Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.06317 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911693664157696 |
|---|---|
| author | Zhan, Dijia Li, Jinyi Zheng, Chenxi Huang, Shaoyu Li, Yong Tang, Jie Xu, Xuemiao |
| author_facet | Zhan, Dijia Li, Jinyi Zheng, Chenxi Huang, Shaoyu Li, Yong Tang, Jie Xu, Xuemiao |
| contents | 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. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To solve this, we introduce NavOne, a unified framework that directly predicts dense path probabilities over multi-modal maps in a single end-to-end forward pass. NavOne features a Top-Down Map Fuser for joint multi-modal map representation, and extends Attention Residuals for spatial-aware depth mixing. Extensive experiments on R2R-TopDown show that NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06317 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps Zhan, Dijia Li, Jinyi Zheng, Chenxi Huang, Shaoyu Li, Yong Tang, Jie Xu, Xuemiao Computer Vision and Pattern Recognition Artificial Intelligence 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. We propose Top-Down VLN (TD-VLN), reformulating navigation as a one-step global path planning problem on pre-built top-down maps, supported by our newly constructed R2R-TopDown dataset. To solve this, we introduce NavOne, a unified framework that directly predicts dense path probabilities over multi-modal maps in a single end-to-end forward pass. NavOne features a Top-Down Map Fuser for joint multi-modal map representation, and extends Attention Residuals for spatial-aware depth mixing. Extensive experiments on R2R-TopDown show that NavOne achieves state-of-the-art performance among map-based VLN methods, with a planning-stage speedup of 8x over existing map-based baselines and 80x over egocentric methods, enabling highly efficient global navigation. |
| title | NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.06317 |