Abstract
Artificial Neural Networks (ANNs) have recently become the focus of considerable attention in many disciplines, including robot control, where they can be used as a general class of nonlinear models to solve highly nonlinear control problems. Feedforward neural networks have been widely applied for modelling and control purposes. One of the ANN applications in robot control is for the solution of the inverse kinematic problem, which is important in path planning of robot manipulators. This paper proposes an iterative approach and an offset error compensation method to improve the accuracy of the inverse kinematic solutions by using an ANN and a forward kinematic model of a robot. The offset error compensation method offers potential to generate accurately the inverse solution for a class of problems which have an easily obtained forward model and a complicated solution.
Similar content being viewed by others
References
Funahash K. On approximate realization of continuous mappings by neural networks. Neural Networks 1989; 2: 183–192
Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks 1991; 4: 251–257
Cybenko G. Approximation by superpositions of a sigmoidal function. Math Control, Signals Systems 1989; 2: 303–314
Psaltis D, Sideris A, Yamamura A. A multi-layer neural networks controller. IEEE Control Systems Mag 1988; 17–21
Kawato M, Uno Y, Isobe M, Suzuki R. A hierarchical model for voluntary movement and its application to robotics. 1st IEEE Int Conf Neural Networks 1987; 4: 573–582
Nguyen DH, Widrow B. Neural networks for self-learning control system. IEEE Control Systems Mag 1990; 18–23
Arteaga-Bravo FJ. Multilayer back-propagation network for learning the forward and inverse kinematics equations. Int Joint Conf Neural Networks 1990; 2: 319–322
Guez A, Ahmad Z. Accelerated convergence in the inverse kinematics via multi-layer feedforward networks. Int Joint Conf Neural Networks 1989; 2; 341–347
Guo J, Cherkassky V. A solution to the inverse kinematic problem in robotics using neural network processing. Int Joint Conf Neural Networks 1989; 2: 299–304
Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. Parallel Distributed Processing 1986, 1
Denavit J, Hartenberg RS. A kinematic notation for lower-pair mechanisms based on matrices. J Appl Mech 1955; 77: 215–221
Craig JJ Introduction to Robotics: Mechanics and Control, Addison-Wesley, 1989
Lou YF, Brunn P. Using artificial neural networks for solving engineering problems. Proc 31st Int MATADOR Conf 1994; 635–640
Hunn L-J. Neural control of a simple robot. MSc dissertation, UMIST, UK, 1994
Lou Y-F. Non-conventional Computing Methods for Manufacturing Robot Control. PhD Thesis, Department of Mechanical Engineering, UMIST, 1996
Author information
Authors and Affiliations
Corresponding author
Additional information
Now Lecturing in Taiwan.
Rights and permissions
About this article
Cite this article
Lou, Y.F., Brunn, P. An offset error compensation method for improving ANN accuracy when used for position control of precision machinery. Neural Comput & Applic 7, 90–95 (1998). https://doi.org/10.1007/BF01413713
Issue Date:
DOI: https://doi.org/10.1007/BF01413713