DemoGrasp: Few-Shot Learning for Robotic Grasping with Human Demonstration

TL;DR

This paper introduces DemoGrasp, a few-shot learning method that enables robots to grasp objects using minimal human demonstration, overcoming the need for large datasets or specific geometries, and demonstrating effectiveness in real and synthetic environments.

Contribution

DemoGrasp is a novel approach that leverages a short human demonstration to teach robots grasping, eliminating the need for extensive annotations or geometric restrictions.

Findings

Effective in real and synthetic environments

Outperforms previous methods in generalization

Requires minimal human demonstration

Abstract

The ability to successfully grasp objects is crucial in robotics, as it enables several interactive downstream applications. To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set of grasping points. While the former approaches do not scale well to multiple object instances or classes yet, the latter require large annotated datasets and are hampered by their poor generalization capabilities to new geometries. To overcome these shortcomings, we propose to teach a robot how to grasp an object with a simple and short human demonstration. Hence, our approach neither requires many annotated images nor is it restricted to a specific geometry. We first present a small sequence of RGB-D images displaying a human-object interaction. This sequence is then leveraged to build associated hand and object meshes that represent the depicted interaction. Subsequently, we complete missing parts of the reconstructed object shape and estimate the relative transformation between the reconstruction and the visible object in the scene. Finally, we transfer the a-priori knowledge from the relative pose between object and human hand with the estimate of the current object pose in the scene into necessary grasping instructions for the robot. Exhaustive evaluations with Toyota's Human Support Robot (HSR) in real and synthetic environments demonstrate the applicability of our proposed methodology and its advantage in comparison to previous approaches.