ALOHA Unleashed: A Simple Recipe for Robot Dexterity

TL;DR

This paper demonstrates that large-scale data collection combined with expressive diffusion models significantly advances imitation learning for complex bimanual dexterous manipulation tasks involving deformable objects.

Contribution

It introduces a simple yet effective recipe leveraging large-scale data and diffusion policies to improve robot dexterity in challenging manipulation tasks.

Findings

Successful application on 8 real-world and simulated tasks

Outperforms state-of-the-art baselines

Shows effectiveness of large-scale data and diffusion models

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. The project website and videos can be found at aloha-unleashed.github.io.