Abstract: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.
From: Jiahao Liu [view email]
[v1]
Thu, 26 Feb 2026 14:03:58 UTC (4,212 KB)
[v2]
Mon, 27 Apr 2026 12:00:13 UTC (5,071 KB)
[v3]
Tue, 28 Apr 2026 06:27:57 UTC (5,071 KB)
[v4]
Wed, 29 Apr 2026 09:32:01 UTC (5,071 KB)
[v5]
Mon, 13 Jul 2026 07:47:54 UTC (9,295 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。