Date of Original Version
Abstract or Description
Long range navigation by unmanned ground ve- hicles continues to challenge the robotics community. Efﬁcient navigation requires not only intelligent on-board perception and planning systems, but also the effective use of prior knowledge of the vehicle’s environment. This paper describes a system for supporting unmanned ground vehicle navigation through the use of heterogeneous overhead data. Semantic information is obtained through supervised classiﬁcation, and vehicle mobility is predicted from available geometric data. This approach is demonstrated and validated through over 50 kilometers of autonomous traversal through complex natural environments.