First Results in Terrain Mapping for a Roving Planetary Explorer

To perform planetary exploration without human supervision, a complete autonomous rover must be able to model its environment while exploring its surroundings. We present a new algorithm to construct a geometric terrain representation from a single range image. The form of the representation is an elevation map that includes uncertainty, unknown areas, and local features. By virtue of working in spherical-polar space, the algorithm is independent of the desired map resolution and the orientation of the sensor, unlike other algorithms that work in Cartesian space. We also describe new methods to evaluate regions of the constructed elevation maps to support legged locomotion over rough terrain.