Cargando…

Single-Camera Multi-View 6DoF pose estimation for robotic grasping

Accurately estimating the 6DoF pose of objects during robot grasping is a common problem in robotics. However, the accuracy of the estimated pose can be compromised during or after grasping the object when the gripper collides with other parts or occludes the view. Many approaches to improving pose...

Descripción completa

Detalles Bibliográficos
Autores principales: Yuan, Shuangjie, Ge, Zhenpeng, Yang, Lu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10293638/
https://www.ncbi.nlm.nih.gov/pubmed/37383402
http://dx.doi.org/10.3389/fnbot.2023.1136882
_version_ 1785063032368398336
author Yuan, Shuangjie
Ge, Zhenpeng
Yang, Lu
author_facet Yuan, Shuangjie
Ge, Zhenpeng
Yang, Lu
author_sort Yuan, Shuangjie
collection PubMed
description Accurately estimating the 6DoF pose of objects during robot grasping is a common problem in robotics. However, the accuracy of the estimated pose can be compromised during or after grasping the object when the gripper collides with other parts or occludes the view. Many approaches to improving pose estimation involve using multi-view methods that capture RGB images from multiple cameras and fuse the data. While effective, these methods can be complex and costly to implement. In this paper, we present a Single-Camera Multi-View (SCMV) method that utilizes just one fixed monocular camera and the initiative motion of robotic manipulator to capture multi-view RGB image sequences. Our method achieves more accurate 6DoF pose estimation results. We further create a new T-LESS-GRASP-MV dataset specifically for validating the robustness of our approach. Experiments show that the proposed approach outperforms many other public algorithms by a large margin. Quantitative experiments on a real robot manipulator demonstrate the high pose estimation accuracy of our method. Finally, the robustness of the proposed approach is demonstrated by successfully completing an assembly task on a real robot platform, achieving an assembly success rate of 80%.
format Online
Article
Text
id pubmed-10293638
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-102936382023-06-28 Single-Camera Multi-View 6DoF pose estimation for robotic grasping Yuan, Shuangjie Ge, Zhenpeng Yang, Lu Front Neurorobot Neuroscience Accurately estimating the 6DoF pose of objects during robot grasping is a common problem in robotics. However, the accuracy of the estimated pose can be compromised during or after grasping the object when the gripper collides with other parts or occludes the view. Many approaches to improving pose estimation involve using multi-view methods that capture RGB images from multiple cameras and fuse the data. While effective, these methods can be complex and costly to implement. In this paper, we present a Single-Camera Multi-View (SCMV) method that utilizes just one fixed monocular camera and the initiative motion of robotic manipulator to capture multi-view RGB image sequences. Our method achieves more accurate 6DoF pose estimation results. We further create a new T-LESS-GRASP-MV dataset specifically for validating the robustness of our approach. Experiments show that the proposed approach outperforms many other public algorithms by a large margin. Quantitative experiments on a real robot manipulator demonstrate the high pose estimation accuracy of our method. Finally, the robustness of the proposed approach is demonstrated by successfully completing an assembly task on a real robot platform, achieving an assembly success rate of 80%. Frontiers Media S.A. 2023-06-13 /pmc/articles/PMC10293638/ /pubmed/37383402 http://dx.doi.org/10.3389/fnbot.2023.1136882 Text en Copyright © 2023 Yuan, Ge and Yang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Yuan, Shuangjie
Ge, Zhenpeng
Yang, Lu
Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title_full Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title_fullStr Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title_full_unstemmed Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title_short Single-Camera Multi-View 6DoF pose estimation for robotic grasping
title_sort single-camera multi-view 6dof pose estimation for robotic grasping
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10293638/
https://www.ncbi.nlm.nih.gov/pubmed/37383402
http://dx.doi.org/10.3389/fnbot.2023.1136882
work_keys_str_mv AT yuanshuangjie singlecameramultiview6dofposeestimationforroboticgrasping
AT gezhenpeng singlecameramultiview6dofposeestimationforroboticgrasping
AT yanglu singlecameramultiview6dofposeestimationforroboticgrasping