《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (8): 2620-2629.DOI: 10.11772/j.issn.1001-9081.2025070852

• 多媒体计算与计算机仿真 • 上一篇    

基于视觉AI与三维网格计算的低空动态导航方法

何胜文1,2(), 张淑军3, 刘羿漩2, 李辉3, 刘宇丰2   

  1. 1.中科星图股份有限公司 立体交通事业部,北京 101300
    2.中科星图智慧科技有限公司 立体交通事业部,山东 青岛 266000
    3.青岛科技大学 数据科学学院,山东 青岛 266061
  • 收稿日期:2025-07-29 修回日期:2025-10-29 接受日期:2025-10-29 发布日期:2025-12-22 出版日期:2026-08-10
  • 通讯作者: 何胜文
  • 作者简介:张淑军(1980—),女,山东泰安人,副教授,博士,主要研究方向:计算机视觉
    刘羿漩(1998—),女,黑龙江青冈人,工程师,硕士,主要研究方向:图像处理、模式识别
    李辉(1984—),男,河南平顶山人,副教授,博士,主要研究方向:计算机视觉、3D视觉、多模态目标检测及跟踪
    刘宇丰(1999—),男,黑龙江宁安人,硕士,主要研究方向:计算机视觉、3D视觉。
  • 基金资助:
    国家重点研发计划项目(2021YFB3901105);山东省自然科学基金面上项目(ZR2024MF023);山东省工程研究中心开放课题(KJ20240388)

Low-altitude dynamic navigation method based on visual AI and 3D grid computing

Shengwen HE1,2(), Shujun ZHANG3, Yixuan LIU2, Hui LI3, Yufeng LIU2   

  1. 1.3D Transportation Business Department,Geovis Technology Company Limited,Beijing 101300,China
    2.3D Transportation Business Department,Geovis Wisdom Technology Company Limited,Qingdao Shandong 266000,China
    3.School of Data Science,Qingdao University of Science and Technology,Qingdao Shandong 266061,China
  • Received:2025-07-29 Revised:2025-10-29 Accepted:2025-10-29 Online:2025-12-22 Published:2026-08-10
  • Contact: Shengwen HE
  • About author:ZHANG Shujun, born in 1980, Ph. D., associate professor. Her research interests include computer vision.
    LIU Yixuan, born in 1998, M. S., engineer. Her research interests include image processing, pattern recognition.
    LI Hui, born in 1984, Ph. D., associate professor. His research interests include computer vision, 3D vision, multimodal object detection and tracking.
    LIU Yufeng, born in 1999, M. S. His research interests include computer vision, 3D vision.
  • Supported by:
    National Key Research and Development Program of China(2021YFB3901105);General Program of Shandong Provincial Natural Science Foundation(ZR2024MF023);Open Project of Shandong Provincial Engineering Research Center(KJ20240388)

摘要:

针对无人机(UAV)导航中三维航图更新慢、动态避障能力差和全局感知缺乏等问题,提出一种基于视觉人工智能(AI)与三维网格计算的低空动态导航方法。该方法构建立体三维空域网格表意体系,利用网格索引高效表示空间信息关联,结合机载视觉AI模型实时感知环境语义信息,并通过语义特征嵌入算法将感知结果实时映射至三维空域网格,以支持UAV自主避障飞行。在同一子级空域对应的局部网格内,构建自组织通信网络,实时共享UAV位置、速度和高度等状态,以形成低空动态信息池,使UAV能够在类似起降区等高密度区域精准掌握邻机状态。同时,采用递归来剖分立体网格,并且层级搜索路径通过局部网格交互协商协议实现过载网格的智能分流。以50 km2城市低空场景为实验对象,设简单、中等和复杂三类场景,对比所提方法与全球导航卫星系统(GNSS)纯定位导航和单目视觉特征点导航。结果显示:在三类场景中,所提方法的平均避障有效率分别为96.7%±1.2%、95.3%±1.1%和93.8%±1.5%,较GNSS纯定位导航分别提升了10.5、10.8和11.7个百分点,较单目视觉特征点导航分别提升26.9、27.8和28.6个百分点。可见,所提方法能有效解决UAV导航的核心痛点,并显著提升复杂低空环境下的导航效率与安全性。

关键词: 网格智能体, 视觉人工智能, 低空路线规划, 无人机导航, 自动避障

Abstract:

Aiming at problems of slow update of 3D aeronautical chart, poor dynamic obstacle avoidance ability and lack of global perception in Unmanned Aerial Vehicle (UAV) navigation, a low-altitude dynamic navigation method based on visual Artificial Intelligence (AI) and 3D grid computing was proposed. In the method, the 3D spatial grid representation system was constructed, grid index was used to represent spatial information associations efficiently, combined with the airborne visual AI model, the environmental semantic information was perceived in real time, and the perceptual results were mapped into the 3D spatial grid in real time through the semantic feature embedding algorithm, so as to support the autonomous obstacle avoidance flight of UAVs. In local grid corresponding to the same sub-level airspace, a self-organizing communication network was constructed to share position, speed, height and other states of UAV in real time, thereby forming a low-altitude dynamic information pool, so that UAVs were able to grasp the neighboring UAV states in high-density areas such as take-off and landing areas accurately. At the same time, the 3D grid was subdivided recursively, and hierarchical search path was used to achieve overload grid intelligent flow distribution through the local grid interactive negotiation protocol. Taking the low-altitude scene of 50 square kilometers of city as the experimental object, three kinds of scenes, simple, medium and complex, were set up to compare the proposed method with Global Navigation Satellite System (GNSS) pure positioning navigation and monocular visual feature point navigation. The results show that in the three scenarios, the average obstacle avoidance efficiency of the proposed method is 96.7%±1.2%, 95.3%±1.1% and 93.8%±1.5%, respectively, which is 10.5, 10.8 and 11.7 percentage points higher than that of GNSS pure positioning navigation, and 26.9, 27.8 and 28.6 percentage points higher than that of monocular visual feature point navigation. It can be seen that the proposed method can solve the core pain points of UAV navigation effectively, and improve navigation efficiency and safety in complex low-altitude environment significantly.

Key words: grid agent, visual Artificial Intelligence (AI), low-altitude route planning, Unmanned Aerial Vehicle (UAV) navigation, automatic obstacle avoidance

中图分类号: