AI RESEARCH
OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer
arXiv CS.CV
•
ArXi:2603.14401v1 Announce Type: cross We present OCRA, an Object-Centric framework for video-based human-to-Robot Action transfer that learns directly from human nstration videos to enable robust manipulation. Object-centric learning emphasizes task-relevant objects and their interactions while filtering out irrelevant background, providing a natural and scalable way to teach robots.