Sensor management for identity fusion on a mobile robot
This paper addresses the problem of identity fusion, i.e. the problem of selecting
one of several identity hypotheses concerning an observed object. Two problems are
considered. Firstly the problem of preserving the information in the representation
and fusion of measurements relating to identity hypotheses is treated. For this a
method that operates within the boundaries of classical probability theory but share
some advantages with less rigorous methods such as Dempster-Shafer reasoning is
introduced. Secondly the problem of selecting the most appropriate sensing action
is addressed. A simple and computationally cheap metric is proposed and shown to be
very efficient.