aiqbench takeAI Products

Reward AI's OM-1 represents a significant architectural shift by eliminating the reliance on teleoperation or direct on-robot data collection for training robot manipulation policies. By leveraging human demonstrations captured via a specialized 7-DoF glove, the system aims to decouple policy learning from specific hardware embodiments, potentially accelerating the deployment of skills across diverse industrial arms and humanoids. While the model remains proprietary with no public weights or API, this approach challenges current paradigms that depend heavily on massive datasets gathered through robot self-interaction.

Sources coveringMarkTechPost, arXiv

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data

MarkTechPostSeptember 14, 20265 min read

Reward AI has released OM-1 (Omnibody Model 1), a general-purpose manipulation policy trained entirely on human demonstrations captured with a 7-DoF wearable glove, with no teleoperation or on-robot data. The policy runs on industrial arms and humanoids at human speed, learns a new task from under 30 minutes of data, and pairs electromagnetic hand tracking (60% lower overshoot than visual-inertial at 67 cm/s) with an RL-trained control layer that runs on its own clock. No weights, code, or API are public yet. The post Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data appeared first on MarkTechPost.

Reward AI, a robotics startup whose team’s prior work includes DexCap, HumanPlus, and ALOHA, has released OM-1, short for Omnibody Model 1. OM-1 is a general-purpose manipulation policy that learns from humans wearing a sensorized glove, then runs on industrial arms and humanoids at human speed. The key findings that stands out: no teleoperation data and no on-robot data go into training. The system follows one principle, ‘One Model, One Data Interface, Any Body,’. Is it deployable? No, OM-1 is Reward AI’s in-house policy. No…

Excerpt shown under the publisher's RSS terms · 85 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article