Reward AI debuts Omnibody Hand & OMI-1, pushing hardware-algorithm co-design for cross-embodiment dexterity
zipengfu · x · 2026-09-15
Robotics researcher ToruOO frames the big question amid the Astra + robotics hype: what should we work on that the next LLM won't solve? His answer: hardware-algorithm co-design, exemplified by Reward AI's new release.
- Omnibody Hand is designed around function: useful contact points, in-hand reorientation, and smooth transitions between precision and power grasps, in a compact 7-DoF design combining thumb-index dexterity with coordinated finger motion.
- Paired with OMI-1, the system enables cross-embodiment dexterity, scaling up from the earlier DexCap work by the same team.
- The author also plans a blog post of study notes on hardware for dexterity.
More from Embodied
- Zipeng Fu's RewardAI team draws praise for OM-1 robot foundation model — zipengfu · 2026-09-15
- RewardAI unveils OM-1 robot foundation model with zero-shot cross-embodiment — zipengfu · 2026-09-15
- RewardAI Unveils OM-1 Robot Foundation Model: Zero-Shot Generalization From Human Data Alone — yifengzhu_ut · 2026-09-15
- Hackathon Project Skillio Turns Vision Pro Into an AR Screw-Driving Coach Agent — seanmcdonaldxyz · 2026-09-15
- Autonomous robot unloads trucks without any fixed infrastructure — TinfoilTricorn · 2026-09-15
- Tesla FSD handles full descent on Slovenia's highest road at 2,055 m — FlorianGallwitz · 2026-09-15