LATIDIA · Robótica

Manipulación de robots con GPT-6-Astra: conocimiento corporal, reutilización de experiencias, habilidades emergentes y transferencia Sim2Real

arXiv: 2609.31770v1Announce Type: new Resumen: Los agentes multimodales de propósito general pueden escribir programas de control de robots, pero la exploración repetida y la selección de acciones mediadas por modelos pueden hacer que la ejecución sea lenta. Estudiamos cómo exter

La noticia

arXiv:2609.31770v1 Announce Type: new Abstract: General-purpose multimodal agents can write robot-control programs, but repeated exploration and model-mediated action selection can make execution slow. We study how external body knowledge, successful experience, and executable skills improve an XLeRobot controlled by GPT-6-Astra in a simulated and a physical elevator-button task. In 30 fixed-start simulation trials, complete robot geometry and camera information reduce mean completion time by 57.4% relative to a baseline with only the common control interface and no prior experience; images with synchronized action and state records reduce it by 68.6% without additional body assets. In nine paired comparisons (18 trials) at starts displaced by 10-100 cm, experience recorded at the