LATIDIA · Robótica

Creación de robots genéticos a través de la generación, verificación y revisión

arXiv:2610.17881v1 Tipo de anuncio: nuevo Resumen: ¿Puede un agente de IA convertir la intención del usuario de alto nivel en un robot funcional y enseñarle cómo comportarse? Estudiamos esta cuestión desde dos aspectos complementarios: la encarnación y el comportamiento

La noticia

arXiv:2610.17881v1 Announce Type: new Abstract: Can an AI agent turn high-level user intent into a functioning robot and teach it how to behave? We study this question from two complementary aspects: embodiment and behavior creation. For embodiment creation, we investigate how well current multimodal models capture mechanical requirements, and introduce computational metrics for evaluating generated designs before fabrication. For behavior creation, we present Roboforge, an agentic framework that turns task specifications into executable policies through motion generation, policy learning, and execution-grounded revision. Given a robot embodiment and task, the agent generates a reference motion, configures the learning objective, and trains a policy. Crucially, motion remains in the loop: rollout feedback