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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-08
Main Authors: Brohan, Anthony, Brown, Noah, Carbajal, Justice, Chebotar, Yevgen, Dabis, Joseph, Finn, Chelsea, Gopalakrishnan, Keerthana, Hausman, Karol, Herzog, Alex, Hsu, Jasmine, Ibarz, Julian, Ichter, Brian, Irpan, Alex, Jackson, Tomas, Jesmonth, Sally, Joshi, Nikhil J, Ryan, Julian, Kalashnikov, Dmitry, Kuang, Yuheng, Leal, Isabel, Lee, Kuang-Huei, Levine, Sergey, Lu, Yao, Malla, Utsav, Manjunath, Deeksha, Mordatch, Igor, Ofir Nachum, Parada, Carolina, Peralta, Jodilyn, Perez, Emily, Pertsch, Karl, Quiambao, Jornell, Rao, Kanishka, Ryoo, Michael, Salazar, Grecia, Sanketi, Pannag, Sayed, Kevin, Singh, Jaspiar, Sontakke, Sumedh, Stone, Austin, Tan, Clayton, Tran, Huong, Vanhoucke, Vincent, Vega, Steve, Vuong, Quan, Xia, Fei, Xiao, Ted, Xu, Peng, Xu, Sichun, Yu, Tianhe, Zitkovich, Brianna
Format: Article
Language:English
Subjects:
Computer vision
Data collection
Datasets
Machine learning
Natural language processing
Robotics
Speech recognition
Transformers
Websites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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
ISSN:2331-8422