Cargando…

DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment

Recent advancements in deep learning techniques have accelerated the growth of robotic vision systems. One way this technology can be applied is to use a mobile robot to automatically generate a 3D map and identify objects within it. This paper addresses the important challenge of labeling objects a...

Descripción completa

Detalles Bibliográficos
Autores principales: Roch, Jesse, Fayyad, Jamil, Najjaran, Homayoun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181773/
https://www.ncbi.nlm.nih.gov/pubmed/37177568
http://dx.doi.org/10.3390/s23094364
_version_ 1785041654648930304
author Roch, Jesse
Fayyad, Jamil
Najjaran, Homayoun
author_facet Roch, Jesse
Fayyad, Jamil
Najjaran, Homayoun
author_sort Roch, Jesse
collection PubMed
description Recent advancements in deep learning techniques have accelerated the growth of robotic vision systems. One way this technology can be applied is to use a mobile robot to automatically generate a 3D map and identify objects within it. This paper addresses the important challenge of labeling objects and generating 3D maps in a dynamic environment. It explores a solution to this problem by combining Deep Object Pose Estimation (DOPE) with Real-Time Appearance-Based Mapping (RTAB-Map) through means of loose-coupled parallel fusion. DOPE’s abilities are enhanced by leveraging its belief map system to filter uncertain key points, which increases precision to ensure that only the best object labels end up on the map. Additionally, DOPE’s pipeline is modified to enable shape-based object recognition using depth maps, allowing it to identify objects in complete darkness. Three experiments are performed to find the ideal training dataset, quantify the increased precision, and evaluate the overall performance of the system. The results show that the proposed solution outperforms existing methods in most intended scenarios, such as in unilluminated scenes. The proposed key point filtering technique has demonstrated an improvement in the average inference speed, achieving a speedup of 2.6× and improving the average distance to the ground truth compared to the original DOPE algorithm.
format Online
Article
Text
id pubmed-10181773
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-101817732023-05-13 DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment Roch, Jesse Fayyad, Jamil Najjaran, Homayoun Sensors (Basel) Article Recent advancements in deep learning techniques have accelerated the growth of robotic vision systems. One way this technology can be applied is to use a mobile robot to automatically generate a 3D map and identify objects within it. This paper addresses the important challenge of labeling objects and generating 3D maps in a dynamic environment. It explores a solution to this problem by combining Deep Object Pose Estimation (DOPE) with Real-Time Appearance-Based Mapping (RTAB-Map) through means of loose-coupled parallel fusion. DOPE’s abilities are enhanced by leveraging its belief map system to filter uncertain key points, which increases precision to ensure that only the best object labels end up on the map. Additionally, DOPE’s pipeline is modified to enable shape-based object recognition using depth maps, allowing it to identify objects in complete darkness. Three experiments are performed to find the ideal training dataset, quantify the increased precision, and evaluate the overall performance of the system. The results show that the proposed solution outperforms existing methods in most intended scenarios, such as in unilluminated scenes. The proposed key point filtering technique has demonstrated an improvement in the average inference speed, achieving a speedup of 2.6× and improving the average distance to the ground truth compared to the original DOPE algorithm. MDPI 2023-04-28 /pmc/articles/PMC10181773/ /pubmed/37177568 http://dx.doi.org/10.3390/s23094364 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Roch, Jesse
Fayyad, Jamil
Najjaran, Homayoun
DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title_full DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title_fullStr DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title_full_unstemmed DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title_short DOPESLAM: High-Precision ROS-Based Semantic 3D SLAM in a Dynamic Environment
title_sort dopeslam: high-precision ros-based semantic 3d slam in a dynamic environment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10181773/
https://www.ncbi.nlm.nih.gov/pubmed/37177568
http://dx.doi.org/10.3390/s23094364
work_keys_str_mv AT rochjesse dopeslamhighprecisionrosbasedsemantic3dslaminadynamicenvironment
AT fayyadjamil dopeslamhighprecisionrosbasedsemantic3dslaminadynamicenvironment
AT najjaranhomayoun dopeslamhighprecisionrosbasedsemantic3dslaminadynamicenvironment