SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery

Hugging Face Daily Papers Papers
vision-language-navigation uav benchmark satellite-imagery long-horizon lvlm embodied-ai

Summary

介绍了 SatNav，一个基于高分辨率卫星图像构建的可扩展长时程 UAV 视觉-语言导航基准，包含 18 个城市 59 个场景的 118K 任务，并提出模块化框架 SwiftVLN 及卫星到真实无人机的迁移实验。

Urban uncrewed aerial vehicle (UAV) vision-language navigation (VLN) requires agents to follow instructions across extended urban spaces, inherently demanding long-term memory and geospatial grounding. However, scaling existing benchmarks remains difficult because of their reliance on costly reconstructed 3D assets, limiting geographic diversity and episode scale. To address this, we introduce SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery. SatNav targets city-level navigation missions and uses satellite crops as approximations of UAV nadir views for visual observations. Through an automated cue-to-episode pipeline, SatNav constructs 118K episodes from 59 scenes across 18 cities, with an average trajectory length of 379 m. To stress-test long-horizon memory and geospatial reasoning, SatNav defines three task families: Boundary, Landmark, and Route, targeting loop progress tracking, landmark-based spatial grounding, and route following with counting cues. Benchmarking classical VLN agents and recent agents based on large vision-language models (LVLMs) on SatNav shows that city-scale navigation remains challenging. We further introduce SwiftVLN, a modular framework with switchable memory components, and conduct systematic memory-design ablations. Finally, satellite-to-UAV transfer experiments show that satellite-trained navigation models can operate on real-flight UAV observations, showing the practical relevance of SatNav. Our project page: https://eku127.github.io/SatNav/
Original Article
View Cached Full Text

Cached at: 10/09/26, 10:21 AM

Paper page - SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery

Source: https://huggingface.co/papers/2609.31507

Abstract

Urbanuncrewedaerialvehicle(UAV)vision-languagenavigation(VLN)requiresagentstofollowinstructionsacrossextendedurbanspaces,inherentlydemandinglong-termmemoryandgeospatialgrounding.However,scalingexistingbenchmarksremainsdifficultbecauseoftheirrelianceoncostlyreconstructed3Dassets,limitinggeographicdiversityandepisodescale.Toaddressthis,weintroduceSatNav,ascalable,long-horizonUAVVLNbenchmarkbuiltfromhigh-resolutionsatelliteimagery.SatNavtargetscity-levelnavigationmissionsandusessatellitecropsasapproximationsofUAVnadirviewsforvisualobservations.Throughanautomatedcue-to-episodepipeline,SatNavconstructs118Kepisodesfrom59scenesacross18cities,withanaveragetrajectorylengthof379m.Tostress-testlong-horizonmemoryandgeospatialreasoning,SatNavdefinesthreetaskfamilies:Boundary,Landmark,andRoute,targetingloopprogresstracking,landmark-basedspatialgrounding,androutefollowingwithcountingcues.BenchmarkingclassicalVLNagentsandrecentagentsbasedonlargevision-languagemodels(LVLMs)onSatNavshowsthatcity-scalenavigationremainschallenging.WefurtherintroduceSwiftVLN,amodularframeworkwithswitchablememorycomponents,andconductsystematicmemory-designablations.Finally,satellite-to-UAVtransferexperimentsshowthatsatellite-trainednavigationmodelscanoperateonreal-flightUAVobservations,showingthepracticalrelevanceofSatNav.Ourprojectpage:https://eku127.github.io/SatNav/

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2609\.31507

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.31507 in a model README.md to link it from this page.

Datasets citing this paper2

#### Eku127/SatNav-Episodes-v0.1 Viewer• Updated11 days ago • 118k • 218 #### Eku127/SatNav-Scenes-v0.1

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.31507 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SuperNav: An Agentic Navigation System for Any Task in Any Scene

Hugging Face Daily Papers

SuperNav is a navigation framework that equips a pretrained multimodal LLM with an agent harness and navigation tools—without navigation-specific fine-tuning—allowing the model to interpret requests and specify visual destination points while delegating motion execution. It outperforms four baselines on instance-level, multi-object, and demand-driven tasks and is demonstrated on a real quadruped robot.