AI RESEARCH
NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps
arXiv CS.CV
•
ArXi:2605.06317v1 Announce Type: new Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency. While recent approaches attempt to leverage pre-built environment maps, they often rely on incrementally updating memory graphs or scoring discrete path proposals, which restricts continuous spatial reasoning and creates discrete bottlenecks.