TouchWGNN: spatio-temporal tactile perception for multimodal dexterous manipulation
Yu Ning, FuQiang Zhao, Qian Liu · 2026
Read TouchWGNN: spatio-temporal tactile perception for multimodal dexterous manipulation by Yu Ning, FuQiang Zhao, Qian Liu (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/PMC13351857.txt.
Description
Yu Ning, FuQiang Zhao, and Qian Liu describe TouchWGNN in 2026, a touch-based system for skilful robot hand control. Robot hands struggle to judge object pose when sight is blocked and contact changes fast. Their hand carries a low-cost sensor array with 113 force points spread across key contact areas of five fingers.
Touch readings form a graph over space and time, where nodes hold force and position and edges link nearby points. A graph encoder reads contact shape, a time module tracks its change, and the result merges with camera and joint data for learning by trial. Tests on cube turning and Baoding ball swapping beat single-sense baselines, showing raw touch adds clear value.
Catalog record
| CREATOR | Yu Ning, FuQiang Zhao, Qian Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71503 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |