AirNav: A Large-Scale Real-World UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions

2026-01-07

arXiv.org

AI Summary

Existing research on vision-and-language navigation (VLN) for unmanned aerial vehicles (UAVs) predominantly relies on simulated environments, often suffering from unnatural instructions and limited scale. This work presents AirNav, the first large-scale, natural, and diverse VLN benchmark constructed from real-world urban aerial imagery, and introduces AirVLN-R1, a novel model that integrates supervised fine-tuning with reinforcement fine-tuning to enhance both navigation performance and generalization capability. Experimental results demonstrate the effectiveness of the proposed approach in real-world settings. The dataset, along with the code, has been publicly released, establishing a new foundation for advancing VLN research for UAVs in authentic environments.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Existing Unmanned Aerial Vehicle (UAV) Vision-Language Navigation (VLN) datasets face issues such as dependence on virtual environments, lack of naturalness in instructions, and limited scale. To address these challenges, we propose AirNav, a large-scale UAV VLN benchmark constructed from real urban aerial data, rather than synthetic environments, with natural and diverse instructions. Additionally, we introduce the AirVLN-R1, which combines Supervised Fine-Tuning and Reinforcement Fine-Tuning to enhance performance and generalization. The feasibility of the model is preliminarily evaluated through real-world tests. Our dataset and code are publicly available.

Problem

• UAV
• Vision-Language Navigation
• real-world dataset
• natural instructions
• large-scale

Innovation

• UAV Vision-Language Navigation
• real-world aerial dataset
• natural language instructions
• reinforcement fine-tuning
• large-scale benchmark