Obstacle Detection for Unmanned Ground Vehicles: A Progress Report

Abstract

To detect obstacles during off-road autonomous navigation, unmanned ground vehicles (UGV’s) must sense terrain geometry and composition (ie. terrain type) under day, night, and low-visibility conditions. To sense terrain geometry, we have developed a real-time stereo vision system that uses a Datacube MV-200 and a 68040 CPU board to produce 256 × 45-pixel range images in about 0.6 seconds/frame. To sense terrain type, we are using the same computing hardware with red and near-infrared imagery to classify 256 × 240-pixel images as a rate of 10 frames/second. This paper reviews the rationale behind the choice of these sensors, describes their recent evolution and on-going development, and summarizes their use in demonstrations of autonomous UGV navigation over the past five years. This work has been the first to show that stereo vision can be practical for autonomous UGV navigation, and is now the first to show a real-time terrain classification system with very low computing requirements.