Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Aquil Mirza Mohammed; Shuai Li

doi:10.1109/TCYB.2015.2451213

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Aquil Mirza Mohammed, Shuai Li

Research output: Journal article publication › Journal article › Academic research › peer-review

58 Citations (Scopus)

Abstract

Redundancy resolution is a critical problem in the control of parallel Stewart platform. The redundancy endows us with extra design degree to improve system performance. In this paper, the kinematic control problem of Stewart platforms is formulated to a constrained quadratic programming. The Karush-Kuhn-Tucker conditions of the problem is obtained by considering the problem in its dual space, and then a dynamic neural network is designed to solve the optimization problem recurrently. Theoretical analysis reveals the global convergence of the employed dynamic neural network to the optimal solution in terms of the defined criteria. Simulation results verify the effectiveness in the tracking control of the Stewart platform for dynamic motions.

Original language	English
Article number	7166310
Pages (from-to)	1538-1550
Number of pages	13
Journal	IEEE Transactions on Cybernetics
Volume	46
Issue number	7
DOIs	https://doi.org/10.1109/TCYB.2015.2451213
Publication status	Published - 1 Jul 2016

Keywords

Constrained quadratic programming
kinematic redundancy
recurrent neural networks
Stewart platform

ASJC Scopus subject areas

Software
Control and Systems Engineering
Information Systems
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

More information

10.1109/TCYB.2015.2451213

Cite this

@article{4c4ef2716c3646fd95b378efb2c2c5b8,

title = "Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms",

abstract = "Redundancy resolution is a critical problem in the control of parallel Stewart platform. The redundancy endows us with extra design degree to improve system performance. In this paper, the kinematic control problem of Stewart platforms is formulated to a constrained quadratic programming. The Karush-Kuhn-Tucker conditions of the problem is obtained by considering the problem in its dual space, and then a dynamic neural network is designed to solve the optimization problem recurrently. Theoretical analysis reveals the global convergence of the employed dynamic neural network to the optimal solution in terms of the defined criteria. Simulation results verify the effectiveness in the tracking control of the Stewart platform for dynamic motions.",

keywords = "Constrained quadratic programming, kinematic redundancy, recurrent neural networks, Stewart platform",

author = "Mohammed, {Aquil Mirza} and Shuai Li",

year = "2016",

month = jul,

day = "1",

doi = "10.1109/TCYB.2015.2451213",

language = "English",

volume = "46",

pages = "1538--1550",

journal = "IEEE Transactions on Cybernetics",

issn = "2168-2267",

publisher = "IEEE Advancing Technology for Humanity",

number = "7",

}

TY - JOUR

T1 - Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

AU - Mohammed, Aquil Mirza

AU - Li, Shuai

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Redundancy resolution is a critical problem in the control of parallel Stewart platform. The redundancy endows us with extra design degree to improve system performance. In this paper, the kinematic control problem of Stewart platforms is formulated to a constrained quadratic programming. The Karush-Kuhn-Tucker conditions of the problem is obtained by considering the problem in its dual space, and then a dynamic neural network is designed to solve the optimization problem recurrently. Theoretical analysis reveals the global convergence of the employed dynamic neural network to the optimal solution in terms of the defined criteria. Simulation results verify the effectiveness in the tracking control of the Stewart platform for dynamic motions.

AB - Redundancy resolution is a critical problem in the control of parallel Stewart platform. The redundancy endows us with extra design degree to improve system performance. In this paper, the kinematic control problem of Stewart platforms is formulated to a constrained quadratic programming. The Karush-Kuhn-Tucker conditions of the problem is obtained by considering the problem in its dual space, and then a dynamic neural network is designed to solve the optimization problem recurrently. Theoretical analysis reveals the global convergence of the employed dynamic neural network to the optimal solution in terms of the defined criteria. Simulation results verify the effectiveness in the tracking control of the Stewart platform for dynamic motions.

KW - Constrained quadratic programming

KW - kinematic redundancy

KW - recurrent neural networks

KW - Stewart platform

UR - http://www.scopus.com/inward/record.url?scp=84937951091&partnerID=8YFLogxK

U2 - 10.1109/TCYB.2015.2451213

DO - 10.1109/TCYB.2015.2451213

M3 - Journal article

SN - 2168-2267

VL - 46

SP - 1538

EP - 1550

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

IS - 7

M1 - 7166310

ER -

Dynamic Neural Networks for Kinematic Redundancy Resolution of Parallel Stewart Platforms

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this