Fuzzy behaviors combination to control a nonholonomic mobile robot using virtual perception memory

Abstract

This paper presents the implementation of the combination of fuzzy reactive navigation behaviors using virtual perception memory. Robot control actions are generated by different fuzzy behavior components which cooperate to determine the motion of the vehicle. This approach differs from other methods in the use of a virtual perception memory to make a robot controller more robust with respect to temporary loss of sensorial information. Experimental results of an application to a real robot demonstrate the robustness of the proposed method.