Promoting safe use of AMRs by assessing their residual risks and safety-related functions
Bibliographic record
Abstract
With Autonomous Mobile Robots (AMRs), the usual risks are those of collision between a worker and the AMR, or a body part trapped between the AMR and a fixed or moving obstacle. To bypass obstacles (human or otherwise), AMRs feature autonomous control systems activating safety-related functions based on machine learning or optimization algorithms. This paper proposes a roadmap to guide integrators and users on the safe implementation of two AMRs. To do so, a risk assessment of two identical AMRs was performed, using ISO 12100, in a test bed consisting of an Intelligent Cyber-Physical Systems laboratory warehouse at Polytechnique Montreal. A safety checklist from the standard R15.08 was filled out to feed the risk assessment process and to help judge the efficiency of the technical protective measures, namely the safety-related functions. Apart from the risks of collision and entrapment, the risk assessment highlighted other hazards stemming from the AMRs, such as intense light that can temporarily distort someone’s view, then potentially become a pitfall during human-robot interactions. Assessing the autonomous localization and mapping ability of the AMRs at their configuration phase highlighted the importance of a high quality and reliable Wi-Fi to detect obstacles on time and avoid unexpected movements. Consequently, the risks have started being addressed to use those AMRs safely. The study showed the gap between today’s safety-related state of the art (e.g., R15.08, ISO/IEC TR 5469) and the manufacturer’s design choices. That gap will raise awareness amongst designers, so they prioritize more inherently safe principles.
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 | 0.011 | 0.023 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".