Repository
Research
Diffusion Policy
A visuomotor policy approach using diffusion to generate robot actions.
Robot policies
Software / Open source
DexUMI · real-stanford
DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
Overview
DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
Inspect installation instructions, supported versions, examples and interfaces in the source. This directory does not claim the software has been installed or tested on your robot.
Project information
- Maintainer
- real-stanford
- Primary language
- C
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-04-18
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- 🚀 Installation
- 🦾 Real-world Deployment
- 🛠️ Build Exoskeleton
- 📷 Data Recording and Processing
- 🚴♂️ Policy Training
- 🏂 Policy Evaluation
Browse this resource’s categories
Explore related collections
Browse Software →More in Software
Repository
Research
Repository
Open source
universal manipulation interface · real-stanford
Interface for collecting in-the-wild demonstrations and teaching robot manipulation.
Robot learning frameworks