Forward kinematics modelling of a parallel ankle rehabilitation robot using modified fuzzy inference

P. K. Jamwal, S. Q. Xie, Y. H. Tsoi, K. C. Aw

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

This article deals with forward kinematics (FK) mapping of a parallel robot, especially designed for ankle joint rehabilitation treatments. Parallel robots exhibit highly coupled non-linear motions hence conventionally a unique closed form solution of their FK cannot be obtained. However, since FK is a key module in closed loop position and force control, its accurate and fast solution is indispensable. To solve the FK problem, a modified fuzzy inference system (FIS) is proposed in this paper for the first time which is time efficient and becomes very accurate when its parameters are optimized. In the proposed work, FIS has been optimized using three approaches namely: gradient descent (GD), genetic algorithm (GA) and modified genetic algorithm (MGA). The FIS, optimized by MGA has been found to be more accurate than the GD and GA optimized FIS. Performance of the MGA based fuzzy system has been found better both in terms of accuracy and computation time, when compared with Newton-Raphson iterative method and other fuzzy and neural approaches.

Original languageEnglish
Pages (from-to)1537-1554
Number of pages18
JournalMechanism and Machine Theory
Volume45
Issue number11
DOIs
Publication statusPublished - Nov 2010
Externally publishedYes

Fingerprint

Fuzzy inference
Patient rehabilitation
Kinematics
Genetic algorithms
Robots
Force control
Position control
Fuzzy systems
Iterative methods

Keywords

  • Forward kinematics
  • Fuzzy inference system
  • Modified genetic algorithm
  • Newton-Raphson method
  • Parallel robots

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Computer Science Applications
  • Bioengineering

Cite this

Forward kinematics modelling of a parallel ankle rehabilitation robot using modified fuzzy inference. / Jamwal, P. K.; Xie, S. Q.; Tsoi, Y. H.; Aw, K. C.

In: Mechanism and Machine Theory, Vol. 45, No. 11, 11.2010, p. 1537-1554.

Research output: Contribution to journalArticle

@article{38c664a2eda648588f679863eefe5e2a,
title = "Forward kinematics modelling of a parallel ankle rehabilitation robot using modified fuzzy inference",
abstract = "This article deals with forward kinematics (FK) mapping of a parallel robot, especially designed for ankle joint rehabilitation treatments. Parallel robots exhibit highly coupled non-linear motions hence conventionally a unique closed form solution of their FK cannot be obtained. However, since FK is a key module in closed loop position and force control, its accurate and fast solution is indispensable. To solve the FK problem, a modified fuzzy inference system (FIS) is proposed in this paper for the first time which is time efficient and becomes very accurate when its parameters are optimized. In the proposed work, FIS has been optimized using three approaches namely: gradient descent (GD), genetic algorithm (GA) and modified genetic algorithm (MGA). The FIS, optimized by MGA has been found to be more accurate than the GD and GA optimized FIS. Performance of the MGA based fuzzy system has been found better both in terms of accuracy and computation time, when compared with Newton-Raphson iterative method and other fuzzy and neural approaches.",
keywords = "Forward kinematics, Fuzzy inference system, Modified genetic algorithm, Newton-Raphson method, Parallel robots",
author = "Jamwal, {P. K.} and Xie, {S. Q.} and Tsoi, {Y. H.} and Aw, {K. C.}",
year = "2010",
month = "11",
doi = "10.1016/j.mechmachtheory.2010.06.017",
language = "English",
volume = "45",
pages = "1537--1554",
journal = "Mechanism and Machine Theory",
issn = "0374-1052",
publisher = "Elsevier",
number = "11",

}

TY - JOUR

T1 - Forward kinematics modelling of a parallel ankle rehabilitation robot using modified fuzzy inference

AU - Jamwal, P. K.

AU - Xie, S. Q.

AU - Tsoi, Y. H.

AU - Aw, K. C.

PY - 2010/11

Y1 - 2010/11

N2 - This article deals with forward kinematics (FK) mapping of a parallel robot, especially designed for ankle joint rehabilitation treatments. Parallel robots exhibit highly coupled non-linear motions hence conventionally a unique closed form solution of their FK cannot be obtained. However, since FK is a key module in closed loop position and force control, its accurate and fast solution is indispensable. To solve the FK problem, a modified fuzzy inference system (FIS) is proposed in this paper for the first time which is time efficient and becomes very accurate when its parameters are optimized. In the proposed work, FIS has been optimized using three approaches namely: gradient descent (GD), genetic algorithm (GA) and modified genetic algorithm (MGA). The FIS, optimized by MGA has been found to be more accurate than the GD and GA optimized FIS. Performance of the MGA based fuzzy system has been found better both in terms of accuracy and computation time, when compared with Newton-Raphson iterative method and other fuzzy and neural approaches.

AB - This article deals with forward kinematics (FK) mapping of a parallel robot, especially designed for ankle joint rehabilitation treatments. Parallel robots exhibit highly coupled non-linear motions hence conventionally a unique closed form solution of their FK cannot be obtained. However, since FK is a key module in closed loop position and force control, its accurate and fast solution is indispensable. To solve the FK problem, a modified fuzzy inference system (FIS) is proposed in this paper for the first time which is time efficient and becomes very accurate when its parameters are optimized. In the proposed work, FIS has been optimized using three approaches namely: gradient descent (GD), genetic algorithm (GA) and modified genetic algorithm (MGA). The FIS, optimized by MGA has been found to be more accurate than the GD and GA optimized FIS. Performance of the MGA based fuzzy system has been found better both in terms of accuracy and computation time, when compared with Newton-Raphson iterative method and other fuzzy and neural approaches.

KW - Forward kinematics

KW - Fuzzy inference system

KW - Modified genetic algorithm

KW - Newton-Raphson method

KW - Parallel robots

UR - http://www.scopus.com/inward/record.url?scp=77956393450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956393450&partnerID=8YFLogxK

U2 - 10.1016/j.mechmachtheory.2010.06.017

DO - 10.1016/j.mechmachtheory.2010.06.017

M3 - Article

VL - 45

SP - 1537

EP - 1554

JO - Mechanism and Machine Theory

T2 - Mechanism and Machine Theory

JF - Mechanism and Machine Theory

SN - 0374-1052

IS - 11

ER -