A 3D laser scanner system for autonomous vehicle navigation

Abstract

Road segmentation, obstacle detection, situation awareness constitute fundamental tasks for autonomous vehicles in urban environments. This paper describes an end-to-end system capable of generating high-quality 3D point clouds from one or two of the popular LMS200 laser on a continuously moving vehicle. Road segmentation and crossing analysis have been performed on the basis of this newly developed 3D laser scanner. This system is cost-efficient and provides a circumferential view that makes it also applicable to mid-sized robotic platforms, like Volksbot robots. Field experiments from the DARPA Urban Challenge are presented. Our aim is to provide a level of hardware and algorithmic detail suitable for replication of our system by interested parties or to get a cheap 3D laser scanner for research for those who do not wish to invest in hardware development.