Visual-Inertial-Laser SLAM Based on ORB-SLAM3

IF 3 3区计算机科学 Q2 AUTOMATION & CONTROL SYSTEMS

Unmanned Systems Pub Date : 2023-04-20 DOI:10.1142/s2301385024500262

Meng Cao, Jia Zhang, Wenjie Chen

{"title":"Visual-Inertial-Laser SLAM Based on ORB-SLAM3","authors":"Meng Cao, Jia Zhang, Wenjie Chen","doi":"10.1142/s2301385024500262","DOIUrl":null,"url":null,"abstract":"At present, visual simultaneous localization and mapping is a hot topic in the field of unmanned systems, which is popular among academic workers because of its advantages of accurate localization, low cost, large amount of information, and wide range of applications, but it still has some problems, including the camera’s vulnerability to the number of feature points and the noise impact of the inertial measurement unit during uniform linear motion. In response to the above problem this paper carries out the research on multi-sensor fusion localization algorithm, the main work is as follows: Based on ORB-SLAM3, a visual-inertial-laser SLAM algorithm is designed. The relative motion of laser location between image frames is obtained from the data of 2D Lidar and laser height sensor. The relative motion of inertial measurement unit between image frames is obtained from inertial measurement unit preintegration. Based on the method of factor graph optimization, the pose of image frame is optimized by reprojection of map point, relative motion increment of inertial measurement unit, and relative motion increment of laser location. The algorithm improves the localization accuracy by about 24.4% over the ORB-SLAM3 visual mode and about 22.6% over the ORB-SLAM3 visual-inertial mode on the data of the UAV physical platform.","PeriodicalId":44832,"journal":{"name":"Unmanned Systems","volume":null,"pages":null},"PeriodicalIF":3.0000,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Unmanned Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/s2301385024500262","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

At present, visual simultaneous localization and mapping is a hot topic in the field of unmanned systems, which is popular among academic workers because of its advantages of accurate localization, low cost, large amount of information, and wide range of applications, but it still has some problems, including the camera’s vulnerability to the number of feature points and the noise impact of the inertial measurement unit during uniform linear motion. In response to the above problem this paper carries out the research on multi-sensor fusion localization algorithm, the main work is as follows: Based on ORB-SLAM3, a visual-inertial-laser SLAM algorithm is designed. The relative motion of laser location between image frames is obtained from the data of 2D Lidar and laser height sensor. The relative motion of inertial measurement unit between image frames is obtained from inertial measurement unit preintegration. Based on the method of factor graph optimization, the pose of image frame is optimized by reprojection of map point, relative motion increment of inertial measurement unit, and relative motion increment of laser location. The algorithm improves the localization accuracy by about 24.4% over the ORB-SLAM3 visual mode and about 22.6% over the ORB-SLAM3 visual-inertial mode on the data of the UAV physical platform.

查看原文本刊更多论文

基于orb -SLAM的视觉-惯性激光SLAM

目前，视觉同步定位与制图是无人系统领域的一个热门课题，因其定位准确、成本低、信息量大、应用范围广等优点受到学术界工作者的青睐，但仍存在一些问题，包括摄像机易受特征点数量的影响以及惯性测量单元在匀速直线运动过程中的噪声影响等。针对上述问题，本文开展了多传感器融合定位算法的研究，主要工作如下:基于ORB-SLAM3，设计了一种视觉-惯性-激光SLAM算法。利用二维激光雷达和激光高度传感器的数据，得到图像帧间激光位置的相对运动。通过对惯性测量单元进行预积分，得到了惯性测量单元在图像帧间的相对运动。基于因子图优化方法，通过地图点的重投影、惯性测量单元的相对运动增量和激光定位的相对运动增量来优化图像帧位姿。在无人机物理平台数据上，该算法的定位精度比ORB-SLAM3视觉模式提高约24.4%，比ORB-SLAM3视觉惯性模式提高约22.6%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Unmanned Systems AUTOMATION & CONTROL SYSTEMS-

CiteScore

8.50

自引率

30.20%

发文量

期刊介绍： An unmanned system is a machine or device that is equipped with necessary data processing units, sensors, automatic control, and communications systems and is capable of performing missions autonomously without human intervention. Unmanned systems include unmanned aircraft, ground robots, underwater explorers, satellites, and other unconventional structures. Unmanned Systems (US) aims to cover all subjects related to the development of automatic machine systems, which include advanced technologies in unmanned hardware platforms (aerial, ground, underwater and unconventional platforms), unmanned software systems, energy systems, modeling and control, communications systems, computer vision systems, sensing and information processing, navigation and path planning, computing, information fusion, multi-agent systems, mission management, machine intelligence, artificial intelligence, and innovative application case studies. US welcomes original manuscripts in the following categories: research papers, which disseminate scientific findings contributing to solving technical issues underlying the development of unmanned systems; review articles and state-of-the-art surveys, which describe the latest in basic theories, principles, and innovative applications; short articles, which discuss the latest significant achievements and the future trends; and book reviews. Special issues related to the topics of US are welcome. A short proposal should be sent to the Editors-in-Chief. It should include a tentative title; the information of the Guest Editor(s); purpose and scope; possible contributors; and a tentative timetable. If the proposal is accepted, the Guest Editor(s) will be responsible for the special issue and should follow the normal US review process. Copies of the reviewed papers and the reviewers'' comments should be given to the Editors-in-Chief for recording purposes.