Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation

2026-05-12

AI Summary

This work addresses the common oversight of the inherent sagittal-plane reflection symmetry in dual-arm mobile manipulation, which often leads to inefficient policy learning and poor generalization. The study formally introduces this morphological symmetry as a prior and proposes a C₂-equivariant flow-matching policy that explicitly enforces reflection symmetry either through an equivariant velocity network or a symmetry-aware regularization loss. Evaluated on both planar and 6-DoF manipulation tasks, the approach substantially improves sample efficiency and demonstrates zero-shot generalization to unseen mirrored configurations when deployed on a real TIAGo++ robot.

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.

Problem

• bimanual manipulation
• morphological symmetry
• imitation learning
• zero-shot generalization
• equivariance

Innovation

• morphological symmetry
• equivariant policy
• flow matching
• bimanual manipulation
• zero-shot generalization