A distributed autonomous system architecture: applications to mobile robotics

Abstract

The author defines autonomy as the capability of a system to use at any time the actual circumstances to serve its purpose. This definition requires the capability both to react to the actual circumstances and to control these reactions in order to fulfil the goals. The reactiveness is achieved by a set of behaviors. The directedness is achieved by a cognitive layer structuring and exploiting the system history. A distributed architecture of such an autonomous system is presented and discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>