Desk Hero4: Robot Teleoperation Data for Desk Manipulation Tasks

LeRobot was used to create this dataset for robot learning. The dataset structure includes separate files for data and video, with a specified frame rate of 30 fps. It was authored by lorenz-k and last updated on June 20, 2026.

Use Cases

• Train imitation learning models based on recorded robot teleoperation data.
• Benchmark robot policy performance on desk manipulation tasks.
• Develop computer vision models for robotic state estimation based on the video data.

Strengths

• Data is structured into separate parquet and video files for efficient access.
• The frame rate for video data is specified as 30 fps.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

huggingface

Collection Method

Created using LeRobot.

Freshness

Last updated 2026-06-20 14:01:15; freshness should be verified.