LATIDIA · Robótica

Kit RoboScope: Interfaces unificadas para la evaluación rápida y escalable de la IA incorporada.

arXiv:2611.03850v1 Anuncio Tipo: nuevo Resumen: Los puntos de referencia de simulación son la forma estándar de comparar las políticas de los robots, pero cada punto de referencia trae su propio evaluador, diseño de observación y convención de acción, y evaluación

La noticia

arXiv:2611.03850v1 Announce Type: new Abstract: 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. Profiling the official StarVLA evaluator shows that simulation occupies CPU cores while the GPU averages 14.3% utilization. RoboScope Kit wraps each model once in a Python class called a Policy, and each benchmark once in an adapter around the benchmark's own evaluator, so the benchmark's rules and scoring stay unchanged. Scheduling runs simulator workers and Policy replicas as separate pools, sizes both from