Get a Grip

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

• id: get-a-grip
• kind: grasping
• robot or device: multi-finger hand with RGB, point clouds and NeRFs (class: dexterous hand)
• how collected: simulation synthesis
• size as stated: 3.5M grasps on 4.3K objects
• hours: not stated | hours only claimed: none | episodes: not stated
• year: 2024
• organisation: Stanford
• licence: not stated (class: not stated)
• access: open (class: open)
• link (dataset): https://sites.google.com/view/get-a-grip-dataset
• note: Includes positive and negative grasps.

Confirm the licence at the link before relying on it.