Title :
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
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;
Conference_Titel :
Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
Conference_Location :
Dalian
Print_ISBN :
1-4244-0332-4
DOI :
10.1109/WCICA.2006.1713732
