RGB-LiDAR sensor fusion for dust de-filtering in autonomous excavation applications
Bibliographic record
Abstract
The dusty environments of autonomous excavation can affect the performance of the sensors onboard the vehicle. Specifically, airborne dust clouds can be perceived as solid objects if not addressed appropriately, which can lead to irrational movements that risk safety. In this article, a light detection and ranging (LiDAR) and red-green-blue (RGB) image sensor fusion model was developed to filter airborne dust particles. The proposed approach processes the RGB and LiDAR data in separate convolutional neural network (CNN) models and combines the predictions in a late fusion model for enhanced real-time performance. Testing shows that the proposed fusion model has an F1 score at least 2.64% higher than a LiDAR only CNN model and a dynamic radius outlier removal paired with low-intensity outlier removal (LIOR-DROR) when dust clouds are around 3 m from the sensors. • Multi-layer deep learning approach for airborne dust particle filtering using late sensor fusion technology. • 2D RGB and 3D LiDAR data was fused using a projection scheme. • Optimal results were obtained when airborne dust is location approximately 3 m from the sensors. • Real-time performance was achieved with respect to the refresh rate of the LiDAR.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".