Vision-Based Imitation Learning of Needle Reaching Skill for Robotic Precision Manipulation

doi:10.1007/s10846-020-01290-1

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Vision-Based Imitation Learning of Needle Reaching Skill for Robotic Precision Manipulation
	Li, Ying1,2 ; Qin, Fangbo1,2 ; Du, Shaofeng 3; Xu, De1,2 ; Zhang, Jianqiang 3
发表期刊	JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
ISSN	0921-0296
	2021
卷号	101 期号:1 页码:13
通讯作者	Li, Ying(liying2016@ia.ac.cn)
摘要	In this paper, an imitation learning approach of vision guided reaching skill is proposed for robotic precision manipulation, which enables the robot to adapt its end-effector's nonlinear motion with the awareness of collision-avoidance. The reaching skill model firstly uses the raw images of objects as inputs, and generates the incremental motion command to guide the lower-level vision-based controller. The needle's tip is detected in image space and the obstacle region is extracted by image segmentation. A neighborhood-sampling method is designed for needle component collision perception, which includes a neural networks based attention module. The neural network based policy module infers the desired motion in the image space according to the neighborhood-sampling result, goal and current positions of the needle's tip. A refinement module is developed to further improve the performance of the policy module. In three dimensional (3D) manipulation tasks, typically two cameras are used for image-based vision control. Therefore, considering the epipolar constraint, the relative movements in two cameras' views are refined by optimization. Experimental are conducted to validate the effectiveness of the proposed methods.
关键词	Imitation learning Skill learning Visual control Robotic precision manipulation Neural networks
DOI	10.1007/s10846-020-01290-1
关键词[WOS]	MICROSCOPIC VISION
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0103005] ; National Natural Science Foundation of China[61873266] ; State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System[GZ2019KF008]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System
WOS研究方向	Computer Science ; Robotics
WOS类目	Computer Science, Artificial Intelligence ; Robotics
WOS记录号	WOS:000600232300001
出版者	SPRINGER
七大方向——子方向分类	智能控制
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42787
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
通讯作者	Li, Ying
作者单位	1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.State Key Lab Smart Mfg Special Vehicles & Transm, Baotou City 014000, Inner Mongolia, Peoples R China
第一作者单位	精密感知与控制研究中心
通讯作者单位	精密感知与控制研究中心
推荐引用方式 GB/T 7714	Li, Ying,Qin, Fangbo,Du, Shaofeng,et al. Vision-Based Imitation Learning of Needle Reaching Skill for Robotic Precision Manipulation[J]. JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,2021,101(1):13.
APA	Li, Ying,Qin, Fangbo,Du, Shaofeng,Xu, De,&Zhang, Jianqiang.(2021).Vision-Based Imitation Learning of Needle Reaching Skill for Robotic Precision Manipulation.JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS,101(1),13.
MLA	Li, Ying,et al."Vision-Based Imitation Learning of Needle Reaching Skill for Robotic Precision Manipulation".JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS 101.1(2021):13.