Navigation of mobile robots using neural networks and genetic algorithms

The navigation of robots has been a subject of widespread interest over the last few decades. In the previous years, traditional methods based on mathematical equations were used, and there has been an evolution towards the use of methods based on artificial intelligence. Two of which have been used in this work: neural networks and genetic algorithms. Neural networks are used as a machine learning model to teach the robot to move from any starting point to a goal, avoiding obstacles along the way. However, this model needs an algorithm to learn how to carry out this activity, which is what the genetic algorithm will be used for. Furthermore, this method of navigation will be compared with the traditional method based on potential fields, where it can be observed how this new method based on artificial intelligence improves and solves some typical problems of the old methods, such as the tendency to get stuck in local minima.