Evolutionary learning for improving performance of robot navigation

This paper presents the application of evolutionary learning techniques for improving performance of robot navigation. The goal is to build an intelligent control algorithm that drives the robot in an unknown environment at the maximum allowable speed, while avoiding obstacles and keeping its rate of turns to a minimum. The robot controller is based on an artificial neural network that takes inputs from range sensors and produces outputs to control the drive motors. The ANN is evolved using a simple genetic algorithm. Two different evolutionary learning approaches are evaluated. In the first approach synaptic weights of the network are evolved, while in the second one the adaptation rules of the synapses are evolved. At the end of the evolutionary processes, both solutions resulted in best performing controllers, that can avoid collisions while maximizing linear speed and minimizing turning.