摘要
无人机自主飞行避障技术是无人机安全飞行和应用中最为基础和关键的技术,也是当前无人机领域的研究热点。随着深度学习在计算机视觉方向的应用,以及事件相机等视觉传感器技术的迅速发展与不断完善,基于视觉传感器的无人机自主飞行避障方法取得一定的进步,但目前有些研究方法在复杂场景下仍存在很大的挑战以及存在一些列亟待解决的问题,在精准性、实时性以及算法鲁棒性方面仍有改进空间。首先介绍无人机避障的相关概念及问题难点;然后将基于视觉传感器的避障算法根据采用的硬件及技术手段,具体划分为传统避障方法、基于深度学习避障方法、基于处理事件流的避障方法、基于传感器融合避障方法,和基于视觉避障的决策层避障方法,并分别介绍每类避障方法相关研究进展与研究成果,以及分析各类避障方法的优缺点;最后总结现有无人机避障算法存在的问题,并对未来研究工作进行展望。
The UAV autonomous flight obstacle avoidance technology is one of the most fundamental and critical technologies for the safe flight and application of drones,and it is also a current research hotspot in the UAV field.With the application of deep learning in computer vision and the rapid development and continuous improvement of visual sensors such as event cameras,methods about UAV autonomous flight obstacle avoidance based on visual sensors have made some progress.However,many existing research methods still face significant challenges in complex scenarios and a series of urgent problems that need to be addressed,particularly in terms of accuracy,real-time performance,and algorithm robustness.This paper first introduces the relevant concepts and difficulties of UAV obstacle avoidance.Then it categorizes obstacle avoidance algorithms based on visual sensors according to the hardware and technical approaches used into traditional obstacle avoidance methods,deep learning-based obstacle avoidance methods,event stream processing-based obstacle avoidance methods,sensor fusion-based obstacle avoidance methods,and decision-level obstacle avoidance methods based on vision.Each category of obstacle avoidance methods is discussed in detail,including their research progress and achievements,as well as an analysis of their advantages and disadvantages.Finally,the paper summarizes the existing problems in UAV obstacle avoidance algorithms and provides an outlook on future research directions.
作者
王家亮
董楷
顾兆军
陈辉
韩强
WANG Jialing;DONG Kai;GU Zhaojun;CHEN Hui;HAN Qiang(School ofComputer Science and Technology,Civil Aviation University of China,TianJin 300300,China;Information Security Assessment Center of Civil Aviation University of China,TianJin 300300,China;Aviation Meteorological Center,Air Traffic Management Bureau,Civil Aviation Administration of China,100022,China)
出处
《西安电子科技大学学报》
北大核心
2025年第1期60-79,共20页
Journal of Xidian University
基金
天津市教委科研计划项目(2020KJ026)
民航安全能力建设资金(PESA2022093)。
关键词
无人机
避障传感器
计算机视觉
事件相机
unmanned aerial vehicle
obstacle detectors
computer vision
event camera
作者简介
王家亮(1983-),男,讲师,博士,E-mail:jl-wang@cauc.edu.cn;董楷(1999-),男,中国民航大学硕士研究生,E-mail:dongkai_cauc@163.com;陈辉(1998-),男,硕士,E-mail:chenhui15532379008@163.com;韩强(1997-),男,中国民航大学硕士研究生,E-mail:hanqiang_cauc@163.com;通信作者:顾兆军(1966-),男,教授,博士,E-mail:zjgu@cauc.edu.cn。
