Vision-based tactile sensing enhanced by microstructures and lightweight convolutional neural network
Mayue Shi, Yongqi Zhang, Xiaotong Guo, Eric M Yeatman · 2026
Read Vision-based tactile sensing enhanced by microstructures and lightweight convolutional neural network by Mayue Shi, Yongqi Zhang, Xiaotong Guo, Eric M Yeatman (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/PMC13265784.txt.
Description
Mayue Shi and co-authors wrote a 2026 engineering paper on a vision-based touch sensor for robots. The sensor watches a soft surface deform through a camera instead of wiring the surface with electronics. Fine trenches cut into the surface bend light as force lands, amplifying the visual signal so a very small neural network can read it.
Using only a commercial webcam, the system detected forces below five millinewtons, a whisper of pressure, and located single touches within a millimetre. Its one-layer network placed contact points with error under 0.05 millimetres on average. The soft body suits robot hands, and the optical design avoids electrical crosstalk and magnetic interference. The authors present it as a light, robust route to machine touch.
Catalog record
| CREATOR | Mayue Shi, Yongqi Zhang, Xiaotong Guo, Eric M Yeatman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52835 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |