Data-Driven Scenario Generation for Enhanced Realism of Equipment Training Simulators
Bibliographic record
Abstract
Improving the training of heavy equipment operators can make a significant contribution to improving the safety of construction sites. In recent years, Virtual Reality (VR)-based simulators have gained increased popularity for the use in equipment training programs. While VR training simulators for heavy equipment are less mature than those used in the aviation industry, these simulators are gradually carving their ways into the training programs for construction equipment operators as well. Presently, the majority of the existing VR scenes are based on hypothetical scenarios and more focused on developing motor skills. However, on real construction sites, the decisions an operator makes to operate the equipment safely and efficiently depend on the decisions made by other operators or workers in addition to the type and location of the work. In the current situation, the training simulators do not capture the dynamism of the construction site and the uncertainties involved in the project as a result of human factors. One way to address this issue is to generate realistic training simulators based on the actual construction operations. In these VR scenes, the data from actual equipment will be used to generate a scene where the trainee is supposed to operate the equipment in face of the movements of many other pieces of surrounding equipment. For this purpose, sensor data needs to be integrated with a multi-agent system to capture the behaviour of many equipment and workers. Nonetheless, the first step towards the generation of such a scene is to reconstruct the actual construction site in the VR environment. This research builds upon the previous work of the authors and the advancements in geo-informatics to propose a method for the reconstruction of actual sites using GIS and cadastral data. Two different approaches for the generation of these scenes are compared and a prototype is developed to show how sensor data can be integrated with the VR scene for the construction of the realistic training simulators. The feasibility of the approach is demonstrated by means of a case study where GPS data from an actual construction project is replayed in the VR model of the site where the project took place.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| 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".