Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D

arXiv:2401.12046v2 Announce Type: replace-cross
Abstract: Many complex robotic manipulation tasks can be decomposed as a sequence of pick and place actions. Training a robotic agent to learn this sequence over many different starting conditions typically requires many iterations or demonstrations, especially in 3D environments. In this work, we propose Fourier Transporter (FourTran) which leverages the two-fold SE(d)xSE(d) symmetry in the pick-place problem to achieve much higher sample efficiency. FourTran is an open-loop behavior cloning method trained using expert demonstrations to …

abstract agent arxiv cs.lg cs.ro environments fourier learn manipulation robotic robotic manipulation tasks training type work