Map building for indoor environment with laser range scanner

Abstract

A method of map building for indoor environment is presented. It is based on adaptive clustering and weighted averaging. Different threshold value is selected to cluster these sampling points at different position. Clustering with variant threshold is more reasonable than it with constant threshold. Line segments are extracted from these sampling points and are used to approximate the shape of environment. Parameters of line segment are computed with a weight vector. Line segments in environmental map are arranged according to their geometric position relation. This type of map is more accurate and more useful for mobile robot navigation. All these techniques have been implemented on our mobile robot ATRVII equipped with 2D laser range scanner SICK.