---
title: "UMI-Live for In-The-Wild Bimanual Robotics Data Collection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.39385v1"
permalink: "https://feed.astralor.com/items/itm_3253cf27c3ecf1116d05f65b"
published: "2026-10-29T05:18:16.000Z"
score: 54
channel: "tech"
tags: ["推理效率","UMI-Live","In-The-Wild Bimanual Robotics","Data Collection Universal","Manipulation Interface","UMI","Using","Universal Manipulation Interface"]
---

# UMI-Live for In-The-Wild Bimanual Robotics Data Collection

## At a glance

Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstrations as training data still requires a consistent h…

## Key points

- Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots.
- Using these demonstrations as training data still requires a consistent hardware setup, calibration, and data processing.
- We present UMI-Live, a full-stack open-source bimanual UMI system for in-the-wild data collection.

## Full text

Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstrations as training data still requires a consistent hardware setup, calibration, and data processing. We present UMI-Live, a full-stack open-source bimanual UMI system for in-the-wild data collection. We design our custom UMI-Live hardware to integrate camera and LiDAR--inertial sensing, onboard compute, and power, without external tracking equipment or calibration within the collection environment. We implement a simple user interface for recording data while an asynchronous pipeline performs parallel SLAM reconstruction and publishes training-ready datasets. We also release software that supports dual-YAM teleoperation and VLA policy training and inference. We validate UMI-Live data quality by fine-tuning $π_{0.5}$ and MolmoAct2, achieving success rates of 10/10 and 8/10, respectively on a bimanual pick-and-place task. Furthermore, we release 40 hours of UMI-Live data across three tasks, and complete hardware designs, software, and reproduction guides at our $\href{https://umi-live.github.io/}{\text{project website}}$.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_3253cf27c3ecf1116d05f65b