HRDexDB
Seoul National University / HRDexDB team
Paired human and robot grasp recordings with visual, kinematic and three-dimensional annotations.
What you can explore
Explore comparable grasps across human and robotic embodiments, including tactile-enabled subsets.
Before you use it
Use the published availability fields and explicitly verified pairings. The train table is a catalog, not a benchmark split; mesh and tracking revisions must stay aligned.
Original contributors
Jongbin Lim, Taeyun Ha and HRDexDB collaborators
License / access: Dataset: CC BY-NC 4.0 · check toolkit and model permissions
Keep exploring
RealDex
Real-world dexterous robot grasp recordings for learning human-like manipulation.
DexYCB
Human hand–object RGB-D data for grasp perception and handover research. Explore downloads, annotation fields, official splits and a first Python inspection.
DextER
Language-conditioned dexterous grasp generation evaluated on instruction and grasp-taxonomy benchmarks.
Editorial reference · checked 2026-09-22