Multi-sensors localization for control of autonomous mobile robot

Abstract

In this paper, we discuss an approach for designing and implementing a multisensory perception system in order to control an autonomous mobile robot when uncertainty and incomplete knowledge are the major characteristics of the situated environment. The approach relies on the combination of local and absolute localization methods. The former is lowly coupled to the environment and makes intensively use of odometric sensors. When high precision is required, telemetric sensors are used, being able to deal with error localization. Then, considering that these modules should cooperate in presence of constraints like limited resources, a knowledgebased system has to be used in order to approach the initially set goals.