Building Object and Terrain Representation for an Autonomous Vehicle

Abstract

This paper presents progress in building environment models for the CMU Navlab, an autonomous vehicle for on-road and cross-country navigation. We present robust object tracking from sequence of range images and building and updating 3-D object representations. Tracking uses object prediction from one image to the next to accurately compute object locations. Object representations are built by merging sets of points from individual images into a single set in an object-centered coordinate frame. The sparse set of points is then segmented into shapes yielding compact and general object representations. The object representation may be used for landmark recognition during a map-based navigation mission.