Stabilize to Act: Learning to Coordinate for Bimanual Manipulation

TL;DR

This paper introduces BUDS, a novel framework for bimanual manipulation that uses a stabilizing arm to simplify the environment, enabling more effective learning of complex tasks with limited demonstrations.

Contribution

The paper proposes a role assignment framework inspired by humans, using a stabilizing arm and a learned classifier to improve bimanual control in robotics, demonstrating significant success with minimal demonstrations.

Findings

BUDS achieves 76.9% success on real-world bimanual tasks.

BUDS generalizes to out-of-distribution objects with 52.7% success.

BUDS outperforms unstructured baseline by 56.0% in success rate.

Abstract

Key to rich, dexterous manipulation in the real world is the ability to coordinate control across two hands. However, while the promise afforded by bimanual robotic systems is immense, constructing control policies for dual arm autonomous systems brings inherent difficulties. One such difficulty is the high-dimensionality of the bimanual action space, which adds complexity to both model-based and data-driven methods. We counteract this challenge by drawing inspiration from humans to propose a novel role assignment framework: a stabilizing arm holds an object in place to simplify the environment while an acting arm executes the task. We instantiate this framework with BimanUal Dexterity from Stabilization (BUDS), which uses a learned restabilizing classifier to alternate between updating a learned stabilization position to keep the environment unchanged, and accomplishing the task with an acting policy learned from demonstrations. We evaluate BUDS on four bimanual tasks of varying complexities on real-world robots, such as zipping jackets and cutting vegetables. Given only 20 demonstrations, BUDS achieves 76.9% task success across our task suite, and generalizes to out-of-distribution objects within a class with a 52.7% success rate. BUDS is 56.0% more successful than an unstructured baseline that instead learns a BC stabilizing policy due to the precision required of these complex tasks. Supplementary material and videos can be found at https://sites.google.com/view/stabilizetoact .