Ropedia releases DONIC: one policy controls two dexterous robot hands, 86.79% success on unseen trajectories
liuziwei7 · x · 2026-10-23
Ropedia's DONIC is a single dexterous tracking policy that controls both robot hands from human bimanual demonstrations, generalizing to unseen trajectories and objects with zero fine-tuning.
- 86.79% success on unseen trajectories, 57.32% on held-out objects in simulation
- Ships with the BiHOI dataset: 1,575 bimanual sequences, 229 objects, 14.77 hours of interaction captured from 32 calibrated RGB cameras and retargeted to robot hands
- Method highlights: object-centered per-hand rewards keep object tracking active throughout, plus clip-centered advantages
More from Embodied
- A $2,490 humanoid and a hosted robot-model API land in the same week — AIFlow_ML · 2026-10-24
- iPhone Duo's fold transition bends the focal plane, not the content — emax · 2026-10-23
- Microduck: why this cute robot toy matters more than it looks — TinfoilTricorn · 2026-10-23
- Rust SLAM system visloc-rs debuts 4th on LaMAria benchmark, top open-source entry — rsasaki0109 · 2026-10-23
- AGIBOT's A3 Ultra humanoid robot demonstrates roller-skating mobility — TinfoilTricorn · 2026-10-23
- Xaira details X-Automate: X-Scientist, X-Bot and mobile robots link protein design to testing — BoWang87 · 2026-10-23