Robotics: Science and Systems XVIII

Sample Efficient Grasp Learning Using Equivariant Models

Xupeng Zhu, Dian Wang, Ondrej Biza, Guanang Su, Robin Walters, Robert Platt


In planar grasp detection, the goal is to learn a function from an image of a scene onto a set of feasible grasp poses in SE(2). In this paper, we recognize that the optimal grasp function is SE(2)-equivariant and can be modeled using an equivariant convolutional neural network. As a result, we are able to significantly improve the sample efficiency of grasp learning, obtaining a good approximation of the grasp function after only 600 grasp attempts. This is few enough that we can learn to grasp completely on a physical robot in about 1.5 hours. Code is available at SE2-equivariant-grasp-learning.



    AUTHOR    = {Xupeng Zhu AND Dian Wang AND Ondrej Biza AND Guanang Su AND Robin Walters AND Robert Platt}, 
    TITLE     = {{Sample Efficient Grasp Learning Using Equivariant Models}}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2022}, 
    ADDRESS   = {New York City, NY, USA}, 
    MONTH     = {June}, 
    DOI       = {10.15607/RSS.2022.XVIII.071}