DEXTEROUS MANIPULATION

The world of dexterous hands.

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

TacSL

NVIDIA Research / University of Washington

Visuotactile sensor simulation and policy-learning research for contact-intensive manipulation.

What you can explore

Explore tactile image/contact modeling and the reported peg placement and insertion experiments.

Before you use it

The linked Isaac Gym toolkit is explicitly deprecated and unsupported. Follow current Isaac Lab documentation for newer integrations; these are not general hand benchmarks.

Original contributors

Iretiayo Akinola, Jie Xu, Jan Carius, Dieter Fox and Yashraj Narang

License / access: Check source branch, simulator and sensor-asset licenses

Original project & resources

Legacy code & setup notes

Keep exploring

Isaac Lab

GPU-oriented robot-learning framework with articulated-robot manipulation environments.

TACTO

An archived research simulator for images from vision-based tactile sensors, including DIGIT and OmniTact examples.

Tactile Gym 2.0

PyBullet learning environments using simulated tactile observations for contact tasks.

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