Research of Polishing Robot Inverse Calibration

Abstract

An innovative robot calibration approach: inverse robot calibration based on neural network, is proposed in this paper. This method takes the robot joint angles and corresponding angle errors as input and output sample of a feed-forward neural network, achieving the errors in arbitrary angles through training the neural network. Pose accuracy is improved only through correcting the joints angles. This calibration method comes down all error effects to joint errors, and completes arbitrary joint errors compensation. Calibration results are compared with those obtained by traditional parametric methodologies. Simulation and experiment results show that this method is more effective than the traditional calibration methods. Finally, a logical explanation for the results is given