Reward AI Unveils OM-1: A Robot Policy Trained Purely on Human Demonstrations, Without Teleoperation or On-Robot Data
Reward AI, a robotics startup whose team previously worked on DexCap, HumanPlus, and ALOHA, has released OM-1 (Omnibody Model 1), a general-purpose manipulation policy that learns from humans wearing a sensorized glove and then runs on industrial arms and humanoids at human speed. The key finding: no teleoperation data and no on-robot data are used in training. The system follows a single principle: One Model, One Data Interface, Any Body.
Is it deployable? Not yet. OM-1 is Reward AI's in-house policy. No weights, code, dataset, or API have been released, so developers cannot run it on their own hardware at this time.
Why Skip Robot Data?
Most robot foundation policies train on teleoperated or self-collected robot data, which binds the dataset to one embodiment. Reward AI argues that human-level manipulation will not emerge from more of this data or more compute, citing Anderson's "More Is Different." Instead, the team designs capture, learning, and control as one pipeline, so demonstrations recorded today can train robot bodies that do not exist yet.
Omnibody Hand: A 7-DoF Wearable
The stack begins with the Omnibody Hand, a wearable that extends the team's earlier DexCap work on portable motion capture. Rather than copying the human hand joint by joint, it uses a seven-degree-of-freedom design built around the functions that matter: choosing contact points, reorienting objects in-hand, and moving between precision and power grasps. It captures thumb-index pinching, thumb and index flexion, and coupled motion of the middle, ring, and little fingers at the MCP joints.
Ergonomics is treated as a data-quality issue: a device that slips or constrains the wearer produces a compensated grasp. A distal flexion mechanism absorbs differences in finger length, so no per-user adjustment is needed.
One Data Interface: Capturing Contact at Human Speed
The One Data Interface turns wearer motion into training data with no staged setup and no supervisor. The design target is conveyor-belt sorting, where a person spots, grasps, and tosses an object in a fraction of a second. To cover the whole interaction, the glove combines high-frequency tactile sensing, proximity sensing for the pre-contact approach, and global-shutter in-hand cameras that hold context through rapid motion.
Hand pose tracking is where Reward AI reports its first quantitative result. Visual-inertial tracking is the common default, but its accuracy at fast reversals is capped by the visual update rate. Reward AI augments it with electromagnetic sensing plus disturbance compensation. Moving both trackers between two...
via MarkTechPost