Vision-based Autonomous Landing of UAV on Dynamic Apron
Bibliographic record
Abstract
Aiming at the landing problem of Unmanned Aerial Vehicle (UAV) without landmarks and global coordinates, this paper proposes an efficient vision-based UAV autonomous landing solution. Firstly, image information is obtained from the bottom visual sensor of the UAV, and the YOLOV5 object detection method is employed to determine the initial position of the dynamic apron. Subsequently, an improved dynamic apron tracking method based on Spatio-Temporal Transformer is designed. This method updates an initial template through target detection algorithm and utilizes multi-source perceptual data for confidence evaluation and dynamic template updates. It outputs the distribution estimation of the predicted bounding box corner coordinates, and achieves the high reliability continuous positional smoothing estimation and dynamic apron loss re-detection based on UAV vision. Finally, the UAV calculates the horizontal control quantity based on the horizontal relative position between the UAV and the apron obtained. The vertical control quantity is calculated based on the vertical relative position between the UAV and the apron. The vertical relative position is estimated using laser ranging and visual odometry techniques. Based on the results of horizontal tracking control and vertical regulation, velocity commands for the UAV in all three directions are generated, enabling the UAV to achieve autonomous landing on the dynamic apron. This paper achieves precise landing for dynamic apron in real-world environments. The experimental results demonstrate that this method avoids the limitations of labeled data and global information on autonomous landing of UAV. Even under GPS-denied conditions, the UAV can generate control commands based on visual data and achieve autonomous landing for randomly moving apron.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| 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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".