MirrorDuo: Reflection-Consistent Visuomotor Learning from Mirrored Demonstration Pairs
For robot learning from visual demonstrations, MirrorDuo reduces data collection cost by doubling effective demo count via reflection symmetry, addressing generalization across workspace variations.
MirrorDuo generates mirrored demonstration pairs from single original demos, improving visuomotor policy performance under limited data budgets. It achieves significant gains when demos are evenly distributed across workspace sides and enables zero- or few-shot skill transfer to mirrored workspaces.
Image-based behaviour cloning leverages demonstrations captured from ubiquitous RGB cameras. However, it remains constrained by the cost of collecting diverse demos, especially for generalizing across workspace variations. We propose MirrorDuo, a reflection-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 five demos in the target arrangement.