SatNav, a scalable, long-horizon UAV VLN benchmark built from high-resolution satellite imagery, is introduced and satellite-to-UAV transfer experiments show that satellite-trained navigation models can operate on real-flight UAV observations, showing the practical relevance of SatNav.
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/
A dual-layer semantic-spatial belief mapping framework that transforms transient VLM observations into persistent spatial guidance is proposed, and object-conditioned visual reasoning with conservative evidence qualification is introduced to improve observation reliability before spatial accumulation.
Jian-Qiang Xiao, Xiang Deng, Yue-Xuan Sun et al.· 1 citation
This work introduces RiverVLN, to its knowledge the first benchmark designed for long-horizon USV VLN under continuous riverine motion, and PGT-NAV, a phase-grounded temporal navigation framework for USVs.
This work presents an instruction-grounded semantic enhancement module that injects object-level semantics and relative spatial cues into the current observation state, and develops a relevance-aware dynamic temporal aggregation strategy that reweights the full history buffer while converting a few high-relevance frame...
This work proposes ARIES-Mission2, a zero-shot Vision-Language-Action (VLA) framework that decouples visual-semantic perception from physical route optimization in low-altitude Unmanned Aerial Vehicle (UAV) mission generation and indicates that the TSP module maintains lower growth in computation time as the number of...
Jun-Hao Wei, Yan-Xiao Li, Hao-Chen Li et al.· 1 citation
Vision-Language-Action (VLA) models have achieved impressive results in robotic manipulation and ground-mobile navigation, yet language-conditioned control of unmanned aerial vehicles (UAVs) in smart warehouses remains largely unexplored, hindered by the lack of benchmarks that jointly provide continuous low-level flig...
Thinh D. Le, Son Nguyen, Duong Q. Nguyen et al.· 0 citations
Foresight-Guided Action Refinement (FGAR), which asymmetrically exploits proximal foresight for local action enhancement and route-critical foresight for feature-wise correction and route-level guidance, is introduced, validating the effectiveness of dual-horizon foresight and FGAR learning.