DEXTEROUS MANIPULATION

The world of dexterous hands.

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

DexArt

SJTU / Tsinghua / UC San Diego research team

A simulated benchmark for learning to manipulate articulated objects and testing generalization to unseen objects.

What you can explore

Explore tasks involving a faucet, laptop, bucket or toilet, and how evaluation separates training and unseen objects.

Before you use it

Results are from a simulation benchmark. Check software versions and asset terms; transfer to physical hardware requires separate evidence.

Original contributors

Chen Bao, Helin Xu, Yuzhe Qin and Xiaolong Wang

License / access: Code: Apache 2.0 · check downloaded asset terms

Research overview

Code & benchmark

Keep exploring

MuJoCo Playground

GPU-accelerated robot-learning environments, including tasks for dexterous manipulation.

ARCTIC

Two human hands interacting with articulated objects, with motion and contact information for reconstruction research.

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