Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation

TL;DR

This paper introduces a symmetry-aware flow matching approach for bimanual mobile manipulation, leveraging morphological symmetry to improve policy generalization and sample efficiency in robotic tasks.

Contribution

It formalizes the symmetry prior in bimanual robots and develops a $ ext{C}_2$-equivariant flow matching policy that enhances zero-shot generalization to mirrored configurations.

Findings

Symmetry-informed policies improve sample efficiency.

Policies achieve zero-shot generalization to mirrored configurations.

Validated on real-world TIAGo++ robot tasks.

Abstract

Mobile manipulation requires coordinated control of high-dimensional, bimanual robots. Imitation learning methods have been broadly used to solve these robotic tasks, yet typically ignore the bilateral morphological symmetry inherent in such systems. We argue that morphological symmetry is an underexplored but crucial inductive bias for learning in bimanual mobile manipulation: knowing how to solve a task in one configuration directly determines how to solve its mirrored counterpart. In this paper, we formalize this symmetry prior and show that it constrains optimal bimanual policies to be ambidextrous and equivariant under reflections across the robot's sagittal plane. We introduce a $\mathbb{C}_2$-equivariant flow matching policy that enforces reflective symmetry either via a regularized training loss or an equivariant velocity network. Across planar and 6-DoF mobile manipulation tasks, symmetry-informed policies consistently improve sample efficiency and achieve zero-shot generalization to mirrored configurations absent from the training distribution. We further validate this zero-shot generalization capability on a real-world manipulation task with a TIAGo++ robot. Together, our findings establish morphological symmetry as an effective, generalizable, and scalable inductive bias for ambidextrous generative policy learning.