yoyowz2026apache-2.0
SO-101 2-Camera Pick-and-Place Validation Dataset
A LeRobot-style validation episode dataset with two camera views (top and arm cameras) for pick-and-place tasks, used by OpenVINO notebook demos for policy inference and offline replay visualization.
Downloads52
Episodes50
Hours0.1647
Why This Matters for Physical AI
This dataset enables validation and demonstration of physical AI policy inference and offline replay using multi-view robotic manipulation data.
Technical Profile
- Modalities
- rgb
- Robot Embodiments
- SO-101
- Action Space
- 6-DoF: shoulder_pan.pos, shoulder_lift.pos, elbow_flex.pos, wrist_flex.pos, wrist_roll.pos, gripper.pos
- Environment
- lab
- Task Types
- pick_and_place
- Episodes
- 50
- Total Hours
- 0.1647
- Data Format
- LeRobot
- Annotation Types
- action_labels
- License
- apache-2.0
Access
Need custom rgb data?
Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.
Request a Sample Pack