Super Poulain Draft 2: Robotic Arm Action Data for Machine Learning

A dataset created using the LeRobot framework, likely containing sequences of robotic arm actions. The data includes 6-dimensional action features for joints such as shoulder, elbow, wrist, and gripper positions. It was authored by 'imstevenpmwork' and last updated on June 16, 2026.

Use Cases

• Training imitation learning or reinforcement learning agents based on recorded robotic arm actions.
• Benchmarking robotic control algorithms using the 6-dimensional action space described.
• Analyzing kinematic patterns for joints like shoulder_pan, shoulder_lift, and wrist_roll.
• Developing sim-to-real transfer methods for robotic manipulation tasks.

Strengths

• Action data is structured with a defined 6-dimensional feature shape.
• Specific joint positions (e.g., shoulder_pan.pos, gripper.pos) are named, providing clear semantics.
• Metadata indicates a codebase version (v3.0) and a frame rate (30 fps) for temporal context.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent for non-action fields; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown, which may limit suitability assessment.

Provenance

Source

huggingface

Collection Method

Created using the LeRobot framework.

Freshness

Last updated 2026-06-16 14:01:41; freshness should be verified.