A hierarchical neuro-fuzzy approach to autonomous navigation

This work proposes a fuzzy-neural-network-based controller that considers the direction and velocity of navigation as controllable terms. The controller is composed of a number of in-born modules responsible for instant actions at each step of navigation. These in-born modules are then coordinated by a neuro-fuzzy module which exhibits learning. The learning processes take place after collisions against obstacles, after targets are reached and, due to a special memory structure, a learning process may also occur due to a remembering process. Thus, the model proposed carries a high degree of autonomy since the controller learns on its own how to coordinate its basic behaviors, while the navigation occurs.