Incorporating energy expenditure and rest allowance in a human-robot collaborative learning-forgetting process
Bibliographic record
Abstract
Collaborative robots (cobots) are being increasingly deployed in modern manufacturing to enhance flexibility, productivity, and safety. However, most existing production models overlook key human-centric factors, such as learning, forgetting, and fatigue, which significantly impact performance in human–robot collaboration (HRC) systems. Unlike manual environments, HRC requires precise synchronization between human adaptability and robotic consistency. Humans improve through learning, but forget over time. Meanwhile, fatigue accumulates, demanding rest that affects pacing and throughput. In parallel, physical fatigue accumulates, requiring rest periods that influence pacing and system throughput. This study, therefore, presents a Learning–Forgetting Fatigue–Recovery Model for Human–Robot Collaboration (LFFRM-HRC) that integrates human learning and forgetting dynamics with energy-based fatigue–recovery behavior within an optimization framework. The model evaluates how learning rate, number of batches, and forgetting duration affect total production time and average rest time across sixty simulation scenarios. Three system configurations are compared: manual assembly, HRC without task assignment, and a proposed HRC approach with dynamic task allocation. The results demonstrate that the proposed LFFRM-HRC with task assignment outperforms both manual and unstructured cobot setups, achieving substantial reductions in production time and rest needs. Moreover, the study shows that the optimal number of batches and shorter rest times mitigate the adverse effects of forgetting and fatigue. These findings necessitate including physical fatigue in system design, noting that cognitive fatigue, though important, is beyond the current scope. The LFFRM-HRC provides a practical, ergonomically sensitive tool for optimizing cobot-enabled production systems, supporting improved productivity while safeguarding worker well-being.
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 | 0.000 |
| 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 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".