PD-type control with neural-network-based gravity compensation for compliant joint robots

Yuancan Huang; Zeguo Li; Zonglin Huang; Qiang Huang

doi:10.1109/ICMA.2015.7237593

PD-type control with neural-network-based gravity compensation for compliant joint robots

Yuancan Huang, Zeguo Li, Zonglin Huang, Qiang Huang

School of Mechatronical Engineering

Beijing Institute of Technology

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

2 Citations (Scopus)

Abstract

Since the gravity terms depend only on the link positions in compliant joint robots, a neural-network-based gravity compensation scheme is conceived while the gravity model is unknown or is too complicated to be expressed explicitly. A PD-type control with this compensation is developed with the high-gain torque inner loop such that singular perturbation theory may be used to analyze the stability and passivity. Finally, three experiments are implemented to validate the effectiveness of the invented PD-type control with neural-network-based gravity compensation.

Original language	English
Title of host publication	2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	831-836
Number of pages	6
ISBN (Electronic)	9781479970964
DOIs	https://doi.org/10.1109/ICMA.2015.7237593
Publication status	Published - 2 Sept 2015
Event	12th IEEE International Conference on Mechatronics and Automation, ICMA 2015 - Beijing, China Duration: 2 Aug 2015 → 5 Aug 2015

Publication series

Name	2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015

Conference

Conference	12th IEEE International Conference on Mechatronics and Automation, ICMA 2015
Country/Territory	China
City	Beijing
Period	2/08/15 → 5/08/15

Keywords

Compliant Joint Robot
Gravity Compensation
Neural Network
PD Control
Singular Perturbation Theory

Access to Document

10.1109/ICMA.2015.7237593

Cite this

Huang, Y., Li, Z., Huang, Z., & Huang, Q. (2015). PD-type control with neural-network-based gravity compensation for compliant joint robots. In 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015 (pp. 831-836). Article 7237593 (2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMA.2015.7237593

Huang, Yuancan ; Li, Zeguo ; Huang, Zonglin et al. / PD-type control with neural-network-based gravity compensation for compliant joint robots. 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 831-836 (2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015).

@inproceedings{12c83144e7294cc1ad7e0b9d276d61ec,

title = "PD-type control with neural-network-based gravity compensation for compliant joint robots",

abstract = "Since the gravity terms depend only on the link positions in compliant joint robots, a neural-network-based gravity compensation scheme is conceived while the gravity model is unknown or is too complicated to be expressed explicitly. A PD-type control with this compensation is developed with the high-gain torque inner loop such that singular perturbation theory may be used to analyze the stability and passivity. Finally, three experiments are implemented to validate the effectiveness of the invented PD-type control with neural-network-based gravity compensation.",

keywords = "Compliant Joint Robot, Gravity Compensation, Neural Network, PD Control, Singular Perturbation Theory",

author = "Yuancan Huang and Zeguo Li and Zonglin Huang and Qiang Huang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th IEEE International Conference on Mechatronics and Automation, ICMA 2015 ; Conference date: 02-08-2015 Through 05-08-2015",

year = "2015",

month = sep,

day = "2",

doi = "10.1109/ICMA.2015.7237593",

language = "English",

series = "2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015",

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

pages = "831--836",

booktitle = "2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015",

address = "United States",

}

Huang, Y, Li, Z, Huang, Z & Huang, Q 2015, PD-type control with neural-network-based gravity compensation for compliant joint robots. in 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015., 7237593, 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015, Institute of Electrical and Electronics Engineers Inc., pp. 831-836, 12th IEEE International Conference on Mechatronics and Automation, ICMA 2015, Beijing, China, 2/08/15. https://doi.org/10.1109/ICMA.2015.7237593

PD-type control with neural-network-based gravity compensation for compliant joint robots. / Huang, Yuancan; Li, Zeguo; Huang, Zonglin et al.
2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 831-836 7237593 (2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015).

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

TY - GEN

T1 - PD-type control with neural-network-based gravity compensation for compliant joint robots

AU - Huang, Yuancan

AU - Li, Zeguo

AU - Huang, Zonglin

AU - Huang, Qiang

PY - 2015/9/2

Y1 - 2015/9/2

N2 - Since the gravity terms depend only on the link positions in compliant joint robots, a neural-network-based gravity compensation scheme is conceived while the gravity model is unknown or is too complicated to be expressed explicitly. A PD-type control with this compensation is developed with the high-gain torque inner loop such that singular perturbation theory may be used to analyze the stability and passivity. Finally, three experiments are implemented to validate the effectiveness of the invented PD-type control with neural-network-based gravity compensation.

AB - Since the gravity terms depend only on the link positions in compliant joint robots, a neural-network-based gravity compensation scheme is conceived while the gravity model is unknown or is too complicated to be expressed explicitly. A PD-type control with this compensation is developed with the high-gain torque inner loop such that singular perturbation theory may be used to analyze the stability and passivity. Finally, three experiments are implemented to validate the effectiveness of the invented PD-type control with neural-network-based gravity compensation.

KW - Compliant Joint Robot

KW - Gravity Compensation

KW - Neural Network

KW - PD Control

KW - Singular Perturbation Theory

UR - http://www.scopus.com/inward/record.url?scp=84955280177&partnerID=8YFLogxK

U2 - 10.1109/ICMA.2015.7237593

DO - 10.1109/ICMA.2015.7237593

M3 - Conference contribution

AN - SCOPUS:84955280177

T3 - 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015

SP - 831

EP - 836

BT - 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE International Conference on Mechatronics and Automation, ICMA 2015

Y2 - 2 August 2015 through 5 August 2015

ER -

Huang Y, Li Z, Huang Z, Huang Q. PD-type control with neural-network-based gravity compensation for compliant joint robots. In 2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 831-836. 7237593. (2015 IEEE International Conference on Mechatronics and Automation, ICMA 2015). doi: 10.1109/ICMA.2015.7237593

PD-type control with neural-network-based gravity compensation for compliant joint robots

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this