Implementation of a Basic Reactive Behavior in Mobile Robotics Through Artificial Neural Networks

In this work we describe the design and implementation in a Nomad200 mobile robot of a reactive behavior aimed at wall following. A detailed analysis of the application domain has allowed us to modularize the design, conjugating in its. synthesis the potential of artificial neural networks for sensorial abstraction with other decision modules. We have carried out several experiments both in simulated and in real environments, obtaining very good results in different and unfavorable situations, which proves the robustness and flexibility of the system.