Query-Centric Diffusion Policy for Generalizable Robotic Assembly

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Ziyi, Lin, Haohong, Liu, Shiqi, Zhao, Ding
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914052134928384
author Xu, Ziyi
Lin, Haohong
Liu, Shiqi
Zhao, Ding
author_facet Xu, Ziyi
Lin, Haohong
Liu, Shiqi
Zhao, Ding
contents The robotic assembly task poses a key challenge in building generalist robots due to the intrinsic complexity of part interactions and the sensitivity to noise perturbations in contact-rich settings. The assembly agent is typically designed in a hierarchical manner: high-level multi-part reasoning and low-level precise control. However, implementing such a hierarchical policy is challenging in practice due to the mismatch between high-level skill queries and low-level execution. To address this, we propose the Query-centric Diffusion Policy (QDP), a hierarchical framework that bridges high-level planning and low-level control by utilizing queries comprising objects, contact points, and skill information. QDP introduces a query-centric mechanism that identifies task-relevant components and uses them to guide low-level policies, leveraging point cloud observations to improve the policy's robustness. We conduct comprehensive experiments on the FurnitureBench in both simulation and real-world settings, demonstrating improved performance in skill precision and long-horizon success rate. In the challenging insertion and screwing tasks, QDP improves the skill-wise success rate by over 50% compared to baselines without structured queries.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18686
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Query-Centric Diffusion Policy for Generalizable Robotic Assembly
Xu, Ziyi
Lin, Haohong
Liu, Shiqi
Zhao, Ding
Robotics
Machine Learning
The robotic assembly task poses a key challenge in building generalist robots due to the intrinsic complexity of part interactions and the sensitivity to noise perturbations in contact-rich settings. The assembly agent is typically designed in a hierarchical manner: high-level multi-part reasoning and low-level precise control. However, implementing such a hierarchical policy is challenging in practice due to the mismatch between high-level skill queries and low-level execution. To address this, we propose the Query-centric Diffusion Policy (QDP), a hierarchical framework that bridges high-level planning and low-level control by utilizing queries comprising objects, contact points, and skill information. QDP introduces a query-centric mechanism that identifies task-relevant components and uses them to guide low-level policies, leveraging point cloud observations to improve the policy's robustness. We conduct comprehensive experiments on the FurnitureBench in both simulation and real-world settings, demonstrating improved performance in skill precision and long-horizon success rate. In the challenging insertion and screwing tasks, QDP improves the skill-wise success rate by over 50% compared to baselines without structured queries.
title Query-Centric Diffusion Policy for Generalizable Robotic Assembly
topic Robotics
Machine Learning
url https://arxiv.org/abs/2509.18686