Robot inverse kinematics via neural and neurofuzzy networks: architectural and computational aspects for improved performance

Neural networks are universal nonlinear-function approximators and have for long time been used to implement various practical nonlinear inverse mappings. The choice of network type and structure depends on the mapping type and the degree of generalization required. The use of neural networks for solving the inverse robot kinematics has been extensively studied by many workers, but still some problems related to the complexity and strong nonlinearity of the inverse kinematics process need suitable heuristic and adhoc techniques and simplifications. The aim of this paper is exactly to contribute towards filling this gap by investigating a number of computational and architectural issues so as to improve the performance of the implementation of the inverse kinematics process. These issues include the generation and preprocessing of training data, the data scaling, the treatment of multiple solutions, the reduction of the approximation error, and the speeding-up of the training process. A generic neural network architecture is proposed which employs multiple radial-basis function (RBF) network elements and the “mixture of local experts” principle. An algorithm is presented for the training data preprocessing which greatly reduces the training time and overall system error. Two fuzzy-logic solutions are provided and discussed; one employing a fuzzy associative memory (FAM), and the other a neurofuzzy cell architecture proposed by the authors. In all cases no knowledge is assumed about the inverse kinematics of the robot at hand, as long as its forward kinematics is known. Some indicative simulation results are included and discussed.

[1]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[2]  C. S. G. Lee,et al.  Robotics: Control, Sensing, Vision, and Intelligence , 1987 .

[3]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[4]  R. Paul.  Robot manipulators : mathematics, programming, and control : the computer control of robot manipulators , 1981 .

[5]  J. Martinez,et al.  A fuzzy logic positioning system for an articulated robot arm , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[6]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[7]  Ali Zilouchian,et al.  Application of Fuzzy Logic for the Solution of Inverse Kinematics and Hierarchical Controls of Robotic Manipulators , 1998, J. Intell. Robotic Syst..

[8]  Michael I. Jordan.  Supervised learning and systems with excess degrees of freedom , 1988 .

[9]  Madan M. Gupta,et al.  General learning scheme for robot coordinate transformations using dynamic neural network , 1993, Other Conferences.

[10]  A. Guez,et al.  Accelerated convergence in the inverse kinematics via multilayer feedforward networks , 1989, International 1989 Joint Conference on Neural Networks.

[11]  A. Zilouchian,et al.  Intelligent Control Using Artificial Neural Networks and Fuzzy Logic: Recent Trends and Industrial Applications , 1997 .

[12]  Eduard Aved’yan,et al.  The Cerebellar Model Articulation Controller (CMAC) , 1995 .

[13]  A. Guez,et al.  Solution to the inverse kinematics problem in robotics by neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[14]  Nan Zeng,et al.  A Neural Network Based Inverse Kinematics Solution In Robotics , 1993 .

[15]  Allon Guez,et al.  Neurocontroller design via supervised and unsupervised learning , 1989, J. Intell. Robotic Syst..

[16]  Moshe Shoham,et al.  Neural Network Control of Robot Arms , 1992 .

[17]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[18]  Spyros G. Tzafestas,et al.  A flexible neurofuzzy cell structure for general fuzzy inference , 1996 .

[19]  Khashayar Khorasani,et al.  Neural network architectures for the forward kinematics problem in robotics , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[20]  Jyh-Shing Roger Jang,et al.  Self-learning fuzzy controllers based on temporal backpropagation , 1992, IEEE Trans. Neural Networks.

[21]  J. Guo,et al.  A solution to the inverse kinematic problem in robotics using neural network processing , 1989, International 1989 Joint Conference on Neural Networks.

[22]  Jun Wang,et al.  A recurrent neural network for manipulator inverse kinematics computation , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[23]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[24]  Chuen-Tsai Sun,et al.  Neuro-fuzzy modeling and control , 1995, Proc. IEEE.

[25]  Costas S. Tzafestas,et al.  Fuzzy and Neural Intelligent Control: Basic Principles and Architectures , 1997 .

[26]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[27]  Richard S. Sutton,et al.  Connectionist Learning for Control , 1995 .

[28]  M. Kuperstein,et al.  Implementation of an adaptive neural controller for sensory-motor coordination , 1989, International 1989 Joint Conference on Neural Networks.

[29]  Andrew G. Barto,et al.  Connectionist learning for control , 1990 .

[30]  H. Kunkel.  GENERAL INTRODUCTION , 1971, The Journal of experimental medicine.

[31]  N. K. Sinha,et al.  Control of Robotic Manipulators Using Neural Networks — A Survey , 1997 .

[32]  Spyros G. Tzafestas,et al.  A solution to the velocity control of redundant robots , 1996 .

[33]  Carme Torras,et al.  Neural Networks for robot control , 1994, AIRTC.

[34]  Takeshi Tsujimura,et al.  On the characteristics of the robot manipulator controller using neural networks , 1989, International Workshop on Industrial Applications of Machine Intelligence and Vision,.

[35]  John M. Lewis,et al.  Inverse robot calibration using artificial neural networks , 1996 .

[36]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.