most citedEquivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

11 citations · 11 across the 2 of their papers we have counts for

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2022★ 11 cited

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

Hyunwoo Ryu, Hong-in Lee, Jeong-Hoon Lee +1

End-to-end learning for visual robotic manipulation is known to suffer from sample inefficiency, requiring large numbers of demonstrations. The spatial roto-translation equivarianc…