ALOHA Unleashed: A Simple Recipe for Robot Dexterity

Tony Z. Zhao, Jonathan Tompson, Danny Driess, Pete Florence, Seyed Kamyar Seyed Ghasemipour, Chelsea Finn, Ayzaan Wahid
Proceedings of The 8th Conference on Robot Learning, PMLR 270:1910-1924, 2025.

Abstract

Recent work has shown promising results for learning end-to-end robot policies using imitation learning. In this work we address the question of how far can we push imitation learning for challenging dexterous manipulation tasks. We show that a simple recipe of large scale data collection on the ALOHA 2 platform, combined with expressive models such as Diffusion Policies, can be effective in learning challenging bimanual manipulation tasks involving deformable objects and complex contact rich dynamics. We demonstrate our recipe on 5 challenging real-world and 3 simulated tasks and demonstrate improved performance over state-of-the-art baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-zhao25b, title = {ALOHA Unleashed: A Simple Recipe for Robot Dexterity}, author = {Zhao, Tony Z. and Tompson, Jonathan and Driess, Danny and Florence, Pete and Ghasemipour, Seyed Kamyar Seyed and Finn, Chelsea and Wahid, Ayzaan}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {1910--1924}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/zhao25b/zhao25b.pdf}, url = {https://proceedings.mlr.press/v270/zhao25b.html}, abstract = {Recent work has shown promising results for learning end-to-end robot policies using imitation learning. In this work we address the question of how far can we push imitation learning for challenging dexterous manipulation tasks. We show that a simple recipe of large scale data collection on the ALOHA 2 platform, combined with expressive models such as Diffusion Policies, can be effective in learning challenging bimanual manipulation tasks involving deformable objects and complex contact rich dynamics. We demonstrate our recipe on 5 challenging real-world and 3 simulated tasks and demonstrate improved performance over state-of-the-art baselines.} }
Endnote
%0 Conference Paper %T ALOHA Unleashed: A Simple Recipe for Robot Dexterity %A Tony Z. Zhao %A Jonathan Tompson %A Danny Driess %A Pete Florence %A Seyed Kamyar Seyed Ghasemipour %A Chelsea Finn %A Ayzaan Wahid %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-zhao25b %I PMLR %P 1910--1924 %U https://proceedings.mlr.press/v270/zhao25b.html %V 270 %X Recent work has shown promising results for learning end-to-end robot policies using imitation learning. In this work we address the question of how far can we push imitation learning for challenging dexterous manipulation tasks. We show that a simple recipe of large scale data collection on the ALOHA 2 platform, combined with expressive models such as Diffusion Policies, can be effective in learning challenging bimanual manipulation tasks involving deformable objects and complex contact rich dynamics. We demonstrate our recipe on 5 challenging real-world and 3 simulated tasks and demonstrate improved performance over state-of-the-art baselines.
APA
Zhao, T.Z., Tompson, J., Driess, D., Florence, P., Ghasemipour, S.K.S., Finn, C. & Wahid, A.. (2025). ALOHA Unleashed: A Simple Recipe for Robot Dexterity. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:1910-1924 Available from https://proceedings.mlr.press/v270/zhao25b.html.

Related Material