A reflexive navigation algorithm for an autonomous mobile robot

Abstract

A new, reflexive type of navigation for the Leuven intelligent autonomous system (LIAS), implemented in a distributed transputer system, is presented. The mobile robot is meant to travel as fast and as safe as possible in a dynamic, vague or even completely unknown and unstructured factory environment. The navigation system consists of a reactive planning module combined with a low level fuzzy logic avoidance behaviour which enables the robot to move to a goal by only specifying the goal coordinates. A fusion algorithm combines perception information of three different sensors for accurate modelling of the world. The presented navigation method was tested with the real robot and it proved to be useful in real world applications.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>