Identification of a golf swing robot using soft computing approach

被引:6
作者
Chen, Chaochao [1 ]
Inoue, Yoshio [2 ]
Shibata, Kyoko [2 ]
机构
[1] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
[2] Kochi Univ Technol, Dept Intelligent Mech Syst Engn, Tosayamada, Kochi 7828502, Japan
关键词
Golf swing robots; Identification; Neural networks; Fuzzy logic; Soft computing; SIMULATE HUMAN SKILL; LEARNING CONTROL; NEURAL-NETWORKS; FUZZY; MODEL; SYSTEMS; MANIPULATORS;
D O I
10.1007/s00521-010-0417-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Golf swing robots have been recently developed in an attempt to simulate the ultra high-speed swing motions of golfers. Accurate identification of a golf swing robot is an important and challenging research topic, which has been regarded as a fundamental basis in the motion analysis and control of the robots. But there have been few studies conducted on the golf swing robot identification, and comparative analyses using different kinds of soft computing methodologies have not been found in the literature. This paper investigates the identification of a golf swing robot based on four kinds of soft computing methods, including feedforward neural networks (FFNN), dynamic recurrent neural networks (DRNN), fuzzy neural networks (FNN) and dynamic recurrent fuzzy neural networks (DRFNN). The performance comparison is evaluated based on three sets of swing trajectory data with different boundary conditions. The sensitivity of the results to the changes in system structure and learning rate is also investigated. The results suggest that both FNN and DRFNN can be used as a soft computing method to identify a golf robot more accurately than FFNN and DRNN, which can be used in the motion control of the robot.
引用
收藏
页码:729 / 740
页数:12
相关论文
共 20 条
[1]  
[Anonymous], 1997, IEEE T AUTOM CONTROL, DOI DOI 10.1109/TAC.1997.633847
[2]  
[Anonymous], 1996, Neural fuzzy systems
[3]   On three intelligent systems: dynamic neural, fuzzy, and wavelet networks for training trajectory [J].
Becerikli, Y .
NEURAL COMPUTING & APPLICATIONS, 2004, 13 (04) :339-351
[4]   Nonlinear black box modelling - Fuzzy networks versus neural networks [J].
Bernd, T ;
Kleutges, M ;
Kroll, A .
NEURAL COMPUTING & APPLICATIONS, 1999, 8 (02) :151-162
[5]   Impedance control for a golf swing robot to emulate different-arm-mass golfers [J].
Chen, C. C. ;
Inoue, Y. ;
Shibata, K. .
JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME, 2008, 130 (02) :0210071-0210078
[6]   A MODEL-REFERENCE CONTROL-STRUCTURE USING A FUZZY NEURAL-NETWORK [J].
CHEN, YC ;
TENG, CC .
FUZZY SETS AND SYSTEMS, 1995, 73 (03) :291-312
[7]   CLOSED-FORM DYNAMIC-MODEL OF PLANAR MULTILINK LIGHTWEIGHT ROBOTS [J].
DELUCA, A ;
SICILIANO, B .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1991, 21 (04) :826-839
[8]   A comparative study of soft-computing methodologies in identification of robotic manipulators [J].
Efe, MO ;
Kaynak, O .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2000, 30 (03) :221-230
[9]   Vibration control using a state observer that considers disturbances of a golf swing robot [J].
Hoshino, Y ;
Kobayashi, Y ;
Yamada, G .
JSME INTERNATIONAL JOURNAL SERIES C-MECHANICAL SYSTEMS MACHINE ELEMENTS AND MANUFACTURING, 2005, 48 (01) :60-69
[10]   Identification and control of dynamic systems using recurrent fuzzy neural networks [J].
Lee, CH ;
Teng, CC .
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2000, 8 (04) :349-366