An Integration visual navigation algorithm for urban air mobility

被引：2

作者：

Li, Yandong ^{[1
]}

Jiang, Bo ^{[1
]}

Zeng, Long ^{[1
]}

Li, Chenglong ^{[1
]}

机构：

[1] Civil Aviat Flight Univ China, Coll Air Traff Management, Guanghan 618307, Peoples R China

来源：

BIG DATA RESEARCH | 2024年 / 36卷

关键词：

Urban air mobility; UAV; Visual SLAM; Position estimation; Big data; SLAM;

D O I：

10.1016/j.bdr.2024.100447

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents an integration visual navigation algorithm called PnP-ORBSLAM for UAV position estimation in Urban Air Mobility (UAM). ORBSLAM is a popular and benchmark algorithm for vision based navigation applications. The proposed method improve the performance of ORBSLAM by adding a post-processing marker recognition phase to the model. Based on the features extracted from the markers, PnP algorithm is introduced to estimate the position of the monocular camera. The position estimation accuracy of the UAV is supposed to be improved by adding the position information of the camera to the model. Experiment is carried out based on Airsim simulation platform. Results show that the PnP-ORBSLAM algorithm can improve the three-dimensional accuracy by a margin of 5.38 % compared with ORBSLAM. In addition, the process speed of the proposed method can reach about 28 frames per second. It means that the PnP-ORBSLAM algorithm can work in real-time.

引用

页数：7

共 30 条

[1] UAV Localization Using Autoencoded Satellite Images [J].

Bianchi, Mollie ;

Barfoot, Timothy D. .

IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) :1761-1768

[2] Convolutional Neural Networks for Geo-Localisation with a Single Aerial Image [J].

Cabrera-Ponce, Aldrich A. ;

Martinez-Carranza, Jose .

JOURNAL OF REAL-TIME IMAGE PROCESSING, 2022, 19 (03) :565-575

[3] ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM [J].

Campos, Carlos ;

Elvira, Richard ;

Gomez Rodriguez, Juan J. ;

Montiel, Jose M. M. ;

Tardos, Juan D. .

IEEE TRANSACTIONS ON ROBOTICS, 2021, 37 (06) :1874-1890

[4] Review of the robustness and applicability of monocular pose estimation systems for relative navigation with an uncooperative spacecraft [J].

Cassinis, Lorenzo Pasqualetto ;

Fonod, Robert ;

Gill, Eberhard .

PROGRESS IN AEROSPACE SCIENCES, 2019, 110

[5] An auto-landing strategy based on pan-tilt based visual servoing for unmanned aerial vehicle in GNSS-denied environments [J].

Chen, Chengbin ;

Chen, Sifan ;

Hu, Guangsheng ;

Chen, Baihe ;

Chen, Pingping ;

Su, Kaixiong .

AEROSPACE SCIENCE AND TECHNOLOGY, 2021, 116

[6] Experimental evaluation of Visual-Inertial Odometry systems for arable farming [J].

Cremona, Javier ;

Comelli, Roman ;

Pire, Taihu .

JOURNAL OF FIELD ROBOTICS, 2022, 39 (07) :1123-1137

[7] Global optical flow-based estimation of velocity for multicopters using monocular vision in GPS-denied environments [J].

Deng, Heng ;

Arif, Usman ;

Yang, Kun ;

Xi, Zhiyu ;

Quan, Quan ;

Cai, Kai-Yuan .

OPTIK, 2020, 219

[8] LiDAR SLAM with a Wheel Encoder in a Featureless Tunnel Environment [J].

Filip, Iulian ;

Pyo, Juhyun ;

Lee, Meungsuk ;

Joe, Hangil .

ELECTRONICS, 2023, 12 (04)

[9] Dynamic Scene Semantics SLAM Based on Semantic Segmentation [J].

Han, Shuangquan ;

Xi, Zhihong .

IEEE ACCESS, 2020, 8 :43563-43570

[10] AGRI-SLAM: a real-time stereo visual SLAM for agricultural environment [J].

Islam, Rafiqul ;

Habibullah, Habibullah ;

Hossain, Tagor .

AUTONOMOUS ROBOTS, 2023, 47 (06) :649-668

← 1 2 3 →