ParsaSharifiapache-2.0

LIBERO Spatial, re-rendered at 224x224 (Patch Policy layout)

500 demonstrations of LIBERO Spatial (10 tasks x 50 demos) re-rendered at 224x224 resolution and converted to the Patch Policy layout, with replayed MuJoCo states and fixed fixture placements.

Downloads5
Episodes500

Why This Matters for Physical AI

This dataset provides high-quality visual and proprioceptive demonstrations for learning manipulation policies in simulated environments, enabling research on imitation learning and visuomotor control.

Technical Profile

Modalities
rgbproprioception
Robot Embodiments
Franka Panda
Action Space
joint_positions
Environment
simulation
Task Types
manipulationpick_and_place
Episodes
500
Data Format
PyTorch
Annotation Types
action_labels
License
apache-2.0
Part of the LIBERO 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