Kavli Affiliate: Xiang Zhang | First 5 Authors: Joohwan Seo, Joohwan Seo, , , | Summary: This paper presents a framework for learning vision-based robotic policies for contact-rich manipulation tasks that generalize spatially across task configurations. We focus on achieving robust spatial generalization of the policy for the peg-in-hole (PiH) task trained from a small […]
Continue.. EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks