ALOHA Static Bimanual Demos
Millimetre-precision bimanual assembly
Stanford IRIS & REAL Labs
RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.
The original ALOHA demonstrations: battery slot insertion, cup opening, candy wrapper peeling, ping-pong ball slotting and cable threading — 50 demos per task, four camera views, 50 Hz joint teleoperation. Trains ACT to 80-90% success.
Reported structure
Values below come from the dataset's own documentation. Missing fields are shown as not provided rather than estimated.
4 cameras
14 DoF
50 Hz
88% success
Data modalities
Dataset Explorer
Real episodes from this dataset, with every camera stream playing in sync.
Episode #00000
instruction: “Place the coffee capsule inside the capsule container, then place the cup onto the center of the cup tray, then push the 'Hot Water' and 'Travel Mug' buttons.”
Linked models, robots & papers
Resolving related models, datasets and papers…
Related datasets
Real-world IndexedMobile ALOHA
Source: Stanford IRIS & REAL Labs
- 1.1K
- 5.8
- 4
Simulation IndexedManiSkill2
Source: UC San Diego Hao Su Lab
- 30K
- 166.7
- 3
Synthetic IndexedMimicGen
Source: NVIDIA GEAR Lab
- 50K
- 277.8
- 3
Real-world IndexedALOHA Unleashed
Source: Google DeepMind Robotics
- 26K
- 290
- 4