Equivariant Transporter Network

TL;DR

This paper introduces an enhanced Transporter Net model that is equivariant to both pick and place orientations, significantly improving sample efficiency and success rates in robotic manipulation tasks.

Contribution

It proposes a novel equivariant Transporter Net that generalizes both pick and place knowledge across orientations, advancing robotic manipulation capabilities.

Findings

Improved success rates over baseline Transporter Net

Enhanced sample efficiency in manipulation tasks

Generalization of pick and place knowledge across orientations

Abstract

Transporter Net is a recently proposed framework for pick and place that is able to learn good manipulation policies from a very few expert demonstrations. A key reason why Transporter Net is so sample efficient is that the model incorporates rotational equivariance into the pick module, i.e. the model immediately generalizes learned pick knowledge to objects presented in different orientations. This paper proposes a novel version of Transporter Net that is equivariant to both pick and place orientation. As a result, our model immediately generalizes place knowledge to different place orientations in addition to generalizing pick knowledge as before. Ultimately, our new model is more sample efficient and achieves better pick and place success rates than the baseline Transporter Net model.