Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping

TL;DR

This paper demonstrates that combining simulation with domain adaptation, specifically the novel GraspGAN, significantly reduces the need for real-world data in training effective robotic grasping systems from monocular RGB images.

Contribution

It introduces a novel domain adaptation method called GraspGAN and shows how synthetic data and domain adaptation can drastically cut down real-world data requirements for robotic grasping.

Findings

Up to 50 times reduction in real-world samples needed.

Achieved real-world grasping performance comparable to using nearly a million labeled samples.

Effective use of synthetic data with domain adaptation for robotic grasping.

Abstract

Instrumenting and collecting annotated visual grasping datasets to train modern machine learning algorithms can be extremely time-consuming and expensive. An appealing alternative is to use off-the-shelf simulators to render synthetic data for which ground-truth annotations are generated automatically. Unfortunately, models trained purely on simulated data often fail to generalize to the real world. We study how randomized simulated environments and domain adaptation methods can be extended to train a grasping system to grasp novel objects from raw monocular RGB images. We extensively evaluate our approaches with a total of more than 25,000 physical test grasps, studying a range of simulation conditions and domain adaptation methods, including a novel extension of pixel-level domain adaptation that we term the GraspGAN. We show that, by using synthetic data and domain adaptation, we are able to reduce the number of real-world samples needed to achieve a given level of performance by up to 50 times, using only randomly generated simulated objects. We also show that by using only unlabeled real-world data and our GraspGAN methodology, we obtain real-world grasping performance without any real-world labels that is similar to that achieved with 939,777 labeled real-world samples.