Using Linde Buzo Gray Clustering Neural Networks for Solving the Motion Equations of a Mobile Robot

Abstract

In this paper, motion equations for the synchro-drive robot Nomad 200 are solved by using Linde Buzo Gray (LBG) clustering neural networks. The trajectories of the Nomad 200 are assumed to be composed of straight line segments and curves. The structure of the curves is determined by only two parameters, turn angle and translational velocity in the curve. The curves of the trajectories are found by using artificial neural networks (ANN) and the LBG clustered ANN. In this study a clustering method is used to improve the learning and test the performance of the ANN. In general, the LBG algorithm is used in image processing as a quantizer. This is the first publication where the LBG algorithm is successfully used in clustering ANN data sets. Thus, the best training data set of the ANN is achieved and minimum error values are obtained. It is shown that LBG-ANN models are better than the classic ANN models.

Characterization of a Mobile Waste-Robot: A Heuristic Method to Path Planning using Artificial Neural Networks

“…SCG is found to be as fast as LM on function approximation but is faster than LM in cases with large datasets [13]. The SCG algorithm is computed using the following equation where "w ji " are the weight values; "v" is number of x vectors; "l" is the learning coefficient' and "S" is the search direction [16]:…”

Motion Control of Non-Holonomic Wheeled Mobile Robot Based on Particle Swarm Optimization Method (PSO)

“…Many investigators have paid their attention to study the problems of controlling the non-holonomic system and as a result of that a number of control algorithms have been achieved to sort out the path-tracking control problems as neural network controller [1], the kinematic back-stepping method controller [2], [3]. Lyapunov criterion is implemented to prove the stability of the proposed control law since this criterion is active in specifying the cited stability [4].…”