Primary-Fine Decoupling for Action Generation in Robotic Imitation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lei, Xiaohan, Wang, Min, Zhou, Wengang, Lu, Xingyu, Li, Houqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910032763813888
author Lei, Xiaohan
Wang, Min
Zhou, Wengang
Lu, Xingyu
Li, Houqiang
author_facet Lei, Xiaohan
Wang, Min
Zhou, Wengang
Lu, Xingyu
Li, Houqiang
contents Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as either a discrete set of tokens or a continuous, latent-variable distribution. However, both approaches present trade-offs: some methods discretize actions into tokens and therefore lose fine-grained action variations, while others generate continuous actions in a single stage tend to produce unstable mode transitions. To address these limitations, we propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations. First, we compress action chunks into a small set of discrete modes, enabling a lightweight policy to select consistent coarse modes and avoid mode bouncing. Second, a mode conditioned MeanFlow policy is learned to generate high-fidelity continuous actions. Theoretically, we prove PF-DAG's two-stage design achieves a strictly lower MSE bound than single-stage generative policies. Empirically, PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks. It further generalizes to real-world tactile dexterous manipulation tasks. Our work demonstrates that explicit mode-level decoupling enables both robust multi-modal modeling and reactive closed-loop control for robotic manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21684
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Primary-Fine Decoupling for Action Generation in Robotic Imitation
Lei, Xiaohan
Wang, Min
Zhou, Wengang
Lu, Xingyu
Li, Houqiang
Robotics
Machine Learning
Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning. To this end, existing approaches often model the action space as either a discrete set of tokens or a continuous, latent-variable distribution. However, both approaches present trade-offs: some methods discretize actions into tokens and therefore lose fine-grained action variations, while others generate continuous actions in a single stage tend to produce unstable mode transitions. To address these limitations, we propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations. First, we compress action chunks into a small set of discrete modes, enabling a lightweight policy to select consistent coarse modes and avoid mode bouncing. Second, a mode conditioned MeanFlow policy is learned to generate high-fidelity continuous actions. Theoretically, we prove PF-DAG's two-stage design achieves a strictly lower MSE bound than single-stage generative policies. Empirically, PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks. It further generalizes to real-world tactile dexterous manipulation tasks. Our work demonstrates that explicit mode-level decoupling enables both robust multi-modal modeling and reactive closed-loop control for robotic manipulation.
title Primary-Fine Decoupling for Action Generation in Robotic Imitation
topic Robotics
Machine Learning
url https://arxiv.org/abs/2602.21684