DecisionFacts2026other

DecisionFacts Physical AI Dataset — SO-101 Robotic Arm Teleoperation

A curated collection of real-world teleoperation data captured on the SO-101 robotic arm, featuring synchronized multi-modal capture across dual cameras, proprioceptive state, and control signals for training robot-learning models including imitation-learning policies, Vision-Language-Action models, and world models.

Downloads57
Episodes30+
Likes4

Why This Matters for Physical AI

This dataset provides high-quality, human-demonstrated teleoperation trajectories with synchronized multi-view vision and proprioceptive feedback, enabling training of embodied AI models including vision-language-action policies and world models for robotic manipulation.

Technical Profile

Modalities
rgbproprioception
Robot Embodiments
SO-101
Action Space
joint_positions
Environment
lab
Task Types
manipulationcup_nesting
Episodes
30+
Data Format
LeRobot
Annotation Types
language_instructionstask_descriptions
License
other
Part of the DecisionFacts Physical AI Dataset family

Access

Need custom rgb data?

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

Request a Sample Pack

Related Datasets