XvKuoMing2026apache-2.0

so101_chess_wide

Chess moves and captures by an SO-101 arm with domain randomization across board sizes, materials, piece sets, camera placements, and lighting conditions. Scripted-expert demonstrations in MuJoCo with 7,521 episodes covering pick-and-place and capture tasks.

Downloads237
Episodes7732
Hours22.5998

Why This Matters for Physical AI

Demonstrates how domain randomization across visual, environmental, and task parameters enables robust learning for manipulation tasks, with systematic evaluation on held-out distributions to measure generalization.

Technical Profile

Modalities
rgbproprioception
Robot Embodiments
SO-101
Action Space
6-DoF: shoulder_pan, shoulder_lift, elbow_flex, wrist_flex, wrist_roll, gripper
Environment
simulation
Task Types
manipulationpick_and_place
Episodes
7732
Total Hours
22.5998
Data Format
LeRobot
Annotation Types
language_instructionsaction_labels
License
apache-2.0
Part of the LeRobot family

Access

Need custom rgb data?

Claru builds purpose-built datasets for simulation applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets