Obstacle avoidance for a mobile robot: A neuro-fuzzy approach

In this paper, a neuro-fuzzy approach is presented in order to guide a mobi le robot. This task could be carried out specifying a set of fuzzy rules ta king into account the different situations found by the mobile robot. This set of fuzzy rules could be optimised according to different criteria. Howe ver, the approach shown in this paper, is able to extract a set of fuzzy ru les set from a set of trajectories provided by a human. These trajectories guide the mobile robot towards the target in different cases. Thus, it has been possible to obtain the rules and membership functions automatically, w hereas other approaches need a previous definition of the rules and members hip functions. In order to verify that the obtained behaviour is satisfacto ry, the neuro-fuzzy approach has been implemented in two mobile robots. (C) 2001 Elsevier Science B.V. All rights reserved.