Representative still for RT-1 Robot Action Dataset

No episode media available here

This is a representative still, not playable footage. Episode video for this dataset lives with its original source.

RT-1 Robot Action Dataset

Language-conditioned kitchen manipulation

Indexed from an external sourceReal-worldUpdated 2023-03-04Open Source

Published by

Google DeepMind Robotics

RobotData indexes this dataset's metadata. Attribution and licensing stay with the original publisher.

The 130,498 teleoperated episodes behind RT-1: 700+ distinct kitchen instructions (pick, place, open drawer, knock over, move near) collected over 17 months with 13 Everyday Robots mobile manipulators. Released in RLDS format as part of Open X-Embodiment.

Reported structure

Values below come from the dataset's own documentation. Missing fields are shown as not provided rather than estimated.

Observation

1 cameras

State

7 DoF

Action

3 Hz

Result

97% success

Data modalities

RGB VideoDepthJoint PositionsRobot StateActionsForce/TorqueAudioLanguage Instructions

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 episodes

Linked models, robots & papers

Resolving related models, datasets and papers…

Related datasets