Automatic map creation for environment modelling in robotic simulators

Abstract

This paper presents an approach to automatically create polygonal maps for environment modeling in simulators based on 3D point cloud data gathered from 3D sensors like laser scanners or RGB-D cameras. The input point clouds are polygonalized using a modified Marching Cubes algorithm and optimized using a pipeline of mesh reduction and filtering steps. Optionally color information from the point clouds can be used to generate textures for the reconstructed geometry. © ECMS Webjøm Rekdalsbakken.