Nonlinear spectral modeling and control of soft-robotic muscles from data
Leonardo Bettini, Amirhossein Kazemipour, Robert K. Katzschmann, George Haller · 2026
Read Nonlinear spectral modeling and control of soft-robotic muscles from data by Leonardo Bettini, Amirhossein Kazemipour, Robert K. Katzschmann, George Haller (2026) 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-13677678.txt.
Description
Leonardo Bettini, Amirhossein Kazemipour, Robert Katzschmann, and George Haller model and control soft robotic muscles from data in a 2026 paper. Soft artificial muscles power compliant robots but act in complex ways. Electrohydraulic muscles are strong yet show memory and lag effects. Full physics models of them are hard to build.
The team uses spectral submanifold theory to shrink the dynamics. When inputs change slowly, motion settles onto a low-dimensional surface. They learn the input-output map on that surface from response data. No harsh step tests are needed to build the model. A real joint with two opposed muscles ran under the model. Tracking error fell well below both feedback-only and feedforward-only control.
Catalog record
| CREATOR | Leonardo Bettini, Amirhossein Kazemipour, Robert K. Katzschmann, George Haller |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 126 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |