A human-robot collaborative order picking system with ergonomic considerations: A novel mathematical model and machine learning approach
Bibliographic record
Abstract
Order Picking Systems (OPS) play a critical role in warehouse operations, particularly in markets where delivery speed is a key competitive factor. While traditional OPSs are labor-intensive, integrating collaborative robots (cobots), such as automated mobile robots (AMRs) and robotic manipulators, offers potential improvements in efficiency and ergonomics. This study proposes a mathematical model for a Human-Robot Collaborative OPS (HRC-OPS) that optimally determines the number and type of cobots to deploy. The objective is to minimize operational costs while maintaining ergonomic safety by limiting the REBA (Rapid Entire Body Assessment) index. In addition to robot allocation, the model optimizes item placement within the warehouse to enhance system performance and worker well-being. As the model aims to reflect real-world warehouse operations, it becomes too complex to solve using exact methods. However, since the model seeks to guide managers’ strategic choices during the design phase, an exact solution is not a priority. Therefore, a machine learning (ML) approach was developed to extract patterns from high-quality solutions and provide actionable managerial insights. Among six tested ML algorithms, XGBoost showed the highest accuracy in identifying effective configurations. Results from a case study demonstrate that cobots can significantly enhance OPS performance. However, the effectiveness of specific robot types depends on system characteristics, such as demand frequency and physical attributes. Moreover, strategic item placement has a direct influence on both performance and ergonomic outcomes, particularly for frequently ordered items or those that are unsuitable for robotic picking, offering practical guidance for warehouse managers.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".