Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours

TL;DR

This paper introduces a large-scale dataset of 50,000 robot grasping attempts collected over 700 hours, enabling training of a CNN for grasp prediction that generalizes well to unseen objects.

Contribution

The authors significantly increase training data for robot grasping, recast the problem as multi-class classification, and propose a multi-stage training approach to improve grasp prediction.

Findings

Large-scale dataset improves grasping accuracy

Multi-stage training enhances model robustness

State-of-the-art generalization to unseen objects

Abstract

Current learning-based robot grasping approaches exploit human-labeled datasets for training the models. However, there are two problems with such a methodology: (a) since each object can be grasped in multiple ways, manually labeling grasp locations is not a trivial task; (b) human labeling is biased by semantics. While there have been attempts to train robots using trial-and-error experiments, the amount of data used in such experiments remains substantially low and hence makes the learner prone to over-fitting. In this paper, we take the leap of increasing the available training data to 40 times more than prior work, leading to a dataset size of 50K data points collected over 700 hours of robot grasping attempts. This allows us to train a Convolutional Neural Network (CNN) for the task of predicting grasp locations without severe overfitting. In our formulation, we recast the regression problem to an 18-way binary classification over image patches. We also present a multi-stage learning approach where a CNN trained in one stage is used to collect hard negatives in subsequent stages. Our experiments clearly show the benefit of using large-scale datasets (and multi-stage training) for the task of grasping. We also compare to several baselines and show state-of-the-art performance on generalization to unseen objects for grasping.