Leveraging Symmetries in Pick and Place

TL;DR

This paper introduces Equivariant Transporter Net, a neural network model that explicitly incorporates symmetries in robotic pick and place tasks, leading to improved generalization and sample efficiency in imitation learning.

Contribution

It analytically studies symmetries in planar pick and place and develops an equivariant neural model capturing all these symmetries, enhancing generalization.

Findings

Significantly more sample efficient than non-symmetric models.

Can generalize pick and place knowledge to different poses.

Achieves effective imitation learning with few demonstrations.

Abstract

Robotic pick and place tasks are symmetric under translations and rotations of both the object to be picked and the desired place pose. For example, if the pick object is rotated or translated, then the optimal pick action should also rotate or translate. The same is true for the place pose; if the desired place pose changes, then the place action should also transform accordingly. A recently proposed pick and place framework known as Transporter Net captures some of these symmetries, but not all. This paper analytically studies the symmetries present in planar robotic pick and place and proposes a method of incorporating equivariant neural models into Transporter Net in a way that captures all symmetries. The new model, which we call Equivariant Transporter Net, is equivariant to both pick and place symmetries and can immediately generalize pick and place knowledge to different pick and place poses. We evaluate the new model empirically and show that it is much more sample efficient than the non-symmetric version, resulting in a system that can imitate demonstrated pick and place behavior using very few human demonstrations on a variety of imitation learning tasks.