Universal Manipulation Interface

From Humanoid Robots Wiki
Revision as of 00:17, 1 May 2024 by Ben (talk | contribs)
Jump to: navigation, search

Universal Manipulation Interface is a data collection and policy learning framework that allows direct skill transfer from in-the-wild human demonstrations to deployable robot policies.

UMI
NameUMI
Full NameUniversal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
ArxivLink
TwitterTwitter
Publication DateFebruary 2024
AuthorsCheng Chi, Zhenjia Xu, Chuer Pan, Eric Cousineau, Benjamin Burchfiel, Siyuan Feng, Russ Tedrake, Shuran Song

The UMI paper was novel for several reasons:

  1. It completely avoids robot teleoperation and the associated latency. This lets the robot do things like reliably tossing balls.
  2. It provides a low-cost, scalable way to collect lots of data in the wild