Direct Kinematics Problem of Parallel Robot Based on LS-SVM

Author

Zha, Shihong ; Mei, Tao ; Luo, Minzhou ; Wang, Deji

Author_Institution

Inst. of Intelligent Machines, Chinese Acad. of Sci., Hefei

Volume

2

fYear

0

fDate

0-0 0

Firstpage

8958

Lastpage

8961

Abstract

Although parallel robot is widely used on many fields now, it is still a fascinating problem of kinematics solution of parallel robot. Using common methods involves the solving a series of simultaneous non-linear equations and, usually, non-unique, multiple sets of solutions are obtained from one set of data. Here a method based on LS-SVM is presented, the proposed method is applied to the parallel robot and satisfactory results are obtained. It proves that the method is feasible and effective. The results show that this approach can be used for the on-line control of parallel manipulators

Keywords

least squares approximations; radial basis function networks; robot kinematics; support vector machines; least square support vector machines; nonlinear equations; parallel manipulators; parallel robot; radial basis function neural network; robot kinematics; Biomimetics; Error analysis; Intelligent robots; Kinematics; Machine intelligence; Multi-layer neural network; Neural networks; Orbital robotics; Parallel robots; Support vector machines; DKP; LS-SVM; RBFNN; parallel robot;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1713732

Filename

1713732