华南理工大学学报（自然科学版）2026，Vol.54Issue(6)：173-182,10.DOI:10.12141/j.issn.1000-565X.260003
无人机视觉语言导航模型综述:从感知理解到智能决策
A Review of Vision-Language Navigation Models for UAVs:From Perceptual Comprehension to Intelligent Decision-Making
摘要
Abstract
The emergence of multimodal large language models(MLLMs)has laid the foundation for the vision-language-navigation paradigm,which integrates visual perception,natural language understanding,and navigation control within a unified strategic framework.This paradigm has been rapidly adopted in the UAV domain,attemp-ting to enable UAVs to understand natural language instructions,reason in three-dimensional environments,and make flight decisions.Compared with traditional modular navigation approaches,the end-to-end framework based on MLLMs can simultaneously process linguistic and visual signals,directly mapping perceptual information into control commands.However,a systematic review of UAV-VLN remains scarce.This paper presents a comprehen-sive review of recent advances in this area:from early modular solutions to reason-centric vision-language-action models.It elucidates how visual,linguistic,and control information are progressively integrated to enhance autono-mous navigation capabilities.It further summarizes existing datasets and evaluation protocols,including simulation tasks in both indoor and outdoor complex environments as well as real-world UAV flight trajectories,with evaluation metrics covering success rate,time cost,and semantic comprehension.Finally,it identifies key challenges,inclu-ding difficulties in cross-modal alignment,insufficient real-time responsiveness in dynamic environments,high an-notation costs,and poor decision-making robustness in complex scenarios.This paper outlines new pathways and future research directions for UAV autonomous navigation research.It highlights the potential of MLLMs in enhan-cing intelligent decision-making and interpretability of UAVs,and serves as a reference for research and practice in achieving safe and efficient autonomous flight of UAVs.关键词
无人机/视觉-语言导航/多模态大语言模型/智能决策Key words
UAV/vision-language navigation/multimodal large language models/intelligent decision-making分类
信息技术与安全科学引用本文复制引用
王子豫,杜宸旭,刘洋..无人机视觉语言导航模型综述:从感知理解到智能决策[J].华南理工大学学报（自然科学版）,2026,54(6):173-182,10.基金项目
北京市昌平区"U35培苗资助计划"项目(CHPU35202504003) （CHPU35202504003）
国家自然科学基金项目(52572334,T2588101,52221005,52220105001) （52572334,T2588101,52221005,52220105001）
清华大学智能绿色车辆与交通全国重点实验室自主研究课题(ZZ-GG-20250403)Supported by the"U35 Pei Miao Funding Program"of Changping District,Beijing(CHPU35202504003),the National Natural Science Foundation of China(52572334,T2588101,52221005,and 52220105001)and the Independent Research Project of the State Key Laboratory of Intelligent Green Vehicle and Mobility,Tsinghua University(ZZ-GG-20250403) （ZZ-GG-20250403）
