LATIDIA · Robótica

LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models

arXiv: 2609.24350v1Tipo de anuncio: nuevo Resumen: Los modelos de cimientos robóticos logran un rendimiento impresionante en los puntos de referencia de manipulación estándar, sin embargo, estas evaluaciones generalmente asumen objetivos visuales limpios, oportunos y consistentes

La noticia

arXiv:2609.24350v1 Announce Type: new Abstract: Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observations throughout execution. We introduce LIBERO-VPro, a benchmark for systematically evaluating the closed-loop visual robustness of robotic foundation models by perturbing the visual evidence available during execution. LIBERO-VPro covers four complementary dimensions, including Visual Evidence Degradation, Camera Staleness, Visual Source Consistency, and Task-Relevant Scene Variation, spanning 12 challenge categories, 96 experimental settings, and 3,296 task-condition cases. We evaluate three vision-language-action models and three world-action models over approximately 196,000 simulated episodes, complemented by 200 real-world rollouts on a Franka Research 3. Our results reveal that strong