Efficient System Identification of a Two-Wheeled Robot (TWR) Using Feed-Forward Neural Networks

Abstract

System identification of a Two-Wheeled Robot (TWR) through nonlinear dynamics is carried out in this paper using a data-driven approach. An Artificial Neural Network (ANN) is used as a kinematic estimator for predicting the TWR’s degree of movement in the directions of x and y and the angle of rotation Ψ along the z-axis by giving a set of input vectors in terms of linear velocity ‘V’ (i.e., generated through the angular velocity ‘ω’ of a DC motor). The DC motor rotates the TWR’s wheels that have a wheel radius of ‘r’. Training datasets are achieved via simulating nonlinear kinematics of the TWR in a MATLAB Simulink environment by varying the linear scale sets of ‘V’ and ‘(r ± ∆r)’. Perturbation of the TWR’s wheel radius at ∆r = 10% is introduced to cater to the robustness of the TWR wheel kinematics. A trained ANN accurately modeled the kinematics of the TWR. The performance indicators are regression analysis and mean square value, whose achieved values met the targeted values of 1 and 0.01, respectively.

Intelligent Control of Robots with Minimal Power Consumption in Pick-and-Place Operations

“…As follows from [35,36], NN controllers successfully outperform human experts in managing quick and accurate robot motion.…”

Faster Implementation of The Dynamic Window Approach Based on Non-Discrete Path Representation

“…As a result, throughout the simulation period, the robot's motion is characterized by constant velocity circular motion, rendering the simulation path as a circular arc. The relationship among translational velocity, rotational velocity, and path radius is articulated in (12) [28][29][30][31][32].…”

“…First, we generate a pair of circles in contact with the starting point of the path. The function of the inner circle is defined in ( 26) and (27), and that of the outer circle is expressed in (28) and (29). The center points of the circles are 0, v 0 ω 0 and 0,…”