Abstract
A key challenge in autonomous planetary surface exploration is the extraction of meaningful information from sensor data, which would allow a good interpretation of the nearby terrain, and a reasonable assessment of more distant areas. In the last decade, the desire to increase the autonomy of unmanned ground vehicles (UGVs), particularly in terms of off-road navigation, has significantly increased the interest in the field of automated terrain classification. Although the field is relatively new, its advances and goals are scattered across different robotic platforms and applications. The objective of this paper is to present a survey of the field from a planetary exploration perspective, bringing together the underlying techniques, existing approaches and relevant applications under a common framework. The aim is to provide a comprehensive overview to the newcomer in the field, and a structured reference for the practitioners.