SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery
cs.CV, cs.RO
Submitted: 2026-09-25
Updated: 2026-09-25
Comments: Accepted at NeurIPS 2026, Track on Evaluations and Datasets. 32 pages, 16 figures. Project page: https://eku127.github.io/SatNav/
Project page: https://eku127.github.io/SatNav
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
Abstract
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/
Sources
- AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
- Gemini: A Family of Highly Capable Multimodal Models
- HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks
- LongFly: Long-Horizon UAV Vision-and-Language Navigation with Spatiotemporal Context Integration
- VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
- SAM 2: Segment Anything in Images and Videos
- StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
- UAV-VisLoc: A Large-scale Dataset for UAV Visual Localization
- OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models