Saved in:
Bibliographic Details
Main Authors: Xue, Rong, Mao, Jiageng, Zhang, Mingtong, Wang, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08583
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909898542940160
author Xue, Rong
Mao, Jiageng
Zhang, Mingtong
Wang, Yue
author_facet Xue, Rong
Mao, Jiageng
Zhang, Mingtong
Wang, Yue
contents Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a selective flow alignment strategy, which leverages expert demonstrations to selectively correct generated actions and restore consistency with observations, while preserving multimodality. This design introduces a consistency correction mechanism that ensures generated actions remain observation-aligned without sacrificing the efficiency of one-step flow inference. Extensive experiments across both simulated and real-world manipulation tasks show that SeFA Policy surpasses state-of-the-art diffusion-based and flow-based policies, achieving superior accuracy and robustness while reducing inference latency by over 98%. By unifying rectified flow efficiency with observation-consistent action generation, SeFA provides a scalable and dependable solution for real-time visuomotor policy learning. Code is available on https://github.com/RongXueZoe/SeFA.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08583
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
Xue, Rong
Mao, Jiageng
Zhang, Mingtong
Wang, Yue
Robotics
Machine Learning
Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a selective flow alignment strategy, which leverages expert demonstrations to selectively correct generated actions and restore consistency with observations, while preserving multimodality. This design introduces a consistency correction mechanism that ensures generated actions remain observation-aligned without sacrificing the efficiency of one-step flow inference. Extensive experiments across both simulated and real-world manipulation tasks show that SeFA Policy surpasses state-of-the-art diffusion-based and flow-based policies, achieving superior accuracy and robustness while reducing inference latency by over 98%. By unifying rectified flow efficiency with observation-consistent action generation, SeFA provides a scalable and dependable solution for real-time visuomotor policy learning. Code is available on https://github.com/RongXueZoe/SeFA.
title SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
topic Robotics
Machine Learning
url https://arxiv.org/abs/2511.08583