Shanghai AI Lab open-sources EgoExplorer, a wearable pipeline for whole-body mobile manipulation data
量子位 · wechat · 2026-11-18
Shanghai AI Lab's InternRobotics team released EgoExplorer, a wearable, environment-free data collection pipeline for whole-body mobile manipulation. It combines 5 VIVE trackers, haptic gloves, and a head-mounted GoPro to sync egocentric video, metric whole-body motion, finger joints, and touch at 30Hz. A Calibrate-Complete-Constrain pipeline reconstructs full-body motion from just 5 anchors at 18.0mm error, 71.9% lower than the strongest baseline. The team collected 100 hours across labs, factories, and homes, trained a joint multimodal world model, and retargeted human demos to a Unitree G1 in simulation. Code and data (LeRobot v3.0) are open-sourced.
More from Embodied
- Peking University Open-Sources PanDWM, a 360° 4D Driving World Model Beating DiST-4D — PekingUniversity · 2026-11-18
- Humanoids serve ice cream and spar in Shenzhen while APEC leaders visit — TansuYegen · 2026-11-18
- Otto by Rockwell explains using Gazebo digital twins for AMR deployments — ___Mufasaa · 2026-11-18
- Tokkey debuts thumb-sized AI hardware to run local models on your Mac — TejasKumar_ · 2026-11-18
- 'Nothing more physical AI than moving tons of rock': live demo at Web Summit shows real-world difficulty — MarvinTBaumann · 2026-11-18
- StellarEdge Auriga report: verifiable execution harness hits 57.74% on 42 RoboDojo tasks — jiqizhixin · 2026-11-18