ROLGDec 14, 2024

Fast and Robust Visuomotor Riemannian Flow Matching Policy

arXiv:2412.10855v317 citationsh-index: 14IEEE Trans robot
Originality Incremental advance
AI Analysis

This work addresses the need for fast and robust visuomotor policies in robotics, representing an incremental improvement by adapting flow matching to incorporate geometric constraints.

The paper tackled the problem of slow inference and complex training in diffusion-based visuomotor policies for robotics by introducing Riemannian Flow Matching Policy (RFMP), which achieved efficient training and inference while outperforming Diffusion Policies and Consistency Policies on ten simulated and real-world tasks.

Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to costly denoising processes or require complex sequential training arising from recent distilling approaches. This paper introduces Riemannian Flow Matching Policy (RFMP), a model that inherits the easy training and fast inference capabilities of flow matching (FM). Moreover, RFMP inherently incorporates geometric constraints commonly found in realistic robotic applications, as the robot state resides on a Riemannian manifold. To enhance the robustness of RFMP, we propose Stable RFMP (SRFMP), which leverages LaSalle's invariance principle to equip the dynamics of FM with stability to the support of a target Riemannian distribution. Rigorous evaluation on ten simulated and real-world tasks show that RFMP successfully learns and synthesizes complex sensorimotor policies on Euclidean and Riemannian spaces with efficient training and inference phases, outperforming Diffusion Policies and Consistency Policies.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes