An Efficient Framework for Personalizing EMG-Driven Musculoskeletal Models Based on Reinforcement Learning
Joseph Berman, I-Chieh Lee, Jie Yin, He Huang · 2024
Read An Efficient Framework for Personalizing EMG-Driven Musculoskeletal Models Based on Reinforcement Learning by Joseph Berman, I-Chieh Lee, Jie Yin, He Huang (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11875965.txt.
Description
Joseph Berman and co-authors speed up the tuning of muscle models that turn forearm signals into prosthetic hand motion. Their 2024 framework teaches a generic upper-limb model to fit each user. Signal-driven models promise natural control, yet hand-tuning them for each person is slow.
A neural policy trained by reinforcement learning adjusts model settings to match recorded hand and wrist moves. The rival method, simulated annealing, needed over thirteen minutes for jobs the new tool finished in under a second. Accuracy matched the slow method in bench tests. In live trials, including one user with a forearm amputation, fitted models beat the generic one. The authors pitch the tool for daily clinic use.
Catalog record
| CREATOR | Joseph Berman, I-Chieh Lee, Jie Yin, He Huang |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |