rtrtwrwapache-2.0
granular-material-pour -- pea, single target
165 teleoperated episodes of pouring pea onto a scale with a YAM arm, recorded at 50 Hz with 3 cameras and a 1 kg load cell. Dataset includes joint positions, gripper state, and scale measurements for a fixed 500g target weight.
Downloads42
Episodes165
Hours2.64
Why This Matters for Physical AI
This dataset provides high-quality demonstrations of a contact-rich manipulation task (pouring granular materials) with precise load cell feedback, enabling research into fine-grained force control and goal-conditioned robotic manipulation.
Technical Profile
- Modalities
- rgbproprioceptionforce_torque
- Robot Embodiments
- YAM arm
- Action Space
- joint_positions
- Environment
- lab
- Task Types
- pouringmanipulation
- Episodes
- 165
- Total Hours
- 2.64
- Data Format
- LeRobot
- Annotation Types
- language_instructions
- 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