anonymous-rabench-2026cc-by-4.0

RA-Bench Runtime Authority Review Artifact

A benchmark and evaluation artifact for runtime authority assessment of learned robot policies in MuJoCo structured-state simulation, submitted to NeurIPS 2026.

Downloads0

Why This Matters for Physical AI

This dataset provides a benchmark for evaluating runtime verification and safety assurance mechanisms for learned robot policies, contributing to trustworthiness and reproducibility standards in robot learning research.

Technical Profile

Modalities
proprioception
Environment
simulation
Task Types
pre-graspmanipulation
Annotation Types
action_labels
License
cc-by-4.0
Part of the RA-Bench family

Access

Need custom proprioception data?

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

Request a Sample Pack

Related Datasets