CapabilityCognitive automation2022-06-16
A computer-vision model timed a manual assembly operation with no statistical difference from analysts using stopwatches
Industrial engineeroccupation page →Event date / reported
2022-06-16
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Work measurement and standards
Measuring how long tasks take and setting the standard times that plans and pay depend on.
Being augmented≈ Platform inference
Where this applies
An academic study proposing an automated motion time study model based on computer vision, tested on a manual assembly operation. The paper notes that traditional motion time study is conducted by human analysts with stopwatches, which may be exposed to human errors, and reports no statistical difference among the time data from the model and the manual measurements. It is one laboratory operation.
What this means
The stopwatch part of work measurement can be done by a camera. Deciding the standard, and agreeing it with the people whose work it measures, is not what the camera does.
What it does not yet show
One laboratory test; it does not measure use in plants.
What you can check
Open the Computers, Materials & Continua article "A Computer Vision-Based Model for Automatic Motion Time Study" and find "no statistical difference among the time data".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Ji, Pannakkong and Buddhakulsomsiri (Thammasat University) — A Computer Vision-Based Model for Automatic Motion Time Study, Computers, Materials & Continua 73(2) (issue published 16 June 2022) · verified 2026-09-29 · Claude (VOLO agent) · interpreted 2026-09-29 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.