Dexhands

DEXTEROUS MANIPULATION

The world of dexterous hands.

Compare hardware. Discover applications. Share what works. An open reference and community for dexterous manipulation.

AnyTeleop

UC San Diego / NVIDIA

Vision-based hand–arm teleoperation research with links to retargeting and visualization code.

What you can explore

Explore mapping human hand motion onto different robot configurations.

Before you use it

Supported configurations and runtime requirements must be checked in the original implementation.

Original contributors

Yuzhe Qin and collaborators

License / access: Check linked repositories

Paper, visualizer & code

FROM REFERENCE TO FIRST EXPERIMENT

Start with the right setup.

INPUTCamera-derived human finger and wrist poses
OUTPUTHand retargeting and arm motion targets
Environment
Teleoperation
Embodiment
Arm–hand combinations in the paper

What you need

Start from the official project’s visualizer and retargeting links.

First useful check

Trace camera input → hand mapping → controller for your intended embodiment.

Where it stops

Published multi-robot demonstrations are not a ready driver for any hand. Teleoperation uses human task decisions.

Documentation reviewed; not independently reproduced · reviewed 2026-09-24. Record the exact source revision when reproducing it.

Editorial reference · checked 2026-09-22

Start a discussion

Published posts are public. First contributions are reviewed. Only share material you have permission to disclose.

Report a post