# UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies

arXiv: https://arxiv.org/abs/2510.02614 · HTML: https://mlsanity.com/paper/2510.02614/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 37 of its 60 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 37)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [Visual Imitation Made Easy](https://mlsanity.com/paper/2008.04899/) (2020)
- [Grasping in the Wild:Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations](https://mlsanity.com/paper/1912.04344/) (2019)
- [On Bringing Robots Home](https://mlsanity.com/paper/2311.16098/) (2023)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Neural Lander: Stable Drone Landing Control using Learned Dynamics](https://mlsanity.com/paper/1811.08027/) (2018)
- [Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds](https://mlsanity.com/paper/2205.06908/) (2022)
- [Humanoid Policy ~ Human Policy](https://mlsanity.com/paper/2503.13441/) (2025)
- [EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning](https://mlsanity.com/paper/2407.01479/) (2024)
- [UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers](https://mlsanity.com/paper/2407.10353/) (2024)
- [My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control](https://mlsanity.com/paper/2010.01856/) (2020)
- [acados: a modular open-source framework for fast embedded optimal control](https://mlsanity.com/paper/1910.13753/) (2019)
- [DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation](https://mlsanity.com/paper/2505.21864/) (2025)
- [Visual Whole-Body Control for Legged Loco-Manipulation](https://mlsanity.com/paper/2403.16967/) (2024)
- [Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation](https://mlsanity.com/paper/2402.19432/) (2024)
- [Generalizable Humanoid Manipulation with 3D Diffusion Policies](https://mlsanity.com/paper/2410.10803/) (2024)
- [Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories](https://mlsanity.com/paper/2505.21851/) (2025)
- [Body Transformer: Leveraging Robot Embodiment for Policy Learning](https://mlsanity.com/paper/2408.06316/) (2024)
- [BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities](https://mlsanity.com/paper/2503.05652/) (2025)
- [SPIN: Simultaneous Perception, Interaction and Navigation](https://mlsanity.com/paper/2405.07991/) (2024)
- [GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization](https://mlsanity.com/paper/2407.15002/) (2024)
- [Continuously Improving Mobile Manipulation with Autonomous Real-World RL](https://mlsanity.com/paper/2409.20568/) (2024)

## Built on by (most cited first, 11 of 11)

- [Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations](https://mlsanity.com/paper/2602.06643/) (2026)
- [π, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation](https://mlsanity.com/paper/2603.25038/) (2026)
- [OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies](https://mlsanity.com/paper/2603.10052/) (2026)
- [LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition](https://mlsanity.com/paper/2606.11628/) (2026)
- [YOR: Your Own Mobile Manipulator for Generalizable Robotics](https://mlsanity.com/paper/2602.11150/) (2026)
- [Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation](https://mlsanity.com/paper/2605.20085/) (2026)
- [Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotors](https://mlsanity.com/paper/2602.21583/) (2026)
- [UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation](https://mlsanity.com/paper/2603.27012/) (2026)
- [AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations](https://mlsanity.com/paper/2609.36915/) (2026)
- [From Local Whole-Body VLA Behaviors to Scene-Scale Aerial Manipulation](https://mlsanity.com/paper/2609.39670/) (2026)
- [Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback](https://mlsanity.com/paper/2610.12549/) (2026)

## Abstract (arXiv)

We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstrations collected with a handheld gripper (UMI) to train generalizable visuomotor policies. A central challenge in transferring these policies to constrained robotic embodiments-such as aerial manipulators-is the mismatch in control and robot dynamics, which often leads to out-of-distribution behaviors and poor execution. To address this, we propose Embodiment-Aware Diffusion Policy (EADP), which couples a high-level UMI policy with a low-level embodiment-specific controller at inference time. By integrating gradient feedback from the controller's tracking cost into the diffusion sampling process, our method steers trajectory generation towards dynamically feasible modes tailored to the deployment embodiment. This enables plug-and-play, embodiment-aware trajectory adaptation at test time. We validate our approach on multiple long-horizon and high-precision aerial manipulation tasks, showing improved success rates, efficiency, and robustness under disturbances compared to unguided diffusion baselines. Finally, we demonstrate deployment in previously unseen environments, using UMI demonstrations collected in the wild, highlighting a practical pathway for scaling generalizable manipulation skills across diverse-and even highly constrained-embodiments. All code, data, checkpoints, and result videos can be found at umi-on-air.github.io.