sreetz-nv
SO-101 simulated teleoperation: perception domain randomization
75 manually teleoperated simulation episodes of a pick-and-place task with vial manipulation, recorded at 30 Hz with perception domain randomization including wrist-camera blur, appearance changes, and camera randomization.
Downloads32
Episodes75
Hours0.21
Why This Matters for Physical AI
This dataset demonstrates the importance of perception domain randomization for sim-to-real transfer in robotic manipulation, using teleoperation from a physical leader to train robust visual policies in simulation.
Technical Profile
- Modalities
- rgbproprioception
- Robot Embodiments
- SO-101
- Action Space
- joint_positions
- Environment
- simulation
- Task Types
- pick_and_placemanipulation
- Episodes
- 75
- Total Hours
- 0.21
- Data Format
- LeRobot
Access
Need custom rgb data?
Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.
Request a Sample Pack