21:08
2026-09-14
marktechpost.com
robotics
Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data
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.…