World model representations for mobile robots

Abstract

World Model is a key component of any intelligent machine. The modeling system must be able to adequately model the complexity of objects in the environment and it must contain enough structure to allow the low level sensory data to map to the model during the robot operations. The world model builds its representation of the environment based on the data returned by the sensory system of the robot. However, the environment is not static and cannot always be constrained. There is much uncertainty in the world. The representation needs to be able to deal with the uncertainties and update its internal structures. This paper evaluates several world models suitable for mobile robot applications.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>