Semantically Controllable Augmentations for Generalizable Robot Learning

TL;DR

This paper introduces a novel data augmentation framework using pre-trained image-text generative models to improve robot manipulation policy generalization in unseen real-world environments, reducing the need for extensive real-world data collection.

Contribution

It presents a semantically controllable augmentation method leveraging generative models to synthesize diverse training data, enhancing robot learning generalization without additional data collection costs.

Findings

Enhanced policy generalization in unseen environments

Effective augmentation of robot datasets with synthetic data

Scalable approach applicable to various robotic tasks

Abstract

Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to generalize despite these challenges, it is essential to leverage sources of data or priors beyond the robot's direct experience. In this work, we posit that image-text generative models, which are pre-trained on large corpora of web-scraped data, can serve as such a data source. These generative models encompass a broad range of real-world scenarios beyond a robot's direct experience and can synthesize novel synthetic experiences that expose robotic agents to additional world priors aiding real-world generalization at no extra cost. In particular, our approach leverages pre-trained generative models as an effective tool for data augmentation. We propose a generative augmentation framework for semantically controllable augmentations and rapidly multiplying robot datasets while inducing rich variations that enable real-world generalization. Based on diverse augmentations of robot data, we show how scalable robot manipulation policies can be trained and deployed both in simulation and in unseen real-world environments such as kitchens and table-tops. By demonstrating the effectiveness of image-text generative models in diverse real-world robotic applications, our generative augmentation framework provides a scalable and efficient path for boosting generalization in robot learning at no extra human cost.