Mobile ALOHA
Mobile bimanual household tasks
Stanford IRIS & REAL Labs
RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.
50 demonstrations per task of whole-body mobile manipulation: cooking shrimp, wiping wine, rinsing pans, calling an elevator, pushing chairs. Co-training with static ALOHA data lifts success up to 90% on some tasks from only tens of demos.
Reported structure
Values below come from the dataset's own documentation. Missing fields are shown as not provided rather than estimated.
4 cameras
16 DoF
50 Hz
80% success
Data modalities
Dataset Explorer
Real episodes from this dataset, with every camera stream playing in sync.
Episode #00000
instruction: “Pick up the wet cloth on the faucet and use it to clean the spilled wine on the table and underneath the glass.”
Linked models, robots & papers
Resolving related models, datasets and papers…
Related datasets
Real-world IndexedRT-1 Robot Action Dataset
Source: Google DeepMind Robotics
- 130K
- 17.4K
- 1
Simulation IndexedManiSkill2
Source: UC San Diego Hao Su Lab
- 30K
- 166.7
- 3
Real-world IndexedAgiBot World Beta
Source: AgiBot
- 1.0M
- 5.6K
- 8
Simulation IndexedCALVIN
Source: Freiburg Robot Learning Lab
- 24K
- 133.3
- 2