arXiv cs.AI· Haoxiang Tang, Dong Zhou, Shen Tan, Minxuan Jiang, Xitong Li·· 12 小时前AI 评分24
SP-Guide：用空间先验增强空中视觉语言导航
SP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial Priors
AI 导读
SP-Guide 是一个基于 Transformer 的目标预测框架，通过空间先验跨模态编码器、指令增强解码器和目标收敛过滤器提升空中视觉语言导航性能。在 CityNav 基准上，其成功率超过代表性基线，且在未见环境中的提升最大。结果表明，物理落地的空间先验为鲁棒的 AVLN 提供了有效的归纳偏置。
正文 · 原文
Abstract:Aerial vision-language navigation (AVLN) requires a UAV to reach a language-described target from partial egocentric observations while reasoning over large outdoor scenes. Existing approaches typically fuse view-centered RGB observations and globally anchored history maps as generic visual embeddings, leaving cross-modal spatial alignment to be learned from sparse navigation supervision. We present SP-Guide, a transformer- based goal-prediction framework that addresses this weakness of alignment through a Spatial Prior Cross-Modal Encoder, an Instruction Enhanced Decoder, and a Goal Convergence Filter for terminal target refinement. Experiments implemented on the CityNav benchmark show that SP-Guide improves success rate over the representative baselines, with the largest gains on unseen environments. These results indicate that physically grounded spatial priors provide an effective inductive bias for robust AVLN.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32697 [cs.CV] |
| (or arXiv:2610.32697v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32697 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoxiang Tang [view email]
[v1]
Fri, 23 Oct 2026 14:21:58 UTC (2,683 KB)
来源：arXiv cs.AI · arxiv.org