No episode media available here
This is a representative still, not playable footage. Episode video for this dataset lives with its original source.
ManiSkill2
Generalizable manipulation skills
UC San Diego Hao Su Lab
RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.
20 task families with 2,000+ object variations and over 4M demonstration frames, including soft-body and precise-insertion tasks. Renders at 2,000+ FPS for large-scale imitation and RL training.
Reported structure
Values below come from the dataset's own documentation. Missing fields are shown as not provided rather than estimated.
3 cameras
13 DoF
100 Hz
Not provided
Data modalities
Episode explorer
No episode media has been added for this dataset, so there is nothing to play. The explorer appears as soon as real clips exist — either uploaded here or extracted from the source.
Contribute episodesLinked models, robots & papers
Resolving related models, datasets and papers…
Related datasets
Mobile ALOHA
Source: Stanford IRIS & REAL Labs
- 1.1K
- 5.8
- 4
ALOHA Static Bimanual Demos
Source: Stanford IRIS & REAL Labs
- 1.0K
- 5.6
- 4
MimicGen
Source: NVIDIA GEAR Lab
- 50K
- 277.8
- 3
ALOHA Unleashed
Source: Google DeepMind Robotics
- 26K
- 290
- 4