Slip detection for compliant robotic hands using inertial signals and deep learning

Miranda Cravetz, Purva Vyas, Cindy Grimm, Joseph R. Davidson · 2025

Read Slip detection for compliant robotic hands using inertial signals and deep learning by Miranda Cravetz, Purva Vyas, Cindy Grimm, Joseph R. Davidson (2025) 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-12756126.txt.

Description

Miranda Cravetz and three co-authors wrote this 2025 study on teaching soft robotic hands to feel when a grip starts slipping. Their hand bends passively as tendons pull, so a slipping object twists the fingers in telltale ways. A small motion sensor at the fingertip picks up both that twist and the buzz of sliding. The team ran 195 handling trials, with and without slips, and labeled them using camera tracking.

A neural network trained on the sensor stream learned to call slips reliably, even amid other jolts and shakes. Better still, the same network worked on a different gripper, a new task, and an object it had never seen. The result matters because cheap inertial sensors could give compliant hands a sense usually reserved for costly skin-like sensors, making warehouse and assistive robots surer-handed.

Catalog record

CREATORMiranda Cravetz, Purva Vyas, Cindy Grimm, Joseph R. Davidson
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE42 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12756126

Browse the full library · About the Tower of Babel