Transparent and flexible neural network structure for robot dynamics identification
Pedram Agand, Mahdi Aliyari Shoorehdeli, Mohammad Teshnehlab · 2016
In this paper, a novel architecture in multilayer perceptron (MLP) neural network with flexible activation function and adaptive learning rate is presented for a data-driven identification of robot dynamics. It is assumed that the measurement of robot end-effector position, velocity and acceleration are available corrupted by Gaussian noise. Since some general property of robot dynamics are included in the proposed structure as well as optimization indices, this structure is envisaged having good performance in confronting with uncertainty in measurements. The main contribution of this paper is to propose a transparent neural network structure for identification of dynamic terms by introducing a gray-box identifier. Simulation results on 2-DOF serial manipulator reveal the accuracy of the method. Finally, experimental results on a laboratory-scaled twin rotor CE 150 helicopter indicate the applicability of the proposed method.