Facet Classification in 3D polygon Maps for Autonomous Vehicle Localisation

Abstract

Autonomous navigation for vehicles in non-trivial environments requires fast and precise localisation. Autonomous vehicles typically operate in 3D environments and require 6DOF localisation, which is computationally costly. We have developed fast, accurate localisation by constraining the 6DOF search space by physical vehicle limitations, and by the use of Graphics Processing Units (GPU's) to enable the use of dense 3D internal representations of the environment. This paper presents a method of classifying polygons in the 3D map in order to further reduce computational load. Polygons are indexed by spatial location and classified by the angle between the up vector and the polygon normal - with polygons with normals closer to the horizontal plane assumed to have greater localisation utility. Simulation results of polygon classification, comparing computation time and localisation accuracy are presented. Real experiments confirm the simulation studies.