A pose estimation system based on deep neural network and ICP registration for robotic spray painting application

doi:10.1007/s00170-019-03901-0

	A pose estimation system based on deep neural network and ICP registration for robotic spray painting application
	Wang, Zhe 1,2; Fan, Junfeng1,2 ; Jing, Fengshui1,2 ; Liu, Zhaoyang1,2 ; Tan, Min1,2
刊名	INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
	2019-09-01
卷号	104 期号:1-4 页码:285-299
关键词	Pose estimation Spray painting RGB-D sensor Deep neural network ICP registration
ISSN号	0268-3768
DOI	10.1007/s00170-019-03901-0
通讯作者	Jing, Fengshui(fengshui.jing@ia.ac.cn)
英文摘要	Nowadays, off-line robot trajectory generation methods based on pre-scanned target model are highly desirable for robotic spray painting application. For actual implementation of the generated trajectory, the relative pose between the actual target and the model needs to be calibrated in the first place. However, obtaining this relative pose remains a challenge, especially from a safe distance in industrial setting. In this paper, a pose estimation system that is able to meet the robotic spray painting requirements is proposed to estimate the pose accurately. The system captures the image of the target using RGB-D vision sensor. The image is then segmented using a modified U-SegNet segmentation network and the resulting segmentation is registered with the pre-scanned model candidates using iterative closest point (ICP) registration to obtain the estimated pose. To strengthen the robustness, a deep convolutional neural network is proposed to determine the rough orientation of the target and guide the selection of model candidates accordingly thus preventing misalignment during registration. The experimental results are compared with relevant researches and validate the accuracy and effectiveness of the proposed system.
资助项目	National Natural Science Foundation of China[U1813208] ; National Natural Science Foundation of China[61573358]
WOS关键词	RECOGNITION ; TOOL
WOS研究方向	Automation & Control Systems ; Engineering
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000483808200016
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27217]
专题	中国科学院自动化研究所
通讯作者	Jing, Fengshui
作者单位	1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Zhe,Fan, Junfeng,Jing, Fengshui,et al. A pose estimation system based on deep neural network and ICP registration for robotic spray painting application[J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY,2019,104(1-4):285-299.
APA	Wang, Zhe,Fan, Junfeng,Jing, Fengshui,Liu, Zhaoyang,&Tan, Min.(2019).A pose estimation system based on deep neural network and ICP registration for robotic spray painting application.INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY,104(1-4),285-299.
MLA	Wang, Zhe,et al."A pose estimation system based on deep neural network and ICP registration for robotic spray painting application".INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 104.1-4(2019):285-299.