus on structural health monitoring (SHM) in global positioning system (GPS)-denied areas. The proposed framework integrates a new obstacle avoidance method (OAM), a localization method using fiducial ArUco markers, and a real-time crack segmentation method. The OAM utilizes You Only Look Once version 3 (YOLOv3) network and a K-means clustering algorithm for robust obstacle detection and clustering. The ArUco marker-based localization method overcomes the limitations of traditional ultrasonic beacon (USB) localization, providing reliable and accurate UAV localization even in the presence of magnetic interference. Comparative studies show that the ArUco marker-based localization method significantly reduces yaw control error by 60.45% and path following error by 67.29% compared to USB-based localization. The developed autonomous UAV system is implemented and validated in both indoor and outdoor environments, demonstrating its effectiveness in GPS-denied areas. Furthermore, the integration of a state-of-the-art crack segmentation network (STRNet) enhances the system's capability for real-time crack segmentation with superior performance (mIoU 92.5%) compared to other deep convolutional neural networks.
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) | 0.000 | 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 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".