LATIDIA · Robótica

Haga que {\pi}0.5 aprenda a llamar a Astra para una manipulación fiable del robot

arXiv: 2610.14117v1Tipo de anuncio: nuevo Resumen: GPT-6 Astra proporciona un razonamiento incorporado sólido, pero las consultas externas frecuentes aumentan el tiempo de inferencia y los costos de los tokens. Equipamos una póliza congelada de $\pi_{0.5}$ con un peso ligero

La noticia

arXiv:2610.14117v1 Announce Type: new Abstract: GPT-6 Astra provides robust embodied reasoning, but frequent external queries increase inference time and token costs. We equip a frozen $\pi_{0.5}$ policy with a lightweight CALL head that learns to predict when assistance is necessary. CALL reuses features from the standard policy forward pass and operates locally without consulting external models. Astra is activated solely for critical recovery events and returns control to $\pi_{0.5}$ upon stabilization. Evaluated across 40 LIBERO tasks (200 episodes), our system achieves a 97.5% success rate, outperforming the 95.5% baseline of pure $\pi_{0.5}$. In the Object, Goal, and Spatial suites, Astra executes only 5.49% of environment steps, consuming approximately 5,027 tokens