航空学报 > 2022, Vol. 43 Issue (8): 25645-025645   doi: 10.7527/S1000-6893.2021.25645

低空小型无人机空域冲突视觉感知技术研究进展

张洲宇1, 曹云峰1, 范彦铭2   

  1. 1. 南京航空航天大学 航天学院, 南京 210016;
    2. 中航工业沈阳飞机设计研究所, 沈阳 110035
  • 收稿日期:2021-04-12 修回日期:2021-08-17 出版日期:2022-08-15 发布日期:2021-08-17
  • 通讯作者: 曹云峰,E-mail:cyfac@nuaa.edu.cn E-mail:cyfac@nuaa.edu.cn
  • 基金资助:
    国家自然科学基金(61673211);南京航空航天大学空间光电探测与感知工业和信息化部重点实验室开放课题(NJ2020021-01);中央高校基本科研业务费专项资金(NJ2020021)

Research progress of vision based aerospace conflict sensing technologies for small unmanned aerial vehicle in low altitude

ZHANG Zhouyu1, CAO Yunfeng1, FAN Yanming2   

  1. 1. College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
    2. ACIC Shenyang Aircraft Design and Research Institute, Shenyang 110035, China
  • Received:2021-04-12 Revised:2021-08-17 Online:2022-08-15 Published:2021-08-17
  • Supported by:
    National Natural Science Foundation of China (61673211);Open Project Funds for the Key Laboratory of Space Photoelectric Detection and Perception (Nanjing University of Aeronautics and Astronautics),Ministry of Industry and Information Technology (NJ2020021-01);Fundamental Research Funds for the Central Universities (NJ2020021)

摘要: 无人机(UAV)空域冲突感知技术是国家空域集成中最具挑战的关键技术,针对小型无人机在低空空域应用愈加广泛、迫切需要融入低空空域的背景,综述了低空小型无人机空域冲突视觉感知技术的研究进展。首先,论述了低空小型无人机的应用现状,归纳了低空空域环境与小型无人机的典型特征;其次,根据感知对象的类型,将现有的空域冲突感知设备分为协同式与非协同式2类,通过对比总结了机器视觉作为低空小型无人机空域冲突感知设备的优势;然后,论述了视觉信息预处理、入侵目标视觉检测、基于视觉的避障路径规划这3项空域冲突视觉感知关键技术的最新研究进展;最后,总结了该领域有待进一步解决的难点,并对未来的发展方向进行展望。

关键词: 低空空域, 无人机(UVA), 空域冲突, 机器视觉, 感知与规避

Abstract: Unmanned Aerial Vehicles (UAV) aerospace conflict sensing is the most challenging key technology in national aerospace integration. Considering the broad application of small sized UAVs in low altitude aerospace, this paper makes a research survey of vision based aerospace conflict sensing technologies. Firstly, the application status of small sized UAVs in low altitude aerospace is briefly introduced, and the typical features of this kind of UAVs is summarized. Secondly, based on the categories of sensing objects, existing aerospace conflict sensing technologies are classified into cooperative sensing method and non-cooperative sensing method. The sensing technology most appropriate for small sized UAVs in low altitude aerospace is concluded. Then, the research progress of three key technologies of vision based aerospace conflict sensing, including visual information pre-processing, vision based intruder detection, vision based collision avoidance trajectory planning, are introduced. Finally, the challenges to be solved in this area are concluded, and several future research trends are introduced.

Key words: low altitude aerospace, Unmanned Aerial Vehicle (UAV), aerospace conflict, machine vision, sensing and avoidance

中图分类号: