‘One Model, One Data Interface, Any Body’: Reward AI’s OM-1 Learns Manipulation Straight From Humans
Reward AI has introduced OM-1, a general-purpose robot foundation model designed to acquire physical intelligence directly from human manipulation data. The company claims the system can generalize zero-shot across robot bodies — including tabletop arms, industrial arms, and humanoids — without teleoperation data, on-robot training, or robot-specific fine-tuning.
The foundation of the system is the Omnibody Hand, a wearable seven-degree-of-freedom device built on the team’s prior Stanford research, DexCap. Rather than replicating the human hand joint by joint, the hand is designed around functional capabilities: selecting useful contact points, reorienting objects in the palm, and transitioning smoothly between precision and power grasps. An ergonomic fit accommodates variations in hand size and finger proportion, ensuring recorded movements reflect natural, uncompensated human behavior.
On top of this sits the “One Data Interface” layer, which combines high-frequency tactile feedback, proximity sensing, global-shutter in-hand cameras, and electromagnetic hand-pose tracking to capture demonstrations at full human pace. The company reports that augmenting visual-inertial tracking with electromagnetic sensing reduced mean overshoot error by 60% at high speed in controlled tests, and that force data is recorded along trajectories so demonstrations encode both the path and the effort behind it.
Learning from People, Not Robots
OM-1 is trained exclusively on human data. According to Reward AI, neither teleoperation nor any on-robot experience is used during training; the policy instead learns to generate robot actions directly from human motion, distilling what the team describes as subconscious physical intelligence into a single, unified model. Because all demonstrations arrive through the same data interface, pre-training and post-training are merged into a single stage — new data requires no re-collection and no separate training pipeline per robot, task, or deployment.
Architecturally, OM-1 processes each sensory modality — images, tactile signals, inter-finger proximity, and hand-pose trajectories — at its native sampling rate, preserving high-frequency contact cues alongside slower visual context. A temporal history of these streams allows the policy to reason about how contact and task progress evolve. Beneath it, a reinforcement learning-based control layer running at high frequency translates actions into actuation for any given body, compensating for dynamics, disturbances, and system delays, while optimizing transitions between successive policy predictions to keep motion smooth at speed.
In its conclusion, the company states that OM-1 can pick up brand-new tasks — including challenging dynamics and long horizons — from less than 30 minutes of data. If validated, the approach positions human demonstration capture, sensing, learning, inference, and control as a single integrated stack — one the company frames as future-proof for robot hardware that has yet to be designed.
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
More articles
Alisa, a dedicated journalist at the MPost, specializes in crypto, AI, investments, and the expansive realm of Web3. With a keen eye for emerging trends and technologies, she delivers comprehensive coverage to inform and engage readers in the ever-evolving landscape of digital finance.
