Autonomous cross-country navigation is essential for outdoor robots moving about in unstructured environments.Most existing systems use range sensors to determine the shape of the terrain, plan a trajectory that avoids obstacles, and then drive the trajectory Performance has been limited by the range and accuracy of sensors, insufficient vehicle-terrain interaction models, and the availability of high-speed computers. As these elements improve, higher-speed navigation on rougher terrain becomes possible. We have developed a software system for autonomous navigation that provides for greater capability. The perception system supports a large braking distance by fusing multiple range images to build a map of the terrain in front of the vehicle. The system identifies range shadows and interpolates undersampled regions to account for rough terrain effects. The motion planner reduces computational complexity by investigating a minimum number of trajectories. Speeds along the trajectory are set to provide for dynamic stabi1ity The entire system was tested in simulation, and a subset of the capability was demonstrated on a real vehicle. Results to date include a continuous 5.1 kilometer run across moderate terrain with obstacles. This paper begins with the applications, prior work, limitations, and current paradigms for autonomous cross-country navigation, and then describes our contribution to the area.In this paper, we define autonomous cross-country navigation to be the safe traverse of an unmanned vehicle across unstructured terresthal or planetary terrain with little or no human intervention. The purpose of navigation can be the transport of cargo or personnel, the deployment of sensors for measuring the environment, or the delivery and support of tools for engaging the environment. This technology has broad application in a number of scenarios. The first class of applications involves navigation in inaccessible or isolated environments, such as the exploration of Mars. In such environments, the cost and safety issues prohibit on-site human operation. Remote operation is not viable due to long communication delays, and autonomy is essential. Proficiency can be low provided the system is robust. The second class involves navigation in hazardous environments, such as toxic waste site characterization and remediation, search and rescue, reconflaissance, and mining. In these environments, the possibilities for on-site human operation range from undesirable to prohibitive due to safety issues. Remote operation of the vehicle is possible but performance may suffer due to limited sensory feedback to the operator. Robustness is essential, and autonomy is preferred if the system's proficiency exceeds that of the remote operator. The third class involves navigation in commercial environments, such as excavation and construction. In these environments, the on-site human operators are generally highly skilled. Remote operation is of little use, and proficiency and robustness are of utmost importance. Autonomy is viable only if...