RewardAI Launches OM-1 Foundation Model Trained on Natural Human Motion
lukas_m_ziegler · x · 2026-09-15
RewardAI launched OM-1, a robot foundation model that controls everything from tabletop arms to full humanoids, trained entirely on natural human movement data captured via their Omnibody Hand wearable — no robot-specific training or fine-tuning required.
Demo videos show robots autonomously mixing drinks, grabbing bottles, pouring precisely, and stirring at human-like speed, with cross-robot generalization from brief exposure.
More from Embodied
- UCLA's ChairNav teaches autonomous wheelchairs to learn each rider's preferences — zhoubolei · 2026-10-31
- Amazon Echo kills local voice storage: everything goes to the cloud from March 28 — alex_verem · 2026-10-31
- HP paid $116M for Humane, then bricked every $699 AI Pin 10 days later — alex_verem · 2026-10-31
- Moxie, the $800 AI robot friend for kids, went silent overnight after shutdown — alex_verem · 2026-10-31
- Subvocal's YC-backed glasses decode silent speech at 200+ wpm, built in 4 months — garrytan · 2026-10-31
- Nomagic warehouse robots go from bimanual to trimanual, pause to solve tricky picks — m_wulfmeier · 2026-10-31