DEXTEROUS MANIPULATION

The world of dexterous hands.

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

HOP

hgaurav2k

Hand–object interaction pretraining followed by task-specific dexterous policy learning.

What you can explore

Study how human interaction observations inform downstream robot manipulation tasks.

Before you use it

Uses the documented Isaac Gym stack and external motion assets. Human pretraining does not eliminate robot-specific fine-tuning.

Original contributors

Himanshu Gaurav Singh and HOP collaborators

License / access: Check original code, model and data terms before reuse

Original code & documentation

Keep exploring

GRAB

Whole-body human motion and object interactions, with articulated hand poses and derived contact.

DexTrack

Dexterous manipulation through reinforcement learning that tracks human-derived hand–object motion.

DexWild

Portable human demonstrations and robot data combined to train dexterous manipulation policies.

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