Publikation
Fast and Robust Visuomotor Riemannian Flow Matching Policy
Haoran Ding; Noémie Jaquier; Jan Peters; Leonel Rozo
In: IEEE Transactions on Robotics (T-RO), Vol. 41, Pages 5327-5343, arXiv, 2025.
Zusammenfassung
Diffusion-based visuomotor policies excel at learning
complex robotic tasks by effectively combining visual data
with high-dimensional, multi-modal action distributions. How-
ever, 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 con-
straints 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.