中国科学院重庆绿色智能技术研究院机构知识库

QQ客服 官方微博 反馈留言

	Diversified Regularization Enhanced Training for Effective Manipulator Calibration
	Li, Zhibin1,2; Li, Shuai3; Bamasag, Omaimah Omar4; Alhothali, Areej5; Luo, Xin1,2,3
	2022-03-08
摘要	Recently, robot arms have become an irreplaceable production tool, which play an important role in the industrial production. It is necessary to ensure the absolute positioning accuracy of the robot to realize automatic production. Due to the influence of machining tolerance, assembly tolerance, the robot positioning accuracy is poor. Therefore, in order to enable the precise operation of the robot, it is necessary to calibrate the robotic kinematic parameters. The least square method and Levenberg-Marquardt (LM) algorithm are commonly used to identify the positioning error of robot. However, it generally has the overfitting caused by improper regularization schemes. To solve this problem, this article discusses six regularization schemes based on its error models, i.e., L ₁, L ₂, dropout, elastic, log, and swish. Moreover, this article proposes a scheme with six regularization to obtain a reliable ensemble, which can effectively avoid overfitting. The positioning accuracy of the robot is improved significantly after calibration by enough experiments, which verifies the feasibility of the proposed method.
关键词	Robots Robot kinematics Calibration Service robots Robot sensing systems Kinematics End effectors Absolute positioning accuracy ensemble kinematic parameters overfitting regularization scheme robot arms
DOI	10.1109/TNNLS.2022.3153039
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	13
通讯作者	Luo, Xin(luoxin21@gmail.com)
收录类别	SCI
WOS记录号	WOS:000767819300001
语种	英语