提出一步全局规划方法，让导航更高效准确
NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps
- 将导航转为单步全局路径规划，直接输出密集路径概率
- 在新数据集上达最优性能，规划速度比基线快80倍
- 适合需要快速高精度导航的机器人应用
现有视觉语言导航方法多采用渐进式、逐步推理模式，易累积误差且效率低。尽管近期方法尝试利用预构建环境地图，但常依赖逐步更新记忆图谱或评分离散路径候选，限制了连续空间推理并引入离散瓶颈。本文提出自上而下视觉语言导航（TD-VLN），将导航重构为基于预建俯视地图的一步全局路径规划问题，并构建了新数据集R2R-TopDown。为此提出NavOne统一框架，通过端到端单次前向传播直接预测多模态地图上的密集路径概率。NavOne包含俯视地图融合模块实现多模态联合表征，并扩展注意力残差机制实现空间感知深度融合。在R2R-TopDown上的大量实验表明，NavOne在基于地图的VLN方法中达到最先进水平，规划阶段速度相较现有地图基线提升8倍，相比原生姿态方法快80倍，实现高效全局导航。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。