A suitable polygonal approximation for laser rangefinder data

Abstract

This paper deals with indoor mobile robot localization using 2D laser rangefinder data. An indoor environment is mainly made of connected or nonconnected planes (e.g., walls, doors and desks). Therefore the laser rangefinder data are a set of points belonging to straight lines. The more suitable preprocessing of those data seems to be a polygonal approximation. However, classical approximation methods are not robust enough to provide a reliable local description. We propose a new method to provide a robust polygonal approximation; it means accurate, reliable and repeatable detection of dominant points, such as angular points or break points. We obtain a set of angular points and break points (e.g., segments) whose detection depends neither on relative sensor location nor on measure noise. We present experimental results that demonstrate successful map building.