Adaptive training simulation using speech interaction for training navy officers
Bibliographic record
Abstract
An important element of the Royal Canadian Navy (RCN) Future Naval Training System Strategy is the deployment of technology enabled learning systems allowing for acquisition of knowledge and skills using a variety of shore-based multipurpose and reconfigurable simulators, as well as at sea embedded simulators. The RCN has a strong culture of one-to-one relationship between instructors and trainees while trainees use simulators. This close relationship allows for direct feedback to trainees, and individualized assessment. With the increased access of distributed learning opportunities in the form of part tasks trainers and serious games, trainees will benefit, and should be encouraged to acquire knowledge, and practice skills in a self-directed manner, outside the context of a supervised simulation session supervised by an instructor. However, the ubiquitous individual access to learning programs should continue to provide immediate feedback to trainees, and allow instructors and course developers to monitor learning. Fulfilling both objectives requires the relevant capture and analysis of learning events. In this context, our particular project focuses on Maritime Surface and Sub-Surface Officer (MARS) training using serious games, capturing learning event data to leverage them for adaptive training, and self-directed learning using learning assessment dashboards. The project is at an early development stage and aims to provide high realism for the officer of the watch (OOW) through speech interactions with simulated agents including a naval communicator, helmsman, range finder, commanding officer, and a guide ship. The training program focuses on the acquisition of conning skills. The paper presents some conceptual foundation for this program, as well as the first training module aimed at demonstrating the feasibility of a speech interaction interface for conning in the context of a manoeuvre scenario. The paper also outlines the intended adaptive training specifications to be implemented in a second project phase, and indicates areas of future work. ABOUT THE AUTHORS Dr. Bruno Emond is a senior research officer at the National Research Council Canada. He joined NRC in 2001 and holds a B.A. and M.A. in philosophy, and a Ph.D. in educational psychology from McGill University. His research evolved over his career on issues related to knowledge representation, logic, text comprehension, and cognitive modelling. Dr. Emond's current interests focus on adaptive training systems, and educational data mining. LCdr Maxime Maugeais joined the Canadian Naval Reserve in 1998 and spent 9 years as a MARS officer. He subsequently transferred to the Regular Force as a Training Development Officer (TDO) in 2007. Both as a MARS officer and TDO, he occupied a variety of learning technology-related jobs. LCdr Maugeais completed his Masters of Arts in Learning and Technology and continues to be involved in finding innovative ways to leverage technology to support effective and efficient learning.
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 | 0.001 |
| 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".