DexH2R
4DVLab
A benchmark for dynamic human-to-robot handovers with dexterous hands.
What you can explore
Study handover motion, object transfer and the released training and evaluation tasks.
Before you use it
Simulation performance does not establish safe operation around people. Real handover requires separate sensing, control and safety validation.
Original contributors
DexH2R authors and repository contributors
License / access: Code and data: CC BY-NC 4.0
Keep exploring
DexYCB
Human hand–object RGB-D data for grasp perception and handover research. Explore downloads, annotation fields, official splits and a first Python inspection.
RealDex
Real-world dexterous robot grasp recordings for learning human-like manipulation.
DexTrack
Dexterous manipulation through reinforcement learning that tracks human-derived hand–object motion.
Editorial reference · checked 2026-09-22