DONIC: one policy drives two dexterous hands, 86.79% on unseen trajectories without fine-tuning
liuziwei7 · x · 2026-10-23
Ropedia AI released DONIC, a bimanual dexterous manipulation method where a single policy drives two dexterous hands to track human bimanual demonstrations with no fine-tuning.
Sim results: 86.79% success on unseen trajectories, 57.32% on unseen objects — a 45.7-point improvement over baselines. The authors frame the open question: for bimanual sim-to-real, is contact modeling or data the bottleneck?
Related event: Ropedia Unveils DONIC: One Policy for Two Dexterous Hands(4 posts)→
More from Embodied
- Physical Agent Capability Index: Astra leads Argon 1349 to 1324 Elo, both fail 4-bottle task — qinzytech · 2026-10-23
- Beijing's service robot output surges 170% in first three quarters — yogthos · 2026-10-23
- ETH Zurich robot learns humanoid mobility from 13 minutes of human motion, no reference at deployment — ChongZzZhang · 2026-10-23
- NVIDIA investigates stuttering issues reported on Surface Laptop Ultra — tomwarren · 2026-10-23
- Ex-OpenAI science head Kevin Weil: US must use AI and robotics to win back pharma before it's too late — beffjezos · 2026-10-23
- 54-second SLAM kitchen scan, Gaussian splats processed in under 9 minutes — jonstephens85 · 2026-10-23