A Novel Prediction Method of Transfer-Assisted Action Oriented to Individual Differences for the Excretion Care Robot
Yina Wang, Wenjie Hao, Yanjun Yu, Junyou Yang, Guang Yang, Andrey V Savkin · 2023
Read A Novel Prediction Method of Transfer-Assisted Action Oriented to Individual Differences for the Excretion Care Robot by Yina Wang, Wenjie Hao, Yanjun Yu, Junyou Yang, Guang Yang, Andrey V Savkin (2023) 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-10747228.txt.
Description
Yina Wang and co-authors predict transfer moves for a toilet care robot, tuned to each user's own motion style, in work from twenty twenty-three. The robot must judge lifting and shifting actions correctly to help safely. People differ in how they perform the same transfer move. Those differences slow recognition and hurt trust in the system. Posture sensors track lower limb motion for a light body model.
A smart filter sharpens pose estimates and adds foresight to them. A two-way memory network reads past and future motion together. An attention head weights the most telling parts of each move. Three subjects test the method against two rival time-series models. The attention model predicts care actions with the highest accuracy. Care robots gain a path to personal, reliable motion reading.
Catalog record
| CREATOR | Yina Wang, Wenjie Hao, Yanjun Yu, Junyou Yang, Guang Yang, Andrey V Savkin |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |