×

Wavelet network solution for the inverse kinematics problem in robotic manipulator. (English) Zbl 1103.68675

Summary: Wavelet network, a class of neural network consisting of wavelets, is proposed to solve the inverse kinematics problem in robotic manipulator. A wavelet network suitable for dealing with multi-input and multi-output system is constructed. The network is optimized by reducing the number of wavelets handling large dimension problem according to the sample data. The algorithms for sparseness analysis of input data and fitting wavelets to the output data with orthogonal method are introduced. Then Levenberg-Marquardt algorithm is used to train the network. Simulation results showed that this method is capable of solving the inverse kinematics problem for PUMA560.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
70B15 Kinematics of mechanisms and robots
65T60 Numerical methods for wavelets
92B20 Neural networks for/in biological studies, artificial life and related topics
68T40 Artificial intelligence for robotics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Chapelle, F., Bidaud, P., 2001. A Closed Form for Inverse Kinematies Approximation of General 6R Manipulators Using Genetic Programming. Proceedings of the 2001 IEEE International Conference on Robotics and Automation, Seoul, Korea, 4:3364-3369. · doi:10.1109/ROBOT.2001.933137
[2] Chen, X.S., Chen, Z.L., Xie, T., 2002. An accurate solution to the inverse kinematic problem of a robot manipulator based on the neural network. Chinese Journal of Robot, 24(2):130-133 (in Chinese).
[3] Guez, A., Ahmad, Z., 1988. Solution to the Inverse Kinematics Problem in Robotics by Neural Networks. IEEE International Conference on Neural Network, San Diego, California, 2:617-621. · doi:10.1109/ICNN.1988.23979
[4] Guo, J., Cherkassky, V., 1989. A Solution to the Inverse Kinematic Problem in Robotics Using Neural Network Processing. IEEE International Conference on Neural Network, Washington D.C., 2:299-304. · doi:10.1109/IJCNN.1989.118714
[5] Mavroidis, C., Ouezdou, F.B., Bidaud, P., 1994. Inverse kinematics of six degree of freedom ‘general’ and ’special’ manipulators using symbolic computation. Robotica, 12(5):421-430. · doi:10.1017/S0263574700017975
[6] Raghavan, M., Roth, B., 1995. Solving polynomial systems for the kinematics analysis and synthesis of mechanisms and robot manipulator. Journal of Mechanical Design, 117:71-79. · doi:10.1115/1.2836473
[7] Sun, W., Wang, Y., Mao, J., 2002. Using Wavelet Network for Identifying the Model of Robot Manipulator. Proceedings of the 4th World Congress on Intelligent Control and Automation, 2:1634-1638. · doi:10.1109/WCICA.2002.1020865
[8] Wu, Y.C., Hsieh, N.H., Chen, Z.R., 2003. The Application of Intelligent Algorithm Principle on Robot Exercise. Proceedings of the 2003 IEEE/ASME International Conference on Advanced Inteligent Mechatronics (AIM 2003), p.371-376.
[9] Zhang, Q.H., 1997. Using wavelet network in nonparametric estimation. IEEE Trans. Neural Network, 8(2):227-236. [doi: 10.1109/72.557660] · doi:10.1109/72.557660
[10] Zhang, Q., Benveniste, A., 1992. Wavelet networks. IEEE Trans. Neural Networks, 3(6):889-898. [doi: 10.1109/72.165591] · doi:10.1109/72.165591
[11] Zhang, W., Ding, Q., 1997. Inverse kinematics for a 6 DOF manipulator based on neural network. Transactions of Nanjing University of Aeronautics and Astronautics, 14(1):73-76. · Zbl 0921.70003
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.