Neural network based global adaptive dynamic surface tracking control for robot manipulators

Tao Teng; Chenguang Yang; Bin Xu; Zhijun Li

doi:10.1109/ICARM.2016.7606888

Neural network based global adaptive dynamic surface tracking control for robot manipulators

Tao Teng, Chenguang Yang, Bin Xu, Zhijun Li

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

5 Scopus citations

Abstract

A neural network empowered dynamic surface control (DSC) technique is addressed for robot manipulators system with unknown dynamics. In comparison to the conventional adaptive neural control algorithms, which could guarantee semi-globally uniformly ultimate boundedness (SGUUB) only when neural approximation keeps effective, the scheme designed in this paper ensures globally uniformly ultimately bounded (GUUB) stability by integrating a switching mechanism which incorporates an additional robust controller to drag the transient state variables back when they go beyond the neural approximation region. Simulation studies on 2-joint robot manipulator have been carried out to validate the designed controller has excellent performance.

Original language	English
Title of host publication	ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	20-25
Number of pages	6
ISBN (Electronic)	9781509033645
DOIs	https://doi.org/10.1109/ICARM.2016.7606888
State	Published - 21 Oct 2016
Externally published	Yes
Event	2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016 - Macau, China Duration: 18 Aug 2016 → 20 Aug 2016

Publication series

Name	ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics

Conference

Conference	2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016
Country/Territory	China
City	Macau
Period	18/08/16 → 20/08/16

Access to Document

10.1109/ICARM.2016.7606888

Cite this

Teng, T., Yang, C., Xu, B., & Li, Z. (2016). Neural network based global adaptive dynamic surface tracking control for robot manipulators. In ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics (pp. 20-25). Article 7606888 (ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICARM.2016.7606888

Teng, Tao ; Yang, Chenguang ; Xu, Bin et al. / Neural network based global adaptive dynamic surface tracking control for robot manipulators. ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 20-25 (ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics).

@inproceedings{0cb79437bdcd461da6769611800b5def,

title = "Neural network based global adaptive dynamic surface tracking control for robot manipulators",

abstract = "A neural network empowered dynamic surface control (DSC) technique is addressed for robot manipulators system with unknown dynamics. In comparison to the conventional adaptive neural control algorithms, which could guarantee semi-globally uniformly ultimate boundedness (SGUUB) only when neural approximation keeps effective, the scheme designed in this paper ensures globally uniformly ultimately bounded (GUUB) stability by integrating a switching mechanism which incorporates an additional robust controller to drag the transient state variables back when they go beyond the neural approximation region. Simulation studies on 2-joint robot manipulator have been carried out to validate the designed controller has excellent performance.",

author = "Tao Teng and Chenguang Yang and Bin Xu and Zhijun Li",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016 ; Conference date: 18-08-2016 Through 20-08-2016",

year = "2016",

month = oct,

day = "21",

doi = "10.1109/ICARM.2016.7606888",

language = "英语",

series = "ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics",

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

pages = "20--25",

booktitle = "ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics",

}

Teng, T, Yang, C, Xu, B & Li, Z 2016, Neural network based global adaptive dynamic surface tracking control for robot manipulators. in ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics., 7606888, ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics, Institute of Electrical and Electronics Engineers Inc., pp. 20-25, 2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016, Macau, China, 18/08/16. https://doi.org/10.1109/ICARM.2016.7606888

Neural network based global adaptive dynamic surface tracking control for robot manipulators. / Teng, Tao; Yang, Chenguang; Xu, Bin et al.
ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics. Institute of Electrical and Electronics Engineers Inc., 2016. p. 20-25 7606888 (ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics).

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

TY - GEN

T1 - Neural network based global adaptive dynamic surface tracking control for robot manipulators

AU - Teng, Tao

AU - Yang, Chenguang

AU - Xu, Bin

AU - Li, Zhijun

PY - 2016/10/21

Y1 - 2016/10/21

N2 - A neural network empowered dynamic surface control (DSC) technique is addressed for robot manipulators system with unknown dynamics. In comparison to the conventional adaptive neural control algorithms, which could guarantee semi-globally uniformly ultimate boundedness (SGUUB) only when neural approximation keeps effective, the scheme designed in this paper ensures globally uniformly ultimately bounded (GUUB) stability by integrating a switching mechanism which incorporates an additional robust controller to drag the transient state variables back when they go beyond the neural approximation region. Simulation studies on 2-joint robot manipulator have been carried out to validate the designed controller has excellent performance.

AB - A neural network empowered dynamic surface control (DSC) technique is addressed for robot manipulators system with unknown dynamics. In comparison to the conventional adaptive neural control algorithms, which could guarantee semi-globally uniformly ultimate boundedness (SGUUB) only when neural approximation keeps effective, the scheme designed in this paper ensures globally uniformly ultimately bounded (GUUB) stability by integrating a switching mechanism which incorporates an additional robust controller to drag the transient state variables back when they go beyond the neural approximation region. Simulation studies on 2-joint robot manipulator have been carried out to validate the designed controller has excellent performance.

UR - http://www.scopus.com/inward/record.url?scp=84998886348&partnerID=8YFLogxK

U2 - 10.1109/ICARM.2016.7606888

DO - 10.1109/ICARM.2016.7606888

M3 - 会议稿件

AN - SCOPUS:84998886348

T3 - ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics

SP - 20

EP - 25

BT - ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016

Y2 - 18 August 2016 through 20 August 2016

ER -

Teng T, Yang C, Xu B, Li Z. Neural network based global adaptive dynamic surface tracking control for robot manipulators. In ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics. Institute of Electrical and Electronics Engineers Inc. 2016. p. 20-25. 7606888. (ICARM 2016 - 2016 International Conference on Advanced Robotics and Mechatronics). doi: 10.1109/ICARM.2016.7606888

Neural network based global adaptive dynamic surface tracking control for robot manipulators

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this