OM-1 robot foundation model generalizes zero-shot to arms and humanoids, no robot data needed
zipengfu · x · 2026-09-15
The RewardAI team introduces OM-1, its first robot foundation model that zero-shot generalizes across tabletop arms, industrial arms, and humanoids.
Key claims:
- Learned directly from human manipulation data — no teleoperation or robot-collected data
- Near human-level dexterity and efficiency
- Multi-robot collaboration support
Reposters including Zipeng Fu hail it as meaningful progress from academic research in robotics. If the claims hold, training a general robot model without robot data is a direct challenge to the prevailing teleop data-pipeline approach.
Related event: Physical Intelligence Unveils OM-1 Robot Foundation Model(35 posts)→
More from Embodied
- World Engine claims $1M to $100M ARR in 3 months building physical AI infrastructure — yuewang314 · 2026-09-15
- Eren Chen launches robot hardware shop: Agibot humanoids from $29,999, US shipping — chris_j_paxton · 2026-09-15
- OpenAI acquires camera startup Glass Imaging for over $300M, WSJ reports — rohanpaul_ai · 2026-09-15
- Amid new robotics launches, a pointer to best practices for policy evaluations — eigenron · 2026-09-15
- "Learning robotics today is like learning to code in 2010" — Paimaamu · 2026-09-15
- Mecha Corp unveils Spike, an RL-trained bipedal robot running purely on proprioception — Scobleizer · 2026-09-15