Saved in:
Bibliographic Details
Main Authors: Liu, Jiahao, Wenbo, Cui, Xia, Zhongpu, Li, Haoran, Zhao, Dongbin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.23024
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915966812684288
author Liu, Jiahao
Wenbo, Cui
Xia, Zhongpu
Li, Haoran
Zhao, Dongbin
author_facet Liu, Jiahao
Wenbo, Cui
Xia, Zhongpu
Li, Haoran
Zhao, Dongbin
contents Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipulator and robust perception under dynamically changing viewpoints. However, existing approaches face two key challenges: strong coupling between base and arm actions complicates control optimization, and perceptual attention is often poorly allocated as viewpoints shift during mobile manipulation. We propose InCoM, an intent-driven perception and structured coordination framework for mobile manipulation. InCoM infers latent motion intent to dynamically reweight multi-scale perceptual features, enabling stage-adaptive allocation of perceptual attention. To support robust cross-modal perception, InCoM further incorporates a geometric-semantic structured alignment mechanism that enhances multimodal correspondence. On the control side, we design a decoupled coordinated flow matching action decoder that explicitly models coordinated base-arm action generation, alleviating optimization difficulties caused by control coupling. Experimental results demonstrate that InCoM significantly outperforms state-of-the-art methods, achieving success rate gains of 28.2%, 26.1%, and 23.6% across three ManiSkill-HAB scenarios without privileged information. Furthermore, its effectiveness is consistently validated in real-world mobile manipulation tasks, where InCoM maintains a superior success rate over existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23024
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
Liu, Jiahao
Wenbo, Cui
Xia, Zhongpu
Li, Haoran
Zhao, Dongbin
Robotics
Mobile manipulation is a fundamental capability for general-purpose robotic agents, requiring both coordinated control of the mobile base and manipulator and robust perception under dynamically changing viewpoints. However, existing approaches face two key challenges: strong coupling between base and arm actions complicates control optimization, and perceptual attention is often poorly allocated as viewpoints shift during mobile manipulation. We propose InCoM, an intent-driven perception and structured coordination framework for mobile manipulation. InCoM infers latent motion intent to dynamically reweight multi-scale perceptual features, enabling stage-adaptive allocation of perceptual attention. To support robust cross-modal perception, InCoM further incorporates a geometric-semantic structured alignment mechanism that enhances multimodal correspondence. On the control side, we design a decoupled coordinated flow matching action decoder that explicitly models coordinated base-arm action generation, alleviating optimization difficulties caused by control coupling. Experimental results demonstrate that InCoM significantly outperforms state-of-the-art methods, achieving success rate gains of 28.2%, 26.1%, and 23.6% across three ManiSkill-HAB scenarios without privileged information. Furthermore, its effectiveness is consistently validated in real-world mobile manipulation tasks, where InCoM maintains a superior success rate over existing baselines.
title InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
topic Robotics
url https://arxiv.org/abs/2602.23024