基于视觉的无人机自主着陆研究综述  

A Review of Vision-Based Autonomous UAV Landing Research

作　　者：钟春来 杨洋 曹立佳 王喆 Zhong Chunlai;Yang Yang;Cao Lijia;Wang Zhe(School of Automation and Information Engineering,Sichuan University of Science&Engineering,Zigong 643000,China;Artificial Intelligence Key Laboratory of Sichuan Province,Zigong 643000,China;Key Laboratory of Higher Education of Sichuan Province for Enterprise Informationalization and Internet of Things,Yibin 644000,China;Sichuan Tengden Science and Technology Co.,Chengdu 610037,China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,四川自贡643000 [2]人工智能四川省重点实验室,四川自贡643000 [3]企业信息化与物联网测控技术四川省高校重点实验室,四川宜宾644000 [4]四川腾盾科技有限公司,成都610037

出　　处：《航空兵器》2023年第5期104-114,共11页Aero Weaponry

基　　金：中国高校产学研创新基金项目(2021ZYA11002)。

摘　　要：无人机被广泛应用于抢险救灾,自主着陆是无人机应用中的关键技术之一。由于精度和干扰的影响,传统的导航技术如GPS和INS往往不能满足着陆阶段的导航要求。基于视觉的自主着陆系统具有自主性强、成本低、功耗低、抗干扰能力强等优点,适合应用于无人机自主着陆阶段的导航。本文总结了当前基于视觉的无人机自主着陆领域的研究成果,按相机安装位置和着陆平台类型进行梳理,对其中的关键技术进行了比较和分析,并指出了未来的发展趋势。UAVs are widely used in rescue and disaster relief,and autonomous landing is one of the key technologies in the application of UAVs.Due to the influence of accuracy and interference,traditional navigation technologies such as GPS and INS often fail to meet the navigation requirements during landing.Vision-based autonomous landing system has the advantages of strong autonomy,low cost,low power consumption and strong anti-jamming capability,which is suitable for application in the navigation of the autonomous landing phase of UAVs.This paper summarises the current research results in the field of vision-based autonomous landing for UAVs.The camera installation locations and landing platform types are sorted out,the key technologies are compared and analysed,and the future development trends are pointed out.

关 键 词：无人机 自主着陆 计算机视觉 标识检测 导航 

分 类 号：TJ760[兵器科学与技术—武器系统与运用工程] V279[航空宇航科学与技术—飞行器设计]