LATIDIA · Robótica

LLM4Robot-Bench: ¿Hasta dónde puede llegar GPT-6 Astra en la manipulación robótica? Un benchmark jerárquico que compara simulaciones reales.

arXiv:2610.34527v2 Anuncio Tipo: reemplazar Resumen: Presentamos LLM4Robot-Bench, un benchmark jerárquico y emparejado Sim-Real para evaluar las capacidades de interacción física en la manipulación con mucho contacto. Sus 16 hogares

La noticia

arXiv:2610.34527v2 Announce Type: replace Abstract: We introduce LLM4Robot-Bench, a hierarchical, matched Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the