Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

Read original
arXiv·Tengbo Yu·Sep 10, 2026, 4:08 PM

SEED-UMI: Sharing Exoskeletons Across Human and Robot for Direct Dexterous Demonstration

Original title:SEED-UMI: Sharing the Exoskeleton between human and robot for onE-to-one Dexterous demonstration

Papers80

SEED-UMI tackles the cross-embodiment gap in dexterous manipulation by having both the human operator and the robotic hand wear the exact same exoskeleton hardware. This shared physical interface aligns encoder measurements and ensures wrist-mounted cameras observe the identical mechanical structure during both demonstrations and autonomous rollouts, removing the need for open-loop retargeting or visual inpainting. Across five contact-rich tasks, the method achieves 3.0x faster data collection than exoskeleton teleoperation and a 70.0% average rollout success rate.

Why it's worth reading

It cleverly eliminates cross-embodiment retargeting and visual domain shift by physically standardizing the human and robot interface through a shared exoskeleton.

Tags

RoboticsDexterous ManipulationImitation LearningExoskeletonCross-EmbodimentData Collection

Score breakdown

  • Novelty84
  • Impact79
  • Practicality81
  • Credibility80
  • Timeliness76