Predicted safety & excavation progress algorithms for autonomous excavation
Bibliographic record
Abstract
Excavation is the process of moving earth and is considered to be one of the primary projects in the construction industry. The adoption of various cutting-edge technologies for full automation can be a solution to the various ongoing issues in construction equipment used for excavation such as safety, monitoring, and productivity. \nTo address this, this project developed advanced safety algorithms and methodologies in ground mapping and estimation of excavation progress, which can accelerate autonomous excavation. \nFor autonomous excavation, safety is a significant concern to reduce accidents and machinery damage. Considering this point, this thesis deals with tracking, motion prediction, and track management of the detected objects that can improve the safety function of autonomous excavators. The proposed safety algorithms can evaluate the degree of a potential collision risk by using the information of predicted motion of detected objects, working areas of the excavator, and safety indices calculation. \nThe second component of this project covers the volume estimation for excavation progress estimation, occlusion problem for ground mapping, and 5D mapping. The volume estimation comprises of ground excavation volume and bucket volume estimation. To overcome the problem of an occlusion area that may result in incorrect mapping and estimation of excavation progress, sensing data of proprioceptive and exteroceptive sensors were integrated. Finally, we proposed the idea of 5D mapping to provide a broad spectrum of the excavated ground info that includes the coordinates and material type and properties using a 3D ground map, LiDAR???s beam reflectivity, and force index.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".