Degrees of confidence fusion in a probabilistic context application to range data fusion

In order to perform sensor-based map building of an indoor environment for autonomous mobile robots, this paper presents a methodology allowing the merging of degrees of confidence associated to beliefs represented by binary propositions. Such a belief is, by hypothesis, the membership of an element to a given set. The degree of confidence notion is introduced in the combined framework of logic and probability theory. The problem is posed as follows: if different experts give their own degrees of confidence in a belief H, how is it possible to merge these degrees? This paper develops only the case in which experts characterize different elements belonging to the same set. Obtained results are applied to ultrasonic range data fusion