Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Haojie Huang, Owen Lewis Howell, Dian Wang, Xupeng Zhu, Robert Platt, Robin Walters
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 ($\text{FourTran}$), which leverages the two-fold $\mathrm{SE}(d)\times\mathrm{SE}(d)$ symmetry in the pick-place problem to achieve much higher sample efficiency. $\text{FourTran}$ is an open-loop behavior cloning method trained using expert demonstrations to predict pick-place actions on new configurations. $\text{FourTran}$ is constrained by the symmetries of the pick and place actions independently. Our method utilizes a fiber space Fourier transformation that allows for memory-efficient computation. Tests on the RLbench benchmark achieve state-of-the-art results across various tasks.
BibTeX
@inproceedings{
huang2024fourier,
title={Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D},
author={Haojie Huang and Owen Lewis Howell and Dian Wang and Xupeng Zhu and Robert Platt and Robin Walters},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=UulwvAU1W0}
}