BridgeData V2: A Dataset for Robot Learning at Scale

Homer Rich Walke, Kevin Black, Tony Z. Zhao, Quan Vuong, Chongyi Zheng, Philippe Hansen-Estruch, Andre Wang He, Vivek Myers, Moo Jin Kim, Max Du, Abraham Lee, Kuan Fang, Chelsea Finn, Sergey Levine
Proceedings of The 7th Conference on Robot Learning, PMLR 229:1723-1736, 2023.

Abstract

We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research in scalable robot learning. BridgeData V2 contains 53,896 trajectories collected across 24 environments on a publicly available low-cost robot. Unlike many existing robotic manipulation datasets, BridgeData V2 provides enough task and environment variability that skills learned from the data generalize across institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments,we apply 6 state-of-the-art imitation learning and offline reinforcement learning methods to the data and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-walke23a, title = {BridgeData V2: A Dataset for Robot Learning at Scale}, author = {Walke, Homer Rich and Black, Kevin and Zhao, Tony Z. and Vuong, Quan and Zheng, Chongyi and Hansen-Estruch, Philippe and He, Andre Wang and Myers, Vivek and Kim, Moo Jin and Du, Max and Lee, Abraham and Fang, Kuan and Finn, Chelsea and Levine, Sergey}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {1723--1736}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/walke23a/walke23a.pdf}, url = {https://proceedings.mlr.press/v229/walke23a.html}, abstract = {We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research in scalable robot learning. BridgeData V2 contains 53,896 trajectories collected across 24 environments on a publicly available low-cost robot. Unlike many existing robotic manipulation datasets, BridgeData V2 provides enough task and environment variability that skills learned from the data generalize across institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments,we apply 6 state-of-the-art imitation learning and offline reinforcement learning methods to the data and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods.} }
Endnote
%0 Conference Paper %T BridgeData V2: A Dataset for Robot Learning at Scale %A Homer Rich Walke %A Kevin Black %A Tony Z. Zhao %A Quan Vuong %A Chongyi Zheng %A Philippe Hansen-Estruch %A Andre Wang He %A Vivek Myers %A Moo Jin Kim %A Max Du %A Abraham Lee %A Kuan Fang %A Chelsea Finn %A Sergey Levine %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-walke23a %I PMLR %P 1723--1736 %U https://proceedings.mlr.press/v229/walke23a.html %V 229 %X We introduce BridgeData V2, a large and diverse dataset of robotic manipulation behaviors designed to facilitate research in scalable robot learning. BridgeData V2 contains 53,896 trajectories collected across 24 environments on a publicly available low-cost robot. Unlike many existing robotic manipulation datasets, BridgeData V2 provides enough task and environment variability that skills learned from the data generalize across institutions, making the dataset a useful resource for a broad range of researchers. Additionally, the dataset is compatible with a wide variety of open-vocabulary, multi-task learning methods conditioned on goal images or natural language instructions. In our experiments,we apply 6 state-of-the-art imitation learning and offline reinforcement learning methods to the data and find that they succeed on a suite of tasks requiring varying amounts of generalization. We also demonstrate that the performance of these methods improves with more data and higher capacity models. By publicly sharing BridgeData V2 and our pre-trained models, we aim to accelerate research in scalable robot learning methods.
APA
Walke, H.R., Black, K., Zhao, T.Z., Vuong, Q., Zheng, C., Hansen-Estruch, P., He, A.W., Myers, V., Kim, M.J., Du, M., Lee, A., Fang, K., Finn, C. & Levine, S.. (2023). BridgeData V2: A Dataset for Robot Learning at Scale. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:1723-1736 Available from https://proceedings.mlr.press/v229/walke23a.html.

Related Material