Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
This addresses the problem of high training costs for robotic manipulation in 3D environments, representing an incremental improvement through symmetry incorporation.
The paper tackles the sample inefficiency problem in training robotic agents for 3D pick-and-place manipulation tasks by proposing Fourier Transporter (FourTran), which leverages SE(d)×SE(d) symmetry to achieve state-of-the-art results on the RLbench benchmark.
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 predict pick-place actions on new environments. FourTran is constrained to incorporate symmetries of the pick and place actions independently. Our method utilizes a fiber space Fourier transformation that allows for memory-efficient construction. We test our proposed network on the RLbench benchmark and achieve state-of-the-art results across various tasks.