Adaptive Neural Network Control of Biped Robots

Changyin Sun; Wei He; Weiliang Ge; Cheng Chang

doi:10.1109/TSMC.2016.2557223

Adaptive Neural Network Control of Biped Robots

Changyin Sun
, Wei He
, Weiliang Ge
, Cheng Chang

Southeast University, Nanjing
University of Science and Technology Beijing
University of Electronic Science and Technology of China

Research output: Contribution to journal › Article › peer-review

154 Scopus citations

Abstract

In this paper, neural network control strategies based on radial basis functions are designed for biped robots, which includes balancing and posture control. To deal with system uncertainties, neural networks are used to approximate the unknown model of the robot. Both full state feedback control and output feedback control are considered in this paper. With the proposed control, the trajectories of the closed-loop system are semiglobally uniformly bounded which can be proved via Lyapunov stability theorem. Simulations are also carried out to illustrate the effectiveness of the proposed control.

Original language	English
Article number	7467542
Pages (from-to)	315-326
Number of pages	12
Journal	IEEE Transactions on Systems, Man, and Cybernetics: Systems
Volume	47
Issue number	2
DOIs	https://doi.org/10.1109/TSMC.2016.2557223
State	Published - Feb 2017
Externally published	Yes

Keywords

Adaptive control
balancing control
biped robots
neural networks
posture control
tracking control

Access to Document

10.1109/TSMC.2016.2557223

Cite this

@article{c98640e2cd3f41cda5c4c981eb1469b0,

title = "Adaptive Neural Network Control of Biped Robots",

abstract = "In this paper, neural network control strategies based on radial basis functions are designed for biped robots, which includes balancing and posture control. To deal with system uncertainties, neural networks are used to approximate the unknown model of the robot. Both full state feedback control and output feedback control are considered in this paper. With the proposed control, the trajectories of the closed-loop system are semiglobally uniformly bounded which can be proved via Lyapunov stability theorem. Simulations are also carried out to illustrate the effectiveness of the proposed control.",

keywords = "Adaptive control, balancing control, biped robots, neural networks, posture control, tracking control",

author = "Changyin Sun and Wei He and Weiliang Ge and Cheng Chang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.",

year = "2017",

month = feb,

doi = "10.1109/TSMC.2016.2557223",

language = "英语",

volume = "47",

pages = "315--326",

journal = "IEEE Transactions on Systems, Man, and Cybernetics: Systems",

issn = "2168-2216",

publisher = "IEEE Advancing Technology for Humanity",

number = "2",

}

TY - JOUR

T1 - Adaptive Neural Network Control of Biped Robots

AU - Sun, Changyin

AU - He, Wei

AU - Ge, Weiliang

AU - Chang, Cheng

PY - 2017/2

Y1 - 2017/2

N2 - In this paper, neural network control strategies based on radial basis functions are designed for biped robots, which includes balancing and posture control. To deal with system uncertainties, neural networks are used to approximate the unknown model of the robot. Both full state feedback control and output feedback control are considered in this paper. With the proposed control, the trajectories of the closed-loop system are semiglobally uniformly bounded which can be proved via Lyapunov stability theorem. Simulations are also carried out to illustrate the effectiveness of the proposed control.

AB - In this paper, neural network control strategies based on radial basis functions are designed for biped robots, which includes balancing and posture control. To deal with system uncertainties, neural networks are used to approximate the unknown model of the robot. Both full state feedback control and output feedback control are considered in this paper. With the proposed control, the trajectories of the closed-loop system are semiglobally uniformly bounded which can be proved via Lyapunov stability theorem. Simulations are also carried out to illustrate the effectiveness of the proposed control.

KW - Adaptive control

KW - balancing control

KW - biped robots

KW - neural networks

KW - posture control

KW - tracking control

UR - https://www.scopus.com/pages/publications/85010001751

U2 - 10.1109/TSMC.2016.2557223

DO - 10.1109/TSMC.2016.2557223

M3 - 文章

AN - SCOPUS:85010001751

SN - 2168-2216

VL - 47

SP - 315

EP - 326

JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems

JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems

IS - 2

M1 - 7467542

ER -

Adaptive Neural Network Control of Biped Robots

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this