Unmanned Ground Vehicle Navigation Using Aerial Ladar Data

Abstract

In this paper, we investigate the use of overhead high-resolution three-dimensional (3D) data for enhancing the performances of an unmanned ground vehicle (UGV) in vegetated terrains. Data were collected using an airborne laser and provided prior to the robot mission. Through extensive and exhaustive field testing, we demonstrate the significance of such data in two areas: robot localization and global path planning. Absolute localization is achieved by registering 3D local ground ladar data with the global 3D aerial data. The same data are used to compute traversability maps that are used by the path planner. Vegetation is filtered both in the ground data and in the aerial data in order to recover the load bearing surface.