Simulation of a Simple Bio-Mimetic Robot with Neuromorphic Control System and Optimization Based on the Genetic Algorithm

Abstract

Abstract-A simulation of the autonomous differential wheeled mobile robot with a survival intellect was organized in virtual environment created in Matlab and Simulink software. A feed forward two-layer artificial neural network was used as control algorithm for path planning of the simple robot. While the simulations two different optimizing algorithms were implemented to adjust the synapses of the artificial neural network, which are linear and genetic algorithms. The analysis of the simulations demonstrates that the heuristic-based genetic optimization algorithm has better results than a linear optimization. The results of simulations can be used in hardware implementation of a simple mobile robot with neuromorphic control system.