One-shot Imitation Learning via Interaction Warping

Ondrej Biza, Skye Thompson, Kishore Reddy Pagidi, Abhinav Kumar, Elise van der Pol, Robin Walters, Thomas Kipf, Jan-Willem van de Meent, Lawson L.S. Wong, Robert Platt

Keywords: 3D manipulation, imitation learning, shape warping

TL;DR: We use shape warping for one-shot learning of SE(3) robotic manipulation policies.

Abstract: Learning robot policies from few demonstrations is crucial in open-ended applications. We propose a new method, Interaction Warping, for one-shot learning SE(3) robotic manipulation policies. We infer the 3D mesh of each object in the environment using shape warping, a technique for aligning point clouds across object instances. Then, we represent manipulation actions as keypoints on objects, which can be warped with the shape of the object. We show successful one-shot imitation learning on three simulated and real-world object re-arrangement tasks. We also demonstrate the ability of our method to predict object meshes and robot grasps in the wild. Webpage: https://shapewarping.github.io.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Website: https://shapewarping.github.io

Code: https://github.com/ondrejbiza/shapewarping

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/one-shot-imitation-learning-via-interaction/code)