RewardAI unveils OM-1 robot foundation model trained on human data only, zero-shot across robots
zipengfu · x · 2026-09-15
RewardAI (with researchers Chen Wang, Yifeng Zhu, Zipeng Fu et al.) introduced OM-1, its first robot foundation model that zero-shot generalizes to tabletop arms, industrial arms, and humanoids. Key points:
- Trained on human manipulation data only — no teleoperation, no on-robot experience, and no pre-train/post-train split: the first-ever demo and the newest one run the same single-stage-trained model
- Full-stack design around one constraint — matching human speed: Omnibody Hand has 7 DoF chosen for function (contact-point selection, in-hand reorientation, precision vs. power grasps) rather than joint-by-joint human mimicry
- One data interface: in-hand cameras combine tactile + proximity + global-shutter sensing; EM-augmented pose tracking cuts high-speed overshoot 60% vs. visual-inertial, keeping data usable at full human pace
- Control: RL-trained in sim, running at high frequency on its own clock so inference latency never stalls motion; supports multi-robot collaboration
The team claims near human-level dexterity and efficiency.
More from Embodied
- Real2Sim2Real is hard: even plugging in a network cable demands high sim fidelity — jonstephens85 · 2026-10-31
- Genspark unveils VoicePad, a $99 five-key AI voice gadget now open for pre-orders — Scobleizer · 2026-10-31
- World's first humanoid robot factory for clothing launches, mass-producing Annie robots — CyberRobooo · 2026-10-31
- Robotics benchmarks feel impossible; Drift builds evals for real deployment sites — jonstephens85 · 2026-10-31
- Tesla's We, Robot promises materialize: Cybercab in production, Robotaxi in six cities — XFreeze · 2026-10-31
- SO-101, AI's 'most famous and infamous' robot, gets official support — jonstephens85 · 2026-10-31