{"slug": "reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with", "title": "Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data", "summary": "Reward AI 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 and learns a new task from under 30 minutes of data, pairing 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.", "body_md": "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.\n\nThe post [Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data](https://www.marktechpost.com/2026/09/14/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with-no-teleoperation-or-on-robot-data/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with", "canonical_source": "https://www.marktechpost.com/2026/09/14/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with-no-teleoperation-or-on-robot-data/", "published_at": "2026-09-14 21:08:17+00:00", "updated_at": "2026-09-14 23:02:03.982999+00:00", "lang": "en", "topics": ["robotics", "machine-learning", "ai-research"], "entities": ["Reward AI", "OM-1", "Omnibody Model 1", "MarkTechPost"], "alternates": {"html": "https://wpnews.pro/news/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with", "markdown": "https://wpnews.pro/news/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with.md", "text": "https://wpnews.pro/news/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with.txt", "jsonld": "https://wpnews.pro/news/reward-ai-releases-om-1-a-robot-policy-trained-on-human-demonstrations-only-with.jsonld"}}