English

FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigation

Computer Vision and Pattern Recognition 2026-03-12 v2

Abstract

Vision-Language Navigation aims to enable agents to understand natural language instructions and carry out appropriate navigation actions in real-world environments. Most work focuses on indoor settings, with little research in complex outdoor scenes. Current UAV Vision-and-Language Navigation models typically act as black boxes without explicit reasoning. We introduce FreeFly-thinking, an end-to-end VLN framework that converts the UAV agent's egocentric images and language instructions into a series of actions, inspired by environment of urban architecture proposed by OpenFly. We first construct a UAV dataset for navigation task, and then performing natural language chain of thought. We adopt a two-stage training strategy: Supervised fine-tuning and Reinforcement fine-tuning. Experiments on unseen test demonstrate a strong performance, presenting robustness and efficiency in UAV navigation issue.

Keywords

Cite

@article{arxiv.2603.07181,
  title  = {FreeFly-Thinking : Aligning Chain-of-Thought Reasoning with Continuous UAV Navigation},
  author = {Jiaxu Zhou and Shaobo Wang and Zhiyuan Yang and Zhenjun Yu and Tao Li},
  journal= {arXiv preprint arXiv:2603.07181},
  year   = {2026}
}

Comments

10 pages, 5 figures, ECCV review

R2 v1 2026-07-01T11:08:28.512Z