MirrorDuo: Reflection-Consistent Visuomotor Learning from Mirrored Demonstration Pairs

Zheyu Zhuang, Ruiyu Wang, Giovanni Luca Marchetti, Florian T. Pokorny, Danica Kragic

Keywords: Behavior Cloning, Data Efficiency, Robotic Manipulation

TL;DR: MirrorDuo is a mirroring-based formulation for image-based behaviour cloning that generates paired demonstrations to improve data efficiency, boost low-data performance, and enable skill transfer to mirrored scenes with minimal degradation.

Abstract: Image-based behaviour cloning leverages demonstrations captured from ubiquitous RGB cameras, enabling impressive visuomotor performance. However, it remains constrained by the cost of collecting sufficiently diverse demonstrations, especially for generalizing across workspace variations. We propose MirrorDuo, a mirroring-based formulation that operates on image, proprioception, and full 6-DoF end-effector action tuples, generating a mirrored counterpart for each original demonstration, effectively achieving ``collect one, get one for free." It can be applied as a data augmentation strategy for existing learning pipelines, such as standard behaviour cloning or diffusion policy, or as a structural prior for reflection-equivariant policy networks. By leveraging the overlap between the original and mirrored domains, MirrorDuo achieves significantly improved performance under the same data budget when demonstrations are evenly distributed across both sides of the workspace. When demonstrations are confined to one side, MirrorDuo enables efficient skill transfer to the mirrored workspace with as few as zero or just 5 demonstrations in the target arrangement.

Submission Number: 823