LeWAMapache-2.0
LeWAM Evaluation Tape Stack
Real-robot evaluation rollouts on a Rebot B601 7-DoF arm executing a tape stacking task using the LeWAM self-supervised policy, with 30 episodes scored by human operators.
Downloads32
Episodes30
Hours0.34
Why This Matters for Physical AI
This dataset provides real-world evaluation data of an end-to-end learned robotic policy on physical hardware, enabling research into self-supervised learning and policy evaluation on manipulation tasks.
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- Rebot B601
- Action Space
- joint_positions
- Environment
- lab
- Task Types
- manipulationpick_and_place
- Episodes
- 30
- Total Hours
- 0.34
- 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