LATIDIA · Robótica

Vea lo que necesito, sueñe lo que quiero: un modelo de base de navegación en un espacio de representación autoconstruido

arXiv:2610.31762v1 Announce Type: new Abstract: ¿Sobre qué representación visual debe actuar una política de navegación? Las políticas de navegación basadas en modelos de base de visión dejan en gran medida el diseño de representación a los codificadores pre

La noticia

arXiv:2610.31762v1 Announce Type: new Abstract: What visual representation should a navigation policy act on? Navigation policies built on vision foundation models largely leave representation design to the encoders' pretraining objectives. We present RepresentNav, a navigation foundation model built on a self-constructed representation space: a visual representation constructed by the policy's own objectives from vision foundation models. RepresentNav builds this space with Representation Residuals, a compact three-layer transformer that attends over features spanning the full depth of multiple complementary vision foundation models, so that the policy learns to see what it needs for navigation. In the same space it dreams what it wants: before every action a latent chain-of-thought predicts the