Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sochopoulos, Andreas, Malkin, Nikolay, Tsagkas, Nikolaos, Moura, João, Gienger, Michael, Vijayakumar, Sethu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913816260902912
author Sochopoulos, Andreas
Malkin, Nikolay
Tsagkas, Nikolaos
Moura, João
Gienger, Michael
Vijayakumar, Sethu
author_facet Sochopoulos, Andreas
Malkin, Nikolay
Tsagkas, Nikolaos
Moura, João
Gienger, Michael
Vijayakumar, Sethu
contents Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the numerical integration of an ODE or SDE, limits their applicability as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples to enforce straight solutions in the flow ODE for robot action generation tasks. We show that naively coupling noise and samples fails in conditional tasks and propose incorporating condition variables into the coupling process to improve few-step performance. The proposed few-step policy achieves a 4% higher success rate with a 10x speed-up compared to Diffusion Policy on a diverse set of simulation tasks. Moreover, it produces high-quality and diverse action trajectories within 1-2 steps on a set of real-world robot tasks. Our method also retains the same training complexity as Diffusion Policy and vanilla Flow Matching, in contrast to distillation-based approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings
Sochopoulos, Andreas
Malkin, Nikolay
Tsagkas, Nikolaos
Moura, João
Gienger, Michael
Vijayakumar, Sethu
Robotics
Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the numerical integration of an ODE or SDE, limits their applicability as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples to enforce straight solutions in the flow ODE for robot action generation tasks. We show that naively coupling noise and samples fails in conditional tasks and propose incorporating condition variables into the coupling process to improve few-step performance. The proposed few-step policy achieves a 4% higher success rate with a 10x speed-up compared to Diffusion Policy on a diverse set of simulation tasks. Moreover, it produces high-quality and diverse action trajectories within 1-2 steps on a set of real-world robot tasks. Our method also retains the same training complexity as Diffusion Policy and vanilla Flow Matching, in contrast to distillation-based approaches.
title Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings
topic Robotics
url https://arxiv.org/abs/2505.01179