LATIDIA · Robótica

Implementación de modelos de cimentación para navegación incorporada

arXiv: 2609.25666v1Tipo de anuncio: nuevo Resumen: Presentamos y abordamos dos problemas asociados con la implementación de modelos de base (FM) en agentes incorporados que realizan la navegación: 1) Sesgo de capacitación en FM que conduce a una mala perso

La noticia

arXiv:2609.25666v1 Announce Type: new Abstract: We present and tackle two problems associated with deploying Foundation Models (FMs) on Embodied Agents performing navigation: 1) Training bias in FMs leading to poor personalization in unseen environments, and 2) Limited FM context length hindering success, especially on long horizon tasks. Our solution for the former involves priming the FM with human-habit data mined from the scene and our solution for the latter involves active memory management via a novel `memory head' augmentation. We first present a taxonomy of existing literature on FM-based Embodied Navigation, and highlight these limitations. We then present our approaches, Transit-Aware Planning (TAP) and MemCtrl to address the limitations. With