RT-1: Robotics Transformer for Real-World Control at Scale

TL;DR

This paper introduces the Robotics Transformer, a high-capacity model trained on large-scale, diverse robotic data, demonstrating improved generalization and scalability for real-world robotic control tasks.

Contribution

It presents a novel Transformer-based model architecture for robotics, emphasizing open-ended, task-agnostic training and scalability in data and model size.

Findings

The Robotics Transformer generalizes well across tasks with diverse data.

Model performance improves with increased data and model size.

Open-ended training enhances robotic control capabilities.

Abstract

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance. While this capability has been demonstrated in other fields such as computer vision, natural language processing or speech recognition, it remains to be shown in robotics, where the generalization capabilities of the models are particularly critical due to the difficulty of collecting real-world robotic data. We argue that one of the keys to the success of such general robotic models lies with open-ended task-agnostic training, combined with high-capacity architectures that can absorb all of the diverse, robotic data. In this paper, we present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks. The project's website and videos can be found at robotics-transformer1.github.io