RoboScope Kit: Unified Interfaces for Fast and Scalable Embodied-AI Evaluation

Benchmark-specific interfaces and lengthy evaluation runs complicate robot-policy comparisons.

Simulation benchmarks are the standard way to compare robot policies, but each benchmark brings its own evaluator, observation layout, and action convention, and evaluation is slow: 500 RoboTwin Easy episodes with one simulator and one model on one GPU take 359.7 minutes.

ArXiv CS.RO2026-11-04