Inverse robot calibration using artificial neural networks

Abstract Robot end-effector locations (position and orientation) achieved by controlling joint values obtained from a robot controller will, in general, deviate from the desired location due to inaccuracies in the internal kinematic model. Inverse calibration is defined as finding the corrected joint values to drive a robot so that deviations of the end-effector are minimised. Conventional numerical approaches to the inverse calibration of robots are time-consuming and suffer from numerical problems of ill-conditioning and singularities. In this paper, methods using artificial neural networks (NN) have been developed for robot inverse compensation, for both local and global calibration problems. Simulation and experimental results for a Puma robot are presented to show the effectiveness of the NN-based approach.

[1]  Bahram Ravani,et al.  An overview of robot calibration , 1987, IEEE Journal on Robotics and Automation.

[2]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[3]  Arthur C. Sanderson,et al.  Arm signature identification , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[4]  Louis J. Everett,et al.  Automatic singularity avoidance using joint variations in robot task modification , 1994, IEEE Robotics & Automation Magazine.

[5]  Jeff Ho,et al.  Design of robot accuracy compensator after calibration , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[6]  Hanqi Zhuang,et al.  Optimal design of robot accuracy compensators , 1993, IEEE Trans. Robotics Autom..

[7]  Alan Pugh.  Recent Trends in Robotics. Modelling, Control and Education , 1989 .

[8]  S A Hayati,et al.  Inverse kinematic solution for near-simple robots and its applications to robot calibration , 1986 .

[9]  X. L. Zhong,et al.  Neuro-accuracy compensator for industrial robots , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

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

[11]  H. Zhuang,et al.  Kinematic modeling, identification and compensation of robot manipulators , 1989 .

[12]  Jeff S. Shamma,et al.  A Method for Inverse Robot Calibration , 1987 .

[13]  Christopher Kozakiewicz,et al.  Calibration analysis of a direct drive robot , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[14]  F. B. Prinz,et al.  A Perturbation Approach to Robot Calibration , 1987 .

[15]  Zvi S. Roth,et al.  Fundamentals of Manipulator Calibration , 1991 .

[16]  K. C. Gupta,et al.  Compensation of Robot joint variables using special Jacobian matrices , 1992, J. Field Robotics.

[17]  Joydeep Ghosh,et al.  Efficient Higher-Order Neural Networks for Classification and Function Approximation , 1992, Int. J. Neural Syst..