# VOMMI: Collecting and Leveraging Portable Demonstrations for Mobile Manipulation

arXiv: https://arxiv.org/abs/2610.08220 · HTML: https://mlsanity.com/paper/2610.08220/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 22 of 22)

- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [HomeRobot: Open-Vocabulary Mobile Manipulation](https://mlsanity.com/paper/2306.11565/) (2023)
- [UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers](https://mlsanity.com/paper/2407.10353/) (2024)
- [QUAR-VLA: Vision-Language-Action Model for Quadruped Robots](https://mlsanity.com/paper/2312.14457/) (2023)
- [FastUMI: A Scalable and Hardware-Independent Universal Manipulation Interface with Dataset](https://mlsanity.com/paper/2409.19499/) (2024)
- [VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation](https://mlsanity.com/paper/2105.09371/) (2021)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration](https://mlsanity.com/paper/2602.10106/) (2026)
- [HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations](https://mlsanity.com/paper/2603.03243/) (2026)
- [Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers](https://mlsanity.com/paper/2507.15833/) (2025)
- [MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation](https://mlsanity.com/paper/2606.09215/) (2026)
- [What Enables In-Context Behavior Prompting for Manipulation?](https://mlsanity.com/paper/2606.30457/) (2026)
- [ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation](https://mlsanity.com/paper/2608.06375/) (2026)
- [OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation](https://mlsanity.com/paper/2606.22174/) (2026)
- [DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation](https://mlsanity.com/paper/2608.20114/) (2026)
- [Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation](https://mlsanity.com/paper/2605.20894/) (2026)

## Abstract (arXiv)

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.