Search for: All records

Work-related musculoskeletal disorders contribute to significant loss in productivity and higher costs for employers. This research utilizes body-worn motion and hand-worn force sensors to provide non-intrusive and continuous recognition of tasks, estimate force exertion, and evaluate if operators are working in safe ergonomic ranges. Work-related motions such as lifting, carrying, pulling, and pushing are measured with varied loads up to 10 kg, and then recognized performed using the IBM Watson cloud service platform. The experiments use sequential and quasi-static postures and mimic those commonly found in an automotive assembly environment. Classification performance included generating 70 input features based on 6 motion and 4 force inputs and three of the resulting classifier had a greater than 90% accuracy in simultaneously classifying both the weight being carried and the task being completed. Future work includes measuring non-quasi-static motions and integrating additional sensors, such as those from smart tooling, which tracks tool position and orientation, to provide a continuous and unobtrusive evaluation of worker exertion and risk of musculoskeletal disorder.