PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps

ArXi:2606.01788v1 Announce Type: new Embodied visual navigation, where an agent perceives a complex environment and acts to reach a goal from raw sensory input, underpins a wide range of applications such as household service robotics, assistive robotics, and large-scale autonomous exploration. However, recent attempts to unify vision-and-language navigation (VLN) and object goal navigation (ObjNa) remain at the level of architectural fusion, mixed-task