Autonomous Localization and Mapping Method of Mobile Robot in Underground Coal Mine Based on Edge Computing

IF 0.9 4区工程技术 Q4 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Circuits Systems and Computers Pub Date : 2023-08-19 DOI:10.1142/s021812662450018x

Qi Mu, Yuhao Wang, Xin Liang, Yang Tang, Zhanli Li

{"title":"Autonomous Localization and Mapping Method of Mobile Robot in Underground Coal Mine Based on Edge Computing","authors":"Qi Mu, Yuhao Wang, Xin Liang, Yang Tang, Zhanli Li","doi":"10.1142/s021812662450018x","DOIUrl":null,"url":null,"abstract":"When applying visual SLAM systems to underground coal mines, several challenges arise. First, there are non-ideal texture areas in the scene, which make feature extraction and matching difficult and reduce the accuracy of positioning and mapping. Second, the limited computing resources of mobile robots prevent the real-time execution of complex algorithms. To address these challenges, this paper proposes an edge computing-based SLAM system that fuses point and line features. The visual odometer of point and line feature fusion solves the problem of insufficient feature extraction in texture sparse areas and incorrect feature matching in texture repetitive areas, thereby improving the accuracy of visual positioning and mapping. The distributed deployment strategy of edge computing enables the algorithm to be executed in real-time on the underground coal mine mobile robot. The experiment demonstrated that using the visual odometer method with ORB-SLAM 2 reduced the absolute trajectory error by 8.87% in dense repetitive texture areas and 9.96% in low texture areas.","PeriodicalId":54866,"journal":{"name":"Journal of Circuits Systems and Computers","volume":" ","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Circuits Systems and Computers","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1142/s021812662450018x","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}

引用次数: 0

Abstract

When applying visual SLAM systems to underground coal mines, several challenges arise. First, there are non-ideal texture areas in the scene, which make feature extraction and matching difficult and reduce the accuracy of positioning and mapping. Second, the limited computing resources of mobile robots prevent the real-time execution of complex algorithms. To address these challenges, this paper proposes an edge computing-based SLAM system that fuses point and line features. The visual odometer of point and line feature fusion solves the problem of insufficient feature extraction in texture sparse areas and incorrect feature matching in texture repetitive areas, thereby improving the accuracy of visual positioning and mapping. The distributed deployment strategy of edge computing enables the algorithm to be executed in real-time on the underground coal mine mobile robot. The experiment demonstrated that using the visual odometer method with ORB-SLAM 2 reduced the absolute trajectory error by 8.87% in dense repetitive texture areas and 9.96% in low texture areas.

查看原文本刊更多论文

基于边缘计算的井下移动机器人自主定位与映射方法

在将可视化SLAM系统应用于煤矿井下时，会遇到一些挑战。首先，场景中存在非理想纹理区域，使得特征提取和匹配困难，降低了定位和映射的精度。其次，移动机器人有限的计算资源阻碍了复杂算法的实时执行。为了解决这些问题，本文提出了一种融合点和线特征的边缘计算SLAM系统。点线特征融合视觉里程计解决了纹理稀疏区域特征提取不足和纹理重复区域特征匹配不正确的问题，从而提高了视觉定位和映射的精度。边缘计算的分布式部署策略使得算法能够在煤矿井下移动机器人上实时执行。实验表明，基于ORB-SLAM 2的视觉里程计方法在密集重复纹理区域的绝对轨迹误差降低8.87%，在低纹理区域的绝对轨迹误差降低9.96%。

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

Journal of Circuits Systems and Computers 工程技术-工程：电子与电气

CiteScore

2.80

自引率

26.70%

发文量

350

审稿时长

5.4 months

期刊介绍： Journal of Circuits, Systems, and Computers covers a wide scope, ranging from mathematical foundations to practical engineering design in the general areas of circuits, systems, and computers with focus on their circuit aspects. Although primary emphasis will be on research papers, survey, expository and tutorial papers are also welcome. The journal consists of two sections: Papers - Contributions in this section may be of a research or tutorial nature. Research papers must be original and must not duplicate descriptions or derivations available elsewhere. The author should limit paper length whenever this can be done without impairing quality. Letters - This section provides a vehicle for speedy publication of new results and information of current interest in circuits, systems, and computers. Focus will be directed to practical design- and applications-oriented contributions, but publication in this section will not be restricted to this material. These letters are to concentrate on reporting the results obtained, their significance and the conclusions, while including only the minimum of supporting details required to understand the contribution. Publication of a manuscript in this manner does not preclude a later publication with a fully developed version.