Building and Navigating Maps of Road Scenes Using Active Range and Reflectance Data

Abstract

This paper presents algorithms for building maps of road scenes using an active range and reflectance sensor and for using the maps to traverse a portion of the world already explored. Using an active sensor has some attractive advantages: It is independent of the illumination conditions, it does not require complex calibration in order to transform observed features to the vehicle’s reference frame, and it provides 3-D terrain models as well as road models. Using the map built from sensor data facilitates navigation in two respects: The vehicle may navigate faster since less perception processing is necessary, and the vehicle may follow a more accurate path since the navigation system does not rely entirely upon inaccurate visual data. We present a complete system that includes road following, map building, and map-based navigation using the ERIM laser range finder. We report on experimentation of the system both on the CMU NAVLAB and the Martin Marietta ALV.