Diversified Regularization Enhanced Training for Effective Manipulator Calibration
文献类型：期刊论文
| 作者 | Li, Zhibin3,4; Li, Shuai1; Bamasag, Omaimah Omar5; Alhothali, Areej2; Luo, Xin1,3,4
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2022-03-08 |
| 页码 | 13 |
| 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 |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2022.3153039 |
| 通讯作者 | Luo, Xin(luoxin21@gmail.com) |
| 英文摘要 | 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. |
| 资助项目 | Chongqing Research Program of Technology Innovation and Application[CAAIXSJLJJ-2021-035A] ; Pioneer Hundred Talents Program of Chinese Academy of Sciences[cstc2019jscx-fxydX0027] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000767819300001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/15341]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Luo, Xin |
| 作者单位 | 1.Swansea Univ, Dept Elect & Elect Engn, Swansea SA1 8EN, W Glam, Wales 2.King Abdulaziz Univ, Fac Comp & Informat Technol, Jeddah 21589, Saudi Arabia 3.Chongqing Univ Posts & Telecommun, Sch Comp Sci & Technol, Chongqing 400065, Peoples R China 4.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China 5.King Abdulaziz Univ, Ctr Excellence Smart Environm Res, Jeddah 21589, Saudi Arabia |
| 推荐引用方式 GB/T 7714 | Li, Zhibin,Li, Shuai,Bamasag, Omaimah Omar,et al. Diversified Regularization Enhanced Training for Effective Manipulator Calibration[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:13. |
| APA | Li, Zhibin,Li, Shuai,Bamasag, Omaimah Omar,Alhothali, Areej,&Luo, Xin.(2022).Diversified Regularization Enhanced Training for Effective Manipulator Calibration.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13. |
| MLA | Li, Zhibin,et al."Diversified Regularization Enhanced Training for Effective Manipulator Calibration".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):13. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。