No episode media available here
This is a representative still, not playable footage. Episode video for this dataset lives with its original source.
Language-Table
Real-time language-guided pushing
Google DeepMind Robotics
RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.
442,226 real and simulated episodes of tabletop block rearrangement driven by free-form language, with 10x more language-annotated trajectories than prior sets. Designed for interactive, correctable instruction following at 10 Hz.
Reported structure
Values below come from the dataset's own documentation. Missing fields are shown as not provided rather than estimated.
2 cameras
2 DoF
10 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
Open X-Embodiment
Source: Open X-Embodiment Collaboration
- 1.0M
- 5.6K
- 3
BridgeData V2
Source: UC Berkeley RAIL
- 60K
- 333.9
- 4
LeRobot Community SO-100 Datasets
Source: Hugging Face LeRobot
- 23K
- 481
- 2
DROID
Source: Stanford IRIS & REAL Labs
- 76K
- 350
- 3