MiTaS fuses slow and fast tactile sensing, lifts robot manipulation success to 80% vs 31%
Jan_R_Peters · x · 2026-09-08
MiTaS, accepted at CoRL 2026, takes a "why choose one tactile sensor?" approach by fusing slow and fast tactile sensing for contact-rich robot manipulation. The result: an 80% success rate versus 31% for vision-only baselines. The team includes Robert Krohn, Erik Helmut, Jan Peters and collaborators, with a project page available.
More from Embodied
- Investors clash: will Tesla's Cybercab kill Uber within a decade? — SumitGup · 2026-09-08
- "Humanoid robots won't replace robots — they'll replace the people, even factory owners" — MatthewChang · 2026-09-08
- Humanoids and quadruped robots stage 'robot protest' on Warsaw streets over AI job displacement — Polymarket · 2026-09-08
- Blogger says their figure robot will ship — cixliv · 2026-09-08
- OpenAI Offers Up to $423,000 Plus Equity for Robot Actuator Engineers — VraserX · 2026-09-08
- TrainBud: Open-Source MCP Server Turns Your Fitness Data Into an AI You Can Ask From Your Wrist — Cr1tsh0t · 2026-09-08