Adaptive Virtual Assistant for Virtual Reality-based Remote Learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract This research describes the development of an adaptive virtual assistant in an immersive virtual reality (VR) serious game aimed at teaching engineering students manufacturing concepts. For undergraduate manufacturing education, students need to learn product design and manufacturing systems that require well-coordinated analysis of requirements and hands-on practices in complex manufacturing assembly lines. While it is often not feasible and practical for students to participate in real factory environments, simulations are created to offer a flexible alternative of digital learning. With the advancements in immersive technologies, VR opens new opportunities for teaching and learning manufacturing, and enables remote learning from any physical location. In this research, we describe the elements of a serious game built using the Unity game engine with VR technology that allows students to practice the concept of craft production. Prior research has shown that adapting learning material to suit individual student needs increases motivation and student successes. While learning remotely using an immersive virtual environment, a student is often working in an independent manner. Seeking help often requires the student to leave the virtual environment and break immersion. In this research, we propose an adaptive virtual assistant in the game environment to support the student learning process. By tracking student actions in the game environment and building a model of the student using reinforcement learning, the virtual assistant can learn and adapt to the student's preference in the types of assistance to provide. We show the adaptation of the virtual assistant through simulated experiments of typical student preferences.
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.
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 | 0.000 |
| 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 it