Neural Networks Approaches for Computing the Forward Kinematics of a Redundant Parallel Manipulator

Authors: H. Sadjadian , H.D. Taghirad Member, A. Fatehi

Abstract:

In this paper, different approaches to solve the forward kinematics of a three DOF actuator redundant hydraulic parallel manipulator are presented. On the contrary to series manipulators, the forward kinematic map of parallel manipulators involves highly coupled nonlinear equations, which are almost impossible to solve analytically. The proposed methods are using neural networks identification with different structures to solve the problem. The accuracy of the results of each method is analyzed in detail and the advantages and the disadvantages of them in computing the forward kinematic map of the given mechanism is discussed in detail. It is concluded that ANFIS presents the best performance compared to MLP, RBF and PNN networks in this particular application.

Keywords: Forward Kinematics, Neural Networks, Numerical Solution, Parallel Manipulators.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1328934

References:

[1] J.P. Merlet, Still a long way to go on the road for parallel mechanisms, ASME 2002 DETC Conference, Montreal, Canada, 2002. Available: http://www-sop.inria.fr.
[2] J.P. Merlet, Parallel Robots: Open problems, In 9th Int'l. Symp. of Robotics Research, Snowbird, 9-12 October 1999. Available: http://www-sop.inria.fr.
[3] O.Didrit, M.Petitot and E.Walter, Guaranteed solution of direct kinematic problems for general configurations of parallel manipulators, IEEE Trans. On Robotics & Automation, April 1998, 259-266.
[4] B. Dasgupta, T.S. Mruthyunjaya, The Stewart platform manipulator: a review, Elsevier Science, Mechanism & Machine theory,2000,15- 40.
[5] Hayward, V.: "Design of a hydraulic robot shoulder based on a combinatorial mechanism" Experimental Robotics III: The 3rd Int'l Symposium, Japan Oct. 1994. Lecture Notes in Control & Information Sciences, Springer-Verlag, 297-310.
[6] Hayward, V.: "Borrowing some design ideas from biological manipulators to design an artificial one" in Robots and Biological System, NATO Series, Springer-Verlag, 1993, 135-148.
[7] Hayward, V. and Kurtz, R.: Modeling of a parallel wrist mechanism with actuator redundancy, Int'l. J. Laboratory Robotics and Automation, VCH Publishers, Vol. 4, No. 2.1992, 69-76.
[8] Z.Geng and L.Haynes, Neural network solution for the forward kinematics problem of a Stewart platform, Proc. Of the 1991 IEEE Int'l Conf. on Robotics & Automation, California, April 1991, 2650- 2655.
[9] C.S.Yee and Kah-bin Lim, Forward kinematics solution of Stewart platform using neural networks, Elsevier Science, Neurocomputing 16, 1997, 333-349.
[10] Nguyen, L., Patel, R.V. and Khorasani, K.: Neural Network Architectures for the forward kinematics problem in robotics. In Proc. of the Joint IEEE International Conference on Neural Networks, San Diego, 1990, 393-399.
[11] D.Wang and A.Zilouchian, Solutions of kinematics of robot manipulators using a kohonen self organizing neural network, Proc. Of the 1997 IEEE Int'l Symp. on intelligent control, Turkey, July 1997, 251-255.
[12] L.H.Sang and M.C.Han, The Estimation for forward kinematic solution of Stewart platform using the neural network, Proc. Of the 1999 IEEE/RSJ Int'l Conf. on Intelligent Robots & Systems, 1999, 501-506.
[13] Lee, S. and Kil, R.M.: Robot kinematic control based on bidirectional mapping neural network. ," in Proc. IJCNN, San Diego, CA, Vol. 3, 1990, 327-335.
[14] Ivakhnenko AG. Polynomial theory of complex systems. IEEE Trans. Systems, Man, Cybernetics, 1971, SMC-1, 364-378.
[15] S.K. Oh, W. Pedrycz, B.J. Park, Polynomial neural networks architecture: analysis & design, Information Sciences 141, 2002, 237-258.
[16] C.Y. Tsai, An iterative feature reduction algorithm for probabilistic neural networks, the International Journal of Management Science, Omega 28, 2000, 513-524.
[17] C.L. Philip chen and A.D. Mc Aulary, Robot kinematics Learning computatons using polynomial neural networks, proceeding of the 1991 IEEE International conference on Robotics and Automation, 1991, 2638-2643.
[18] R. Boudreau, S. Darenfed, On the computation of the Direct kinematics of parallel Maniputators using polynomial networks, IEEE transactions on systems, man and cybernetics, Vol. 28, No. 2, March 1998, 213-220.
[19] J.R. Jang, "ANFIS: Adaptive-network-based fuzzy inference system," IEEE Transaction on systems, man and cybernetics, Vol. 23, No. 3, May/June 1993, 665-685.