vehicles in the Army. Particular emphasis is given to terrain navigation

There is rising interest in autonomous systems for future military environments. Systems that can take mission directives and then plan and conduct the desired mission will deeply involve aspects of machine intelligence for terrain navigation. Can we build such a system? The answer is "Yes, but definitely not today." Explanation of this answer requires reasons why today's technologies will not support autonomous vehicles and rationale for expecting these capabilities in the future. These reasons and rationale are presented by first defining functional requirements for an autonomous vehicle and its subsystems. Then the functional requirements are linked to technologies. The state of todays technologies and those expected in the future are outlined. Planned Army and DARPA programs in semi- autonomous and autonomous vehicles are described and shown to be the basis for future optimism for autonomous vehicles in the Army. Particular emphasis is given to terrain navigation concepts that will be generic for any type of autonomous ground vehicle. The pacing problem for developing autonomous vehicles that can efficiently move to de­ signated locations in the real world in the performance of Army missions will deeply in­ volve .aspects of machine intelligence for terrain navigation. A system must know where it is with respect to its destination, it must have knowledge of the terrain conditions which affect its movement in the area, and it must have the capability tc develop plans for safe and efficient locomotion to its destination. While traveling along the planned route it must be capable of recognizing natural and man-made terrain features which coordinate with the plan. It must know its capabilities and limitations and the state of its operating system. It must be capable of recognizing obstacles and plan detours when necessary. It must be able to anticipate and detect active threats and actions, and plan accordingly for its own offensive/defensive actions. It must have a rationale for recognizing and dealing with real world activities such as operational characteristics of humans and other vehicles. And above all else, it must know when to ask for help in dealing with a problem for which it cannot solve. These autonomous functions can serve as general terrain navigation re­ quirements for our discussion of autonomous vehicles. Can we build a vehicular system that will autonomously perform these functions? The answer is "Yes, but definitely not today." Explanation of this answer requires reasons why today's technologies will not support autonomous vehicles and rationale for expecting these capabilities in the future. The paper presents these reasons and rationale by first defining functional requirements for an autonomous vehicle and its subsystems. Then the functional requirements are linked to technologies, the state of todays technologies and those expected in the future are outlined. Planned Army and DARPA programs in semi- autonomous and autonomous vehicles are outlined and shown to be the basis for optimism for the future of autonomous vehicles in the Army. Particular emphasis is given to terrain navigation concepts that will be generic for any type of autonomous ground vehicle. Definitions The dictionary defines the noun "navigation" as the act or practice of navigating; especially, the science of locating and plotting the course of ships and aircraft. And the verb "navigate" means to steer, or direct, a ship or aircraft. Of course, for our purposes we will substitute "land vehicle" for "ship or aircraft" in these definitions. Thus within the intent of these definitions, terrain navigation for autonomous vehicles must involve the self-location of the route to be traveled and the self-steering along the selected route. For an autonomous military vehicle in a combat area, the system will have added requirements associated with its mission and the enemy that must be satisfied in the