MPM-based simulation and bounded-error compression of material points for magnetic tactile sensors
Xing Lin, Guiru Lin, Ruikai Liu, Anjia Wang, Yunjiang Lou · 2026
Read MPM-based simulation and bounded-error compression of material points for magnetic tactile sensors by Xing Lin, Guiru Lin, Ruikai Liu, Anjia Wang, Yunjiang Lou (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/PMC13311028.txt.
Description
Xing Lin and co-authors build a physics simulation for magnetic touch sensors in a 2026 study. Touch feedback guides fine robot assembly when sight is blocked, and magnetic sensors are fast and compact. A lack of true to life simulation blocks training of robot policies, so a joint frame was built.
Soft material bending is modeled with a particle method at fine scale on modest hardware. A masked learning model compresses touch point clouds by over 88 percent of size while keeping shape error tiny. A mapping model then projects real signals into the simulated space. Mapped forms kept contact shape and aligned domains well for later real use.
Catalog record
| CREATOR | Xing Lin, Guiru Lin, Ruikai Liu, Anjia Wang, Yunjiang Lou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64936 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |