LATIDIA · Robótica

HGWM: Hierarchical Graph-Guided World Model for Zero-Shot Object Navigation via Graph Matching

arXiv:2610.32554v1 Announce Type: new Abstract: La navegación por objetos de disparo cero requiere que un agente incorporado elija dónde buscar mientras conserva la evidencia de observaciones anteriores. HGWM acopla una habitación-anc generada por LLM

La noticia

arXiv:2610.32554v1 Announce Type: new Abstract: Zero-shot object navigation requires an embodied agent to choose where to search while retaining evidence from previous observations. HGWM couples an LLM-generated room-anchor prior with persistent spatial-semantic memory. A coarse stage assigns visual-semantic scores to candidate headings on a 0-10 scale; a fine stage measures symbolic compatibility between observed objects, room context, and the goal prior. Phase-dependent fusion combines these scores with an LLM direction recommendation before local action selection. On HM3D v0.1, the reported HGWM configuration achieves 62.6% success rate (SR) and 31.5% success weighted by path length (SPL), compared with 58.1% and 31.2% for WMNav. On MP3D, the corresponding values are 46.8% and