Fuzzy Behavior-Based Control : 1st Report, A Proposal of Control System Realization

Abstract

A fuzzy behavior-based control system is proposed for a mobile robot by applying the concept of subsumption architecture. A simple fuzzy reasoning (e.g., simplified fuzzy reasoning) is assigned to one elemental behavior consisting of a single input-output relation, and then two consequent results from two behavioral groups are competed or cooperated. Here, it is assumed that the order of the input in a behavioral group is the same as that of the output and other behavioral groups have the same condition. For the competition or cooperation between behavioral groups or elemental behaviors, a suppression unit is constructed as a neural network by using a sgn function or saturation function. Furthermore, a Jacobian net is introduced to transform the results obtained from the competition or cooperation to the joint coordinate systems. Finally, we consider one example for a mobile robot with two independent driving wheels.