So101 Fold Towel 100Ep is a dataset of robot demonstrations for a towel-folding task, created using the LeRobot framework. The dataset contains 75 episodes and 144,579 video frames recorded at 30 frames per second. It was authored by Sengankou and last updated on April 12, III.
Use Cases
- Training imitation learning policies based on recorded robot actions and visual observations.
- Developing computer vision models for object manipulation based on video sequences of a towel-folding task.
- Benchmarking robot learning algorithms on a single-task, demonstration-based dataset.
- Analyzing temporal action sequences for robotic skill acquisition.
Strengths
- Contains 144,579 video frames, providing substantial visual data for model training.
- Includes 75 complete episodes for a single, defined task (towel folding).
- Recorded at a standard 30 frames per second, suitable for temporal analysis.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- The dataset description is incomplete, referencing a full description on an external page.
Provenance
- Source
- huggingface
- Collection Method
- Created using the LeRobot framework, likely involving recording demonstrations from a 'so_follower' type robot.
- Time Range
- null
- Freshness
- Last updated 2026-04 12 20:06:27; freshness should be verified.
- Geography
- null