LeWAMapache-2.0
LeWAM Eval Tape Stack
Real-robot evaluation rollouts of a LeWAM self-supervised policy on a Rebot B601 7-DoF arm performing tape stacking tasks, with 30 policy rollouts scored by human operators.
Downloads32
Episodes30
Hours0.27
Why This Matters for Physical AI
This dataset provides real-world policy evaluation data demonstrating the performance of self-supervised learning approaches on physical manipulation tasks, offering insights into the gap between training and deployment on real robots.
Technical Profile
- Modalities
- rgbproprioceptionforce_torque
- Robot Embodiments
- Rebot B601
- Action Space
- joint_positions
- Environment
- lab
- Task Types
- manipulationtape_stack
- Episodes
- 30
- Total Hours
- 0.27
- 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