arXiv：cs.AI· Yutian Zhang, Xingrui Xiong, Siyuan Ma, Yang Li, Jiawen Wen, Jiaqi Zhai, Liwen Yang, Ce Hao, Haozhen Chi, Yangkun Zhu, Yifan Zhu, Xiaowen Chu, Dong Wei, Qiaojun Yu, Dibo Hou·· 6 小时前AI 评分37
VOMMI：为移动操作收集并利用便携式演示数据
VOMMI: Collecting and Leveraging Portable Demonstrations for Mobile Manipulation
AI 导读
研究者提出 VOMMI，一个将便携 RGB 演示数据接入 VLA 后训练的演示收集与学习框架，无需遥操作或专用传感设备。其 R2-VO 用稀疏几何锚点精修离线轨迹并生成局部运动 token 用于在线策略条件化，使身体与手部流轨迹误差平均降低 24.6%。
正文
Authors:Yutian Zhang, Xingrui Xiong, Siyuan Ma, Yang Li, Jiawen Wen, Jiaqi Zhai, Liwen Yang, Ce Hao, Haozhen Chi, Yangkun Zhu, Yifan Zhu, Xiaowen Chu, Dong Wei, Qiaojun Yu, Dibo Hou
Abstract:Portable mobile-manipulation demonstrations can help alleviate data scarcity for embodied intelligence, but obtaining reliable, low-cost, and robot-free motion supervision from RGB observations remains challenging. Existing approaches often rely on teleoperation or specialized devices equipped with additional sensing hardware, while directly using estimated visual odometry (VO) trajectories can introduce inconsistencies due to accumulated drift and imperfect motion supervision. We present the Visual-Odometry-Conditioned Mobile Manipulation Interface (VOMMI), a portable demonstration collection and learning framework that connects portable RGB demonstrations to vision-language-action (VLA) post-training through offline trajectory reconstruction and online visual-motion conditioning. VOMMI synchronizes body and hand views to capture navigation context and local object interactions without requiring human-robot kinematic correspondence calibration. R2-VO refines offline demonstration trajectories using sparse geometric anchors and produces causal local-motion tokens over multiple prediction horizons for online policy conditioning. An action-group residual adapter incorporates these tokens only into the base branch. Experiments use a 500-trajectory portable for each task, with 75 trajectories held out for RGB-VO evaluation, and 200 robot demonstrations as references. Our policy, post-trained only on portable demonstrations, achieves 18.2% lower base-velocity error than a policy trained with robot-collected demonstrations, while maintaining comparable end-effector translation accuracy. Offline reconstruction reduces absolute trajectory errors for the body and hand streams by 24.6% on average relative to the best evaluated baseline for each stream. The complete system improves the mean success rate by 8.3 percentage points over OpenPI 0.5 across three real-robot tasks.
| Comments: | 9 pages, 6 figures |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08220 [cs.RO] |
| (or arXiv:2610.08220v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08220 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yutian Zhang [view email]
[v1]
Tue, 6 Oct 2026 12:10:48 UTC (4,724 KB)
来源：arXiv：cs.AI · arxiv.org