LATIDIA · Robótica

HuGo: LLM como diseñadores de códigos de políticas de cuerpo entero para la loco-manipulación humanoide

arXiv:2609.30594v1 Tipo de anuncio: nuevo Resumen: Para que los humanoides sean útiles en entornos cotidianos, deben realizar una amplia gama de tareas que combinan la locomoción y la manipulación. Los enfoques existentes comúnmente adquieren una

La noticia

arXiv:2609.30594v1 Announce Type: new Abstract: For humanoids to be useful in everyday environments, they must perform a wide range of tasks that couple locomotion and manipulation. Existing approaches commonly acquire a loco-manipulation policy through reward engineering or demonstrations followed by task-specific training, making it costly to scale to new tasks. In this work, we propose a hierarchical approach to humanoid loco-manipulation that eliminates these per-task requirements. HuGo, Humanoid policy code Generation, uses a Large Language Model (LLM) to generate executable, closed-loop high-level policy code from a task description on top of a frozen low-level whole-body policy. Given the task, observation, and command specifications, the LLM constructs the task logic in