OrbitGrasp: $SE(3)$-Equivariant Grasp Learning

TL;DR

OrbitGrasp introduces an $SE(3)$-equivariant model for grasp detection from point clouds, improving accuracy and efficiency in robotic manipulation tasks in unstructured environments.

Contribution

The paper presents a novel $SE(3)$-equivariant framework using spherical harmonics and a UNet-style architecture for improved grasp detection from point clouds.

Findings

Outperforms baseline methods in simulation

Achieves higher grasp detection accuracy in physical experiments

Handles large point clouds efficiently

Abstract

While grasp detection is an important part of any robotic manipulation pipeline, reliable and accurate grasp detection in $SE(3)$ remains a research challenge. Many robotics applications in unstructured environments such as the home or warehouse would benefit a lot from better grasp performance. This paper proposes a novel framework for detecting $SE(3)$ grasp poses based on point cloud input. Our main contribution is to propose an $SE(3)$-equivariant model that maps each point in the cloud to a continuous grasp quality function over the 2-sphere $S^2$ using spherical harmonic basis functions. Compared with reasoning about a finite set of samples, this formulation improves the accuracy and efficiency of our model when a large number of samples would otherwise be needed. In order to accomplish this, we propose a novel variation on EquiFormerV2 that leverages a UNet-style encoder-decoder architecture to enlarge the number of points the model can handle. Our resulting method, which we name $\textit{OrbitGrasp}$, significantly outperforms baselines in both simulation and physical experiments.