Team-RAMENcc-by-4.0
RAMEN G1 IKEA Assembly — RAMEN-Ori pick_table_leg
Training dataset for the RAMEN-Ori policy on the pick_table_leg assembly skill, containing 786 episodes of a Unitree G1 humanoid with Dex1-1 gripper assembling a children's table. Includes multi-camera RGB and infrared imagery, proprioceptive state, and action commands with pre-rendered image caches and YOLO-OBB object detections.
Downloads26
Episodes786
Hours2.2
Why This Matters for Physical AI
This dataset provides high-quality multi-view sensor data and curated skill demonstrations for training humanoid robot policies on complex assembly tasks, advancing learning-based approaches for dexterous manipulation in real-world scenarios.
Technical Profile
- Modalities
- rgbinfraredproprioception
- Robot Embodiments
- Unitree G1humanoid
- Action Space
- joint_positions
- Environment
- lab
- Task Types
- manipulationassemblypick_and_place
- Episodes
- 786
- Total Hours
- 2.2
- Data Format
- LeRobot
- Annotation Types
- bounding_boxescuration_labels
- License
- cc-by-4.0
Access
Need custom rgb data?
Claru builds purpose-built datasets for lab applications with dense human annotations and quality assurance.
Request a Sample Pack