docs/content/howto/logging-and-ingestion/lerobot.md
The Rerun Viewer has built-in support for opening LeRobot datasets, the directory-based format used for robot-learning datasets. Both the v2.1 and v3.0 dataset layouts are supported.
A LeRobot dataset is a directory (metadata, parquet, and video files), so point Rerun at the dataset directory:
# View a LeRobot dataset in the Rerun Viewer
rerun path/to/lerobot_dataset
You can also drag and drop the dataset directory into the Rerun Viewer, or load it using the SDK:
snippet: howto/load_lerobot
Each episode in the dataset is loaded as its own recording. Within an episode, the dataset's features are mapped onto Rerun entities: scalar observations and actions, camera images and videos, and the task descriptions are each logged under their own entity, indexed on a shared timeline.
To go the other way — querying recordings and exporting them as a LeRobot dataset — see Export recordings to LeRobot datasets.