LeWAMapache-2.0
LeWAM Evaluation PushT (Rebot B601)
Real-robot evaluation rollouts of a self-supervised policy performing non-prehensile pushing tasks on a Rebot B601 7-DoF arm, with human-scored success labels and multi-camera observations.
Downloads30
Episodes30
Hours0.527
Why This Matters for Physical AI
This dataset provides real-world policy evaluation data demonstrating how self-supervised learning transfers to physical robot control, with human-validated success metrics for benchmarking manipulation policies.
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- Rebot B601
- Action Space
- joint_positions
- Environment
- lab
- Task Types
- manipulationnon-prehensile_pushing
- Episodes
- 30
- Total Hours
- 0.527
- Data Format
- LeRobot
- Annotation Types
- reward_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