Bibliographic record
Abstract
The end state of an autonomous system in South Africa's deep mines is a “fait accompli”. The current unacceptable safety records, and the increasing dangers as the mines get deeper, necessitate the removal of miners from the dangerous stope areas. Robotics seems an obvious solution. An autonomous robotic system to inspect the mine ceiling (hanging wall) is being developed at the Center for Mining Innovation as an initial robotic application for South African deep gold mines. A number of the key technologies needed to enable this are discussed. The localization system, the underground alternative to the GPS, is perhaps the single biggest hurdle needed in enabling underground robotics. A low cost, disposable solution for the small area gold stope (30m × 3m) is presented. Machine sensing of both the environment and of humans is critical in a shared working environment. Here we discuss alternatives to the current sensors used above ground for machine perception. In the deep gold mines the geothermal heat result in hot walls and thermal imaging becomes an option for structural imaging. The combination of temperature with a 3D data enables the determination of a risk measure, indicating potential danger areas. Potential methods of representing the risk data for the miner to interpret are discussed. Finally, the thermal camera in conjunction with a distance sensor is used to identify and track pedestrians in order to predict potential collisions.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".