LATIDIA · Robótica

¿Puede un VLM de Frontier servir como una política de robot para la manipulación dependiente de la memoria?

arXiv: 2610.17350v1Tipo de anuncio: nuevo Resumen: Utilizamos un modelo de lenguaje de visión de frontera congelado, GPT-6-Astra, directamente como la política del robot en RoboMME, un punto de referencia de 16 tareas de manipulación dependientes de la memoria que abarcan tempora

La noticia

arXiv:2610.17350v1 Announce Type: new Abstract: We use a frozen frontier vision-language model, GPT-6-Astra, directly as the robot policy on RoboMME, a benchmark of 16 memory-dependent manipulation tasks spanning temporal, spatial, object, and procedural memory. The model keeps the whole episode in context and outputs every end-effector waypoint and gripper command, with no RoboMME-specific training. On the 800 test episodes it succeeds in 92.1%, above the previously reported human score of 90.5%, which was obtained with an oracle skill interface, and far ahead of the best leaderboard entry (60.8%) and of a hierarchical system that pairs the same model with a RoboMME-trained policy (79.1%). It matches or exceeds the human score