# REGRAD

From the catalogue. Listed by one researcher from one source page.

- id: `regrad`
- kind: grasping
- robot or device: simulated cluttered scenes with relationship and grasp labels (class: simulation)
- how collected: simulation generated
- size as stated: 111.8k scenes
- hours: not stated | hours only claimed: none | episodes: not stated
- year: 2021
- organisation: Xi'an Jiaotong University
- licence: not stated (class: not stated)
- access: open (class: open)
- link (dataset): https://github.com/poisonwine/REGRAD
- note: 6D poses, boxes, masks and manipulation relationships.

Confirm the licence at the link before relying on it.
