Point Pair Feature based 6D pose estimation for robotic grasping

Hejie Fu; Xue Song Mei; Zhaohui Zhang; Wanqiu Zhao; Jun Yang

doi:10.1109/ITNEC48623.2020.9084720

Point Pair Feature based 6D pose estimation for robotic grasping

Hejie Fu
, Xue Song Mei
, Zhaohui Zhang
, Wanqiu Zhao
, Jun Yang

机械工程学院

Xi'an Jiaotong University

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

3 引用（Scopus）

摘要

6D pose estimation is a crucial research topic for flexible and autonomous systems. With the development of 3D sensors, methods using range data or point clouds show great potentials. This paper proposes an effective approach to estimate the target object's 6D pose based on point pair features. Several improvements including cluster-based downsampling, neighbor search using K-D tree, multi-frame point clouds fusion and pose verification were made to optimize the performance of the approach. Based on the object's pose, we propose a strategy to grasp the object. We tested our approach in real environment and get 97.5^% success rate of pose estimation and 95.8% success rate of grasping objects.

源语言	英语
主期刊名	Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020
编辑	Bing Xu, Kefen Mou
出版商	Institute of Electrical and Electronics Engineers Inc.
页	1803-1808
页数	6
ISBN（电子版）	9781728143903
DOI	https://doi.org/10.1109/ITNEC48623.2020.9084720
出版状态	已出版 - 6月 2020
活动	4th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020 - Chongqing, 中国期限: 12 6月 2020 → 14 6月 2020

出版系列

姓名	Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020

会议

会议	4th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020
国家/地区	中国
市	Chongqing
时期	12/06/20 → 14/06/20

联合国可持续发展目标

此成果有助于实现下列可持续发展目标：

可持续发展目标 7 经济适用的清洁能源

访问文件

10.1109/ITNEC48623.2020.9084720

其它文件与链接

链接到 Scopus 的出版物

引用此

Fu, H., Mei, X. S., Zhang, Z., Zhao, W., & Yang, J. (2020). Point Pair Feature based 6D pose estimation for robotic grasping. 在 B. Xu, & K. Mou (编辑), Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020 (页码 1803-1808). 文章 9084720 (Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITNEC48623.2020.9084720

Fu, Hejie ; Mei, Xue Song ; Zhang, Zhaohui 等. / Point Pair Feature based 6D pose estimation for robotic grasping. Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020. 编辑 / Bing Xu ; Kefen Mou. Institute of Electrical and Electronics Engineers Inc., 2020. 页码 1803-1808 (Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020).

@inproceedings{d094b2704d8e48db8f04bcc07974353d,

title = "Point Pair Feature based 6D pose estimation for robotic grasping",

abstract = "6D pose estimation is a crucial research topic for flexible and autonomous systems. With the development of 3D sensors, methods using range data or point clouds show great potentials. This paper proposes an effective approach to estimate the target object's 6D pose based on point pair features. Several improvements including cluster-based downsampling, neighbor search using K-D tree, multi-frame point clouds fusion and pose verification were made to optimize the performance of the approach. Based on the object's pose, we propose a strategy to grasp the object. We tested our approach in real environment and get 97.5\% success rate of pose estimation and 95.8\% success rate of grasping objects.",

keywords = "6D pose estimation, object detection, point pair features, robotic grasping",

author = "Hejie Fu and Mei, \{Xue Song\} and Zhaohui Zhang and Wanqiu Zhao and Jun Yang",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 4th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020 ; Conference date: 12-06-2020 Through 14-06-2020",

year = "2020",

month = jun,

doi = "10.1109/ITNEC48623.2020.9084720",

language = "英语",

series = "Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1803--1808",

editor = "Bing Xu and Kefen Mou",

booktitle = "Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020",

}

Fu, H, Mei, XS, Zhang, Z, Zhao, W & Yang, J 2020, Point Pair Feature based 6D pose estimation for robotic grasping. 在 B Xu & K Mou (编辑), Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020., 9084720, Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020, Institute of Electrical and Electronics Engineers Inc., 页码 1803-1808, 4th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020, Chongqing, 中国, 12/06/20. https://doi.org/10.1109/ITNEC48623.2020.9084720

Point Pair Feature based 6D pose estimation for robotic grasping. / Fu, Hejie; Mei, Xue Song; Zhang, Zhaohui 等.
Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020. 编辑 / Bing Xu; Kefen Mou. Institute of Electrical and Electronics Engineers Inc., 2020. 页码 1803-1808 9084720 (Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Point Pair Feature based 6D pose estimation for robotic grasping

AU - Fu, Hejie

AU - Mei, Xue Song

AU - Zhang, Zhaohui

AU - Zhao, Wanqiu

AU - Yang, Jun

PY - 2020/6

Y1 - 2020/6

N2 - 6D pose estimation is a crucial research topic for flexible and autonomous systems. With the development of 3D sensors, methods using range data or point clouds show great potentials. This paper proposes an effective approach to estimate the target object's 6D pose based on point pair features. Several improvements including cluster-based downsampling, neighbor search using K-D tree, multi-frame point clouds fusion and pose verification were made to optimize the performance of the approach. Based on the object's pose, we propose a strategy to grasp the object. We tested our approach in real environment and get 97.5% success rate of pose estimation and 95.8% success rate of grasping objects.

AB - 6D pose estimation is a crucial research topic for flexible and autonomous systems. With the development of 3D sensors, methods using range data or point clouds show great potentials. This paper proposes an effective approach to estimate the target object's 6D pose based on point pair features. Several improvements including cluster-based downsampling, neighbor search using K-D tree, multi-frame point clouds fusion and pose verification were made to optimize the performance of the approach. Based on the object's pose, we propose a strategy to grasp the object. We tested our approach in real environment and get 97.5% success rate of pose estimation and 95.8% success rate of grasping objects.

KW - 6D pose estimation

KW - object detection

KW - point pair features

KW - robotic grasping

UR - https://www.scopus.com/pages/publications/85086229201

U2 - 10.1109/ITNEC48623.2020.9084720

DO - 10.1109/ITNEC48623.2020.9084720

M3 - 会议稿件

AN - SCOPUS:85086229201

T3 - Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020

SP - 1803

EP - 1808

BT - Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020

A2 - Xu, Bing

A2 - Mou, Kefen

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020

Y2 - 12 June 2020 through 14 June 2020

ER -

Fu H, Mei XS, Zhang Z, Zhao W, Yang J. Point Pair Feature based 6D pose estimation for robotic grasping. 在 Xu B, Mou K, 编辑, Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 页码 1803-1808. 9084720. (Proceedings of 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2020). doi: 10.1109/ITNEC48623.2020.9084720

Point Pair Feature based 6D pose estimation for robotic grasping

摘要

出版系列

会议

联合国可持续发展目标

访问文件

其它文件与链接

学术指纹

引用此