Awesome Aerial Visual-Language Navigation

The new spin-off of Visual Language Navigation.

Your suggestions to the list are highly encouraged (use the issues).

---

Table of Contents

• Core Labs
• Datasets and Benchmarks
• Aerial VLN
• Simulators
• Links

---

Core Labs

Research groups with multiple or foundational contributions to Aerial VLN.

Lab / PI	Institution	Country	Papers
Bin Zhao, Dong Wang, Xuelong Li	Shanghai AI Laboratory	China	STMR, OpenFLY
Boyu Zhou	Southern University of Science and Technology (SUSTech) + Sun Yat-Sen University	China	OnFly
Fei Gao (FAST Lab)	Zhejiang University	China	NavDreamer
Chen Gao, Yong Li (FIBLab)	Tsinghua University	China	EmbodiedCity, AirCopBench
Si Liu	Beihang University	China	OpenUAV
Xian Sun, Kun Fu	Aerospace Information Research Institute, Chinese Academy of Sciences	China	AeroVerse
Yutao Yue, Hui Xiong	HKUST (Guangzhou)	China	AutoFly, AirCopBench
Yongming Huang	Southeast University + Purple Mountain Labs	China	AutoFly
Xin Eric Wang	University of California, Santa Cruz	USA	AVDN
Lin Zhong	Yale University	USA	TypeFly
Shubo Liu et al.	Northwestern Polytechnical University (NWPU) + Macquarie University	China / Australia	AerialVLN
Yutaka Matsuo, Nakamasa Inoue	University of Tokyo + Institute of Science Tokyo	Japan	CityNAV

---

Datasets and Benchmarks

• [AirCopBench]: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning
  AAAI 2026 paper page

• [EmbodiedCity]: A Benchmark Platform for Embodied Agent in Real-world City Environment
  Preprint, 2024 paper page code

• [OpenUAV]: Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
  Preprint, 2024 paper page code

• [AeroVerse]: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models
  Preprint, 2024 paper code

• [CityNAV]: Language-Goal Aerial Navigation Dataset with Geographic Information
  Preprint, 2024 paper code

• [AerialVLN]: Vision-and-Language Navigation for UAVs
  ICCV 2023 paper code

• [AVDN]: Aerial Vision-and-Dialog Navigation
  ACL 2023 paper code

---

Aerial VLN

• [OnFly]: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency
  2026 page paper

• [AutoFly]: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild
  2026 page paper

• [NavDreamer]: Video Models as Zero-Shot 3D Navigators
  2026 page paper

• [See, Point, Fly (SPF)]: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation
  2025 paper

• [OpenFLY]: A Versatile Toolchain and Large-scale Benchmark for Aerial Vision-Language Navigation
  Preprint, 2025 paper code

• [AeroVerse]: UAV-Agent Benchmark Suite for Simulating, Pre-training, Finetuning, and Evaluating Aerospace Embodied World Models
  Journal Preprint, 2025 paper

• [STMR]: Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning
  Preprint, 2024 paper video

• [OpenUAV]: Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
  Preprint, 2024 paper page

• [CityNAV]: Language-Goal Aerial Navigation Dataset with Geographic Information
  Preprint, 2024 paper code

• [PIVOT]: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
  2024 paper

• [AerialVLN]: Vision-and-Language Navigation for UAVs
  ICCV 2023 paper code

• [AVDN]: Aerial Vision-and-Dialog Navigation
  ACL 2023 paper code

• [TypeFly]: Flying Drones with Large Language Model
  2023 paper

---

Simulators

• [AVDN] code

• [AerialVLN] code

• [CityNAV] code

• [OpenUAV] page

• [EmbodiedCity] page code

---

Links

• Awesome VLN by Eric Lab

mail: oleg.sautenkov[at]skoltech.ru