Sensor selection in a fusion process: a fuzzy approach

Abstract

This paper addresses the problem of sensor selection during automatic tasks, such as data fusion or sensing process, and the design of a perceptual system for a mobile robot. The authors propose an approach based on the fuzzy set theory. The process of selection uses a fuzzy preference concept from a criteria set defined by a given task. A mechanism of preference is applied to a sensor, and a technique of aggregation based on the Choquet integrator allows one to define a preference for a set of criteria. We build a preference graph to choose the appropriate sensor or to define the equivalent classes of sensors. After a brief recall on the fuzzy set theory, the selection method is explained and an example is detailed to illustrate the method.<>