microsoft2026cc-by-nc-4.0
MuseVLA Dataset
Multi-modal robot manipulation dataset with synchronized RGB, depth, acoustic, thermal, and radar streams covering ~1400 episodes across 11 manipulation instructions.
Downloads61
Episodes1397
Why This Matters for Physical AI
MuseVLA demonstrates the value of multi-modal sensing (acoustic, thermal, radar) beyond traditional vision for robotic manipulation, advancing perception capabilities for real-world physical tasks.
Technical Profile
- Modalities
- rgbdepthacousticthermalradarproprioception
- Action Space
- end_effector_delta
- Environment
- lab
- Task Types
- manipulationtowel_manipulationclothes_manipulationbox_manipulationitem_manipulationdrink_manipulation
- Episodes
- 1397
- Annotation Types
- language_instructionssegmentationaction_labels
- License
- cc-by-nc-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