cs.CVNov 8, 2026

Reaching Is Not Finding: Map-Anchored Visual Prompting for the Last Mile of Aerial Vision-Language Navigation

Authors: Ningbo Li, Kebin Liu, Jingcan Chen, Weichen Zhang, Rong Ding, Yunhao Liu, Mo Li

Organizations: The Hong Kong University of Science and Technology · Tsinghua University · The University of Hong Kong

Abstract

Aerial vision-language navigation (VLN) asks a drone to find an object described in natural language. The description usually locates the object relative to named landmarks, such as streets and buildings. We observe that current navigators often bring the drone close to the target and then stop at the wrong place: they reach the target without finding it. This gap is shared by navigators of very different designs, from imitation learners to a fine-tuned 7B vision-language model. A simple test reveals the cause. When we replace the target object in the instruction with another one next to the same landmarks, no navigator goes to it, and most stop where they did before. Navigators learn to reach the landmarks, not to identify the described object. We therefore propose MAP-VP, a plug-and-play module for the last step. After any navigator stops, MAP-VP draws the landmarks named in the instruction onto the drone's current view, using the landmark outlines that the benchmark provides on a map. A fine-tuned 4B vision-language model then locates the target relative to these landmarks. The training data are generated automatically from the benchmark annotations. Neither drawing the landmarks nor fine-tuning helps much alone, but together they are highly effective. Without retraining any navigator, MAP-VP significantly improves all six navigators we test on CityNav. It roughly doubles the success rate of the two strongest trained navigators, raising HETT from 25.9% to 54.6% and FlightGPT from 24.2% to 48.9%, whereas CityNav's official detector-based last step adds less than two points to HETT.

Figures & tables

Explore similar work

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

    Oct 30, 2026Jiawei Ge, Wenkang Gong, Jiuxin Cao +8Vision-Language NavigationAerial VLN

  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