Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications

In smart cities and factories, robotic applications require high accuracy and security, which depends on precise inverse dynamics modeling. However, the physical modeling methods cannot include the nondeterministic factors of the manipulator, such as flexibility, joint clearance, and friction. In th...

Full description

Saved in:
Bibliographic Details
Main Authors: Nan Liu, Liangyu Li, Bing Hao, Liusong Yang, Tonghai Hu, Tao Xue, Shoujun Wang, Xingmao Shao
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/9053715
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849412623959851008
author Nan Liu
Liangyu Li
Bing Hao
Liusong Yang
Tonghai Hu
Tao Xue
Shoujun Wang
Xingmao Shao
author_facet Nan Liu
Liangyu Li
Bing Hao
Liusong Yang
Tonghai Hu
Tao Xue
Shoujun Wang
Xingmao Shao
author_sort Nan Liu
collection DOAJ
description In smart cities and factories, robotic applications require high accuracy and security, which depends on precise inverse dynamics modeling. However, the physical modeling methods cannot include the nondeterministic factors of the manipulator, such as flexibility, joint clearance, and friction. In this paper, the Semiparametric Deep Learning (SDL) method is proposed to model robot inverse dynamics. SDL is a type of deep learning framework, designed for optimal inference, combining the Rigid Body Dynamics (RBD) model and Nonparametric Deep Learning (NDL) model. The SDL model takes advantage of the global characteristics of classic RBD and the powerful fitting capabilities of the deep learning approach. Moreover, the parametric and nonparametric parts of the SDL model can be optimized at the same time instead of being optimized separately. The proposed method is validated using experiments, performed on a UR5 robotic platform. The results show that the performance of SDL model is better than that of RBD model and NDL model. SDL can always provide relatively accurate joint torque prediction, even when the RBD or NDL model is not accurate.
format Article
id doaj-art-5f356ce0846444eea1bbd1ee137a8543
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-5f356ce0846444eea1bbd1ee137a85432025-08-20T03:34:22ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/90537159053715Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial ApplicationsNan Liu0Liangyu Li1Bing Hao2Liusong Yang3Tonghai Hu4Tao Xue5Shoujun Wang6Xingmao Shao7School of Mechanical Engineering, Tianjin Polytechnic University, Tianjin 300387, ChinaSchool of Mechanical Engineering, Tianjin Polytechnic University, Tianjin 300387, ChinaCITIC Heavy Industries Co., Ltd., Luoyang 471003, ChinaCITIC Heavy Industries Co., Ltd., Luoyang 471003, ChinaCITIC Heavy Industries Co., Ltd., Luoyang 471003, ChinaNational Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, ChinaNational Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, ChinaNational Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin 300384, ChinaIn smart cities and factories, robotic applications require high accuracy and security, which depends on precise inverse dynamics modeling. However, the physical modeling methods cannot include the nondeterministic factors of the manipulator, such as flexibility, joint clearance, and friction. In this paper, the Semiparametric Deep Learning (SDL) method is proposed to model robot inverse dynamics. SDL is a type of deep learning framework, designed for optimal inference, combining the Rigid Body Dynamics (RBD) model and Nonparametric Deep Learning (NDL) model. The SDL model takes advantage of the global characteristics of classic RBD and the powerful fitting capabilities of the deep learning approach. Moreover, the parametric and nonparametric parts of the SDL model can be optimized at the same time instead of being optimized separately. The proposed method is validated using experiments, performed on a UR5 robotic platform. The results show that the performance of SDL model is better than that of RBD model and NDL model. SDL can always provide relatively accurate joint torque prediction, even when the RBD or NDL model is not accurate.http://dx.doi.org/10.1155/2020/9053715
spellingShingle Nan Liu
Liangyu Li
Bing Hao
Liusong Yang
Tonghai Hu
Tao Xue
Shoujun Wang
Xingmao Shao
Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
Complexity
title Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
title_full Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
title_fullStr Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
title_full_unstemmed Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
title_short Semiparametric Deep Learning Manipulator Inverse Dynamics Modeling Method for Smart City and Industrial Applications
title_sort semiparametric deep learning manipulator inverse dynamics modeling method for smart city and industrial applications
url http://dx.doi.org/10.1155/2020/9053715
work_keys_str_mv AT nanliu semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT liangyuli semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT binghao semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT liusongyang semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT tonghaihu semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT taoxue semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT shoujunwang semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications
AT xingmaoshao semiparametricdeeplearningmanipulatorinversedynamicsmodelingmethodforsmartcityandindustrialapplications