Learning Robust Real-World Dexterous Grasping Policies via Implicit Shape Augmentation

TL;DR

This paper introduces ISAGrasp, a system that uses implicit shape augmentation to generate diverse training data from limited demonstrations, enabling robust real-world grasping with a dexterous robotic hand.

Contribution

The paper presents a novel implicit shape augmentation method that leverages human demonstrations to improve grasping policies for unseen objects.

Findings

Achieves 79% success rate on grasping unseen objects in the real world.

Effectively handles new semantic classes of objects.

Demonstrates robust grasping with a four-fingered Allegro hand.

Abstract

Dexterous robotic hands have the capability to interact with a wide variety of household objects to perform tasks like grasping. However, learning robust real world grasping policies for arbitrary objects has proven challenging due to the difficulty of generating high quality training data. In this work, we propose a learning system (ISAGrasp) for leveraging a small number of human demonstrations to bootstrap the generation of a much larger dataset containing successful grasps on a variety of novel objects. Our key insight is to use a correspondence-aware implicit generative model to deform object meshes and demonstrated human grasps in order to generate a diverse dataset of novel objects and successful grasps for supervised learning, while maintaining semantic realism. We use this dataset to train a robust grasping policy in simulation which can be deployed in the real world. We demonstrate grasping performance with a four-fingered Allegro hand in both simulation and the real world, and show this method can handle entirely new semantic classes and achieve a 79% success rate on grasping unseen objects in the real world.