Data-Based Design of Inverse Dynamics Using Gaussian Process

Junghoon Lee; Sehoon Oh

doi:10.1109/ICMECH.2019.8722853

Data-Based Design of Inverse Dynamics Using Gaussian Process

Junghoon Lee, Sehoon Oh

Department of Robotics and Mechatronics Engineering

Daegu Gyeongbuk Institute of Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Model-based controller design has been widely utilized for various purposes, and many methodologies have been proposed to identify accurate models of the target plants. In this paper, a different methodology to design dynamics model, particularly inverse dynamics model is proposed using Gaussian process. The design process and selection of training input pattern for inverse dynamics learning Gaussian process are analyzed in this paper. The simulation results reveal the potential and limitation of the proposed Gaussian process based inverse dynamics learning.

Original language	English
Title of host publication	Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	449-454
Number of pages	6
ISBN (Electronic)	9781538669594
DOIs	https://doi.org/10.1109/ICMECH.2019.8722853
State	Published - 24 May 2019
Event	2019 IEEE International Conference on Mechatronics, ICM 2019 - Ilmenau, Germany Duration: 18 Mar 2019 → 20 Mar 2019

Publication series

Name	Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

Conference

Conference	2019 IEEE International Conference on Mechatronics, ICM 2019
Country/Territory	Germany
City	Ilmenau
Period	18/03/19 → 20/03/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Data-based controller design
Disturbance observer
Gaussian Process
Inverse dynamics model

Access to Document

10.1109/ICMECH.2019.8722853

Cite this

Lee, J., & Oh, S. (2019). Data-Based Design of Inverse Dynamics Using Gaussian Process. In Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019 (pp. 449-454). Article 8722853 (Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMECH.2019.8722853

@inproceedings{82bc87a3c2a0471990c64ea5551ce620,

title = "Data-Based Design of Inverse Dynamics Using Gaussian Process",

abstract = "Model-based controller design has been widely utilized for various purposes, and many methodologies have been proposed to identify accurate models of the target plants. In this paper, a different methodology to design dynamics model, particularly inverse dynamics model is proposed using Gaussian process. The design process and selection of training input pattern for inverse dynamics learning Gaussian process are analyzed in this paper. The simulation results reveal the potential and limitation of the proposed Gaussian process based inverse dynamics learning.",

keywords = "Data-based controller design, Disturbance observer, Gaussian Process, Inverse dynamics model",

author = "Junghoon Lee and Sehoon Oh",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE International Conference on Mechatronics, ICM 2019 ; Conference date: 18-03-2019 Through 20-03-2019",

year = "2019",

month = may,

day = "24",

doi = "10.1109/ICMECH.2019.8722853",

language = "English",

series = "Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "449--454",

booktitle = "Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019",

}

Lee, J & Oh, S 2019, Data-Based Design of Inverse Dynamics Using Gaussian Process. in Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019., 8722853, Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019, Institute of Electrical and Electronics Engineers Inc., pp. 449-454, 2019 IEEE International Conference on Mechatronics, ICM 2019, Ilmenau, Germany, 18/03/19. https://doi.org/10.1109/ICMECH.2019.8722853

Data-Based Design of Inverse Dynamics Using Gaussian Process. / Lee, Junghoon; Oh, Sehoon.
Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 449-454 8722853 (Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Data-Based Design of Inverse Dynamics Using Gaussian Process

AU - Lee, Junghoon

AU - Oh, Sehoon

PY - 2019/5/24

Y1 - 2019/5/24

N2 - Model-based controller design has been widely utilized for various purposes, and many methodologies have been proposed to identify accurate models of the target plants. In this paper, a different methodology to design dynamics model, particularly inverse dynamics model is proposed using Gaussian process. The design process and selection of training input pattern for inverse dynamics learning Gaussian process are analyzed in this paper. The simulation results reveal the potential and limitation of the proposed Gaussian process based inverse dynamics learning.

AB - Model-based controller design has been widely utilized for various purposes, and many methodologies have been proposed to identify accurate models of the target plants. In this paper, a different methodology to design dynamics model, particularly inverse dynamics model is proposed using Gaussian process. The design process and selection of training input pattern for inverse dynamics learning Gaussian process are analyzed in this paper. The simulation results reveal the potential and limitation of the proposed Gaussian process based inverse dynamics learning.

KW - Data-based controller design

KW - Disturbance observer

KW - Gaussian Process

KW - Inverse dynamics model

UR - http://www.scopus.com/inward/record.url?scp=85067095295&partnerID=8YFLogxK

U2 - 10.1109/ICMECH.2019.8722853

DO - 10.1109/ICMECH.2019.8722853

M3 - Conference contribution

AN - SCOPUS:85067095295

T3 - Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

SP - 449

EP - 454

BT - Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE International Conference on Mechatronics, ICM 2019

Y2 - 18 March 2019 through 20 March 2019

ER -

Data-Based Design of Inverse Dynamics Using Gaussian Process

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this