EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation

TL;DR

EquiBim introduces a symmetry-equivariant policy learning framework for bimanual manipulation, leveraging physical symmetry as a group action to improve robustness and performance in dual-arm robotic tasks.

Contribution

The paper presents a novel, model-agnostic framework that enforces bilateral equivariance in imitation learning for dual-arm robots, accommodating diverse observation and action modalities.

Findings

Improves performance and robustness in simulation and real-world dual-arm tasks.

Effectively integrates with various observation modalities and action representations.

Enhances symmetry-aware generalization in bimanual manipulation policies.

Abstract

Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not explicitly account for the physical symmetries of robotic systems, often resulting in asymmetric or inconsistent behaviors under symmetric observations. This limitation is particularly pronounced in dual-arm manipulation, where bilateral symmetry is inherent to both the robot morphology and the structure of many tasks. In this paper, we introduce EquiBim, a symmetry-equivariant policy learning framework for bimanual manipulation that enforces bilateral equivariance between observations and actions during training. Our approach formulates physical symmetry as a group action on both observation and action spaces, and imposes an equivariance constraint on policy predictions under symmetric transformations. The framework is model-agnostic and can be seamlessly integrated into a wide range of imitation learning pipelines with diverse observation modalities and action representations, including point cloud-based and image-based policies, as well as both end-effector-space and joint-space parameterizations. We evaluate EquiBim on RoboTwin, a dual-arm robotic platform with symmetric kinematics, and evaluate it across diverse observation and action configurations in simulation. We further validate the approach on a real-world dual-arm system. Across both simulation and physical experiments, our method consistently improves performance and robustness under distribution shifts. These results suggest that explicitly enforcing physical symmetry provides a simple yet effective inductive bias for bimanual robot learning.