arXiv cs.AI· Yosub Shin, Yuan Liu, Igor Molybog·· 12 小时前AI 评分38
一个头戴相机就够了：单目移动相机标注与观测的无电子 UMI 手套
A Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving Camera
AI 导读
研究者提出用一只 122 美元的头戴自视角相机替代 UMI 手套方案中的腕部相机、位姿追踪器和多路数据流，通过读取 22 美元无电子手套上的印刷标记与工作区纸片标记，直接输出 6-DoF 夹爪位姿与夹爪开度。
正文 · 原文
Abstract:Handheld demonstration devices decouple data collection from the robot, but conventional designs burden the hand with a wrist camera, cables and a pose tracker (SLAM, an IMU, a VR controller, or a fixed external camera that the collector's body occludes), and burden the pipeline with as many data streams to timestamp, synchronise and cross-calibrate. We show that a single egocentric camera (USD 122) worn on the collector's head replaces the wrist camera, the pose tracker and their separate streams with one. It reads printed fiducials on an electronics-free glove (USD 22) against paper tiles taped around the workspace, giving the 6-DoF gripper pose and the jaw width from the same frames the policy will see; at deployment the same camera rides a low-cost (USD 120) arm beside the robot that mimics the collector's head from the robot's joint state. Against the robot's encoders the labels are accurate to 6.5 mm and 1.6 degrees median with 93-100% frame coverage, and a policy trained on them instead of encoders pays 3% in validation loss. Adding 194 glove demonstrations to 48 teleoperated episodes lifts rollout success from 10/25 to 17/25, level with 172 teleoperated episodes alone (18/25), and the full co-trained head-camera policy succeeds in 20/25 against 15/25 for the wrist-camera recipe, whose policies drop the object when the goal leaves their view, and 12/25 for a fixed camera.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27622 [cs.RO] |
| (or arXiv:2610.27622v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27622 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yosub Shin [view email]
[v1]
Tue, 20 Oct 2026 04:40:10 UTC (1,534 KB)
来源：arXiv cs.AI · arxiv.org