AI RESEARCH
GIFT: Geometry-Induced Functional Transfer for Category-level Object Manipulation
arXiv CS.LG
•
ArXi:2503.15371v2 Announce Type: replace-cross Robotic manipulation of unfamiliar objects in new environments is challenging due to limited generalisation capabilities. We propose a new skill transfer framework, GIFT (Geometry-Induced Functional Transfer), which enables a robot to transfer complex object manipulation skills and constraints from a single human nstration. Our approach addresses the challenge of skill acquisition and task execution by deriving geometric representations from nstrations focusing on object-centric interactions.