Robot indoor navigation point cloud map generation algorithm based on visual sensing
At present, low-cost Red Green Blue Depth (RGB-D) sensors are mainly used in indoor robot environment perception, but the depth information obtained by RGB-D cameras has problems such as poor accuracy and high noise, and the generated 3D color point cloud map has low accuracy. In order to solve thes...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2023-04-01
|
Series: | Journal of Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1515/jisys-2022-0258 |
_version_ | 1797832484459642880 |
---|---|
author | Zhang Qin Liu Xiushan |
author_facet | Zhang Qin Liu Xiushan |
author_sort | Zhang Qin |
collection | DOAJ |
description | At present, low-cost Red Green Blue Depth (RGB-D) sensors are mainly used in indoor robot environment perception, but the depth information obtained by RGB-D cameras has problems such as poor accuracy and high noise, and the generated 3D color point cloud map has low accuracy. In order to solve these problems, this article proposes a vision sensor-based point cloud map generation algorithm for robot indoor navigation. The aim is to obtain a more accurate point cloud map through visual SLAM and Kalman filtering visual-inertial navigation attitude fusion algorithm. The results show that in the positioning speed test data of the fusion algorithm in this study, the average time-consuming of camera tracking is 23.4 ms, which can meet the processing speed requirement of 42 frames per second. The yaw angle error of the fusion algorithm is the smallest, and the ATE test values of the algorithm are smaller than those of the Inertial measurement unit and Simultaneous-Localization-and-Mapping algorithms. This research algorithm can make the mapping process more stable and robust. It can use visual sensors to make more accurate route planning, and this algorithm improves the indoor positioning accuracy of the robot. In addition, the research algorithm can also obtain a dense point cloud map in real time, which provides a more comprehensive idea for the research of robot indoor navigation point cloud map generation. |
first_indexed | 2024-04-09T14:08:37Z |
format | Article |
id | doaj.art-4ba4786989e445b5a568624debe8307d |
institution | Directory Open Access Journal |
issn | 2191-026X |
language | English |
last_indexed | 2024-04-09T14:08:37Z |
publishDate | 2023-04-01 |
publisher | De Gruyter |
record_format | Article |
series | Journal of Intelligent Systems |
spelling | doaj.art-4ba4786989e445b5a568624debe8307d2023-05-06T15:50:45ZengDe GruyterJournal of Intelligent Systems2191-026X2023-04-01321032171610.1515/jisys-2022-0258Robot indoor navigation point cloud map generation algorithm based on visual sensingZhang Qin0Liu Xiushan1College of Electronics and Information, Guangdong Polytechnic Normal University, Guangzhou510665, ChinaCollege of Electronics and Information, Guangdong Polytechnic Normal University, Guangzhou510665, ChinaAt present, low-cost Red Green Blue Depth (RGB-D) sensors are mainly used in indoor robot environment perception, but the depth information obtained by RGB-D cameras has problems such as poor accuracy and high noise, and the generated 3D color point cloud map has low accuracy. In order to solve these problems, this article proposes a vision sensor-based point cloud map generation algorithm for robot indoor navigation. The aim is to obtain a more accurate point cloud map through visual SLAM and Kalman filtering visual-inertial navigation attitude fusion algorithm. The results show that in the positioning speed test data of the fusion algorithm in this study, the average time-consuming of camera tracking is 23.4 ms, which can meet the processing speed requirement of 42 frames per second. The yaw angle error of the fusion algorithm is the smallest, and the ATE test values of the algorithm are smaller than those of the Inertial measurement unit and Simultaneous-Localization-and-Mapping algorithms. This research algorithm can make the mapping process more stable and robust. It can use visual sensors to make more accurate route planning, and this algorithm improves the indoor positioning accuracy of the robot. In addition, the research algorithm can also obtain a dense point cloud map in real time, which provides a more comprehensive idea for the research of robot indoor navigation point cloud map generation.https://doi.org/10.1515/jisys-2022-0258visual sensorinertial measurement unitrobot indoor navigationpoint cloud mapvisual slam algorithm68t07 |
spellingShingle | Zhang Qin Liu Xiushan Robot indoor navigation point cloud map generation algorithm based on visual sensing Journal of Intelligent Systems visual sensor inertial measurement unit robot indoor navigation point cloud map visual slam algorithm 68t07 |
title | Robot indoor navigation point cloud map generation algorithm based on visual sensing |
title_full | Robot indoor navigation point cloud map generation algorithm based on visual sensing |
title_fullStr | Robot indoor navigation point cloud map generation algorithm based on visual sensing |
title_full_unstemmed | Robot indoor navigation point cloud map generation algorithm based on visual sensing |
title_short | Robot indoor navigation point cloud map generation algorithm based on visual sensing |
title_sort | robot indoor navigation point cloud map generation algorithm based on visual sensing |
topic | visual sensor inertial measurement unit robot indoor navigation point cloud map visual slam algorithm 68t07 |
url | https://doi.org/10.1515/jisys-2022-0258 |
work_keys_str_mv | AT zhangqin robotindoornavigationpointcloudmapgenerationalgorithmbasedonvisualsensing AT liuxiushan robotindoornavigationpointcloudmapgenerationalgorithmbasedonvisualsensing |