As UAV technologies mature and decision and perception approaches become established, there is a need to focus on advanced autonomy to put unmanned systems to work. A key limitation of current systems is the tail-to-tooth ratio: many unmanned systems require multiple operators. Ideally, a single operator should be able to control multiple (heterogeneous) assets. With this in mind, we are working on the notion of force augmentation: providing utility to a force without requiring continuous command and control of the platform. Specifically, we aim to provide utility to a forward tactical force with a quadrotor (i.e., urban operations, etc.).
This initial effort is aimed at demonstrating basic force augmentation by a quadrotor UAV (agile, low-altitude assets): provide utility to a ground force without burdening them with mission/task specification for the UAV (quadrotor, see Figure 1). The UAV is to assist a ground force moving through an urban environment by anticipating information needs (i.e., the information deficit due to occlusions) and then provide a real-time video feed of these identified regions of interest. The quadrotor will adapt its behavior in response to ground force movements. 
Approach:
We are investigating the Dynamic, Persistent Surveillance framework to obtain a flexible, extendable approach to provide utility. This framework captures information gain, and different approaches are being considered (e.g., optimal instantaneous information, optimal complete information, etc.). The utility of interest here is providing visual data of occluded regions. Two approaches are illustrated below: instantaneous information gain, and information gain after some time (5 seconds - this captures the effect of the tactical force's movement and information gain). We can also look at total information gain along the way (though this is more computationally intensive).
