LATIDIA · Robótica

P-BFM: Modelos básicos de comportamiento perceptivo para el control humanoide a través del aprendizaje de refuerzo no supervisado

arXiv: 2610.15833v1Tipo de anuncio: nuevo Resumen: Los modelos de fundamentos conductuales (BFM) proporcionan a los humanoides repertorios reutilizables de comportamientos de todo el cuerpo; en el control humanoide del mundo real, la misma intención conductual puede requerir

La noticia

arXiv:2610.15833v1 Announce Type: new Abstract: Behavioral foundation models (BFMs) provide humanoids with reusable repertoires of whole-body behaviors; in real-world humanoid control, the same behavioral intent may require fundamentally different motions under different terrain constraints. Covering such variation with terrain-matched demonstrations requires enumerating a combinatorial space of behaviors and terrain geometries. We introduce P-BFM, a perceptive behavioral foundation model that factorizes humanoid control into terrain-invariant intent and terrain-conditioned realization. A forward-backward representation maps motion references, target states, and reward functions into a shared intent space without terrain information, while a perceptive policy learns how to realize each intent under the surrounding terrain geometry. We further identify a complementary limitation of purely