ObjDex
cypypccpy
Object-centric dexterous manipulation policies learned from human interaction motion.
What you can explore
Explore ARCTIC-based training examples for interacting with articulated objects using a simulated hand.
Before you use it
The release uses legacy Isaac Gym and Python 3.8. Source ARCTIC data and object models retain separate access and use restrictions.
Original contributors
Yuanpei Chen, Chen Wang, Yaodong Yang and C. Karen Liu
License / access: MIT stated in README · ARCTIC and external assets have separate terms
Keep exploring
ARCTIC
Two human hands interacting with articulated objects, with motion and contact information for reconstruction research.
DexMachina
Physics-based retargeting of human demonstrations into coordinated robot-hand manipulation of articulated objects.
DexTrack
Dexterous manipulation through reinforcement learning that tracks human-derived hand–object motion.
Editorial reference · checked 2026-09-22