cs.CVOct 30, 2026

Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation

Authors: Jiawei Ge, Wenkang Gong, Jiuxin Cao, Bo Liu, Lei Cui, Haoran Wang, Xuelin Zhu, Biwei Cao, 

Organizations: Southeast University · Institute of AI for Industries, Chinese Academy of Sciences · The Hong Kong Polytechnic University · Hohai University · 

Abstract

Aerial Vision-and-Language Navigation (VLN) requires UAVs to locate language-specified goals in large-scale urban environments, where objects often appear small and visually ambiguous from high-altitude viewpoints. Existing methods largely follow a reactive paradigm common in indoor VLN, repeatedly updating navigation states from local observations while underutilizing the geospatial structure that remains stable during navigation. As a result, visually similar distractors can cause a reactive goal search to repeatedly reinforce locally plausible goal hypotheses based on passively accumulated evidence, leading to unreliable localization. To address this, we propose GeoReasoner, a robust framework that shifts the paradigm of Aerial VLN from reactive trial-and-error to geospatial-guided active reasoning. Specifically, GeoReasoner first performs pre-search geospatial reasoning to derive region-level priors and constrain the goal hypothesis space. Building on these, it further conducts hypothesis-driven exploration to actively acquire discriminative evidence and refine competing goal hypotheses. Finally, consistency-aware goal verification adversarially assesses complementary evidence sources before stopping, hence reducing premature or erroneous goal confirmations. Experiments on the real-world CityNav benchmark demonstrate that GeoReasoner sets a new SOTA among zero-shot Aerial VLN methods while competing favorably with supervised approaches.

Figures & tables

Explore similar work

CardsList
  1. ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation

    Mar 9, 2026Haoyu Tong, Xiangyu Dong, Xiaoguang Ma +3Aerial VLNVisual Navigation

  2. LookasideVLN: Direction-Aware Aerial Vision-and-Language Navigation

    Apr 19, 2026Yuwei Ning, Ganlong Zhao, Yipeng Qin +4Vision-Language NavigationAerial VLN

  3. SP-Guide: Enhancing Aerial Vision-Language Navigation with Spatial Priors

    Oct 23, 2026Haoxiang Tang, Dong Zhou, Shen Tan +2Vision-Language NavigationAerial VLN