Scheduling multiple uninhabited aerial vehicles for target classification by single human operator

We address the problem of a single human operator in charge of monitoring multiple uninhabited aerial vehicles in a reconnaissance mission. The human operator must classify targets as they appear on video feeds from the various aircraft as friends or foes.We introduce the idea of the human monitoring a single screen and a decision aid that automatically selects the video feed to be displayed on that screen, thereby relieving the human of the cognitive burden that comes from having to choose which video feed to look at. In this setting and given that the location of the targets is unknown and the target classification must be performed in real time, the challenge addressed is the development of a scheduling strategy that selects the video feeds presented to the operator in such a way that no target is missed and all targets are looked at for a specified amount of time. We present a Linear Program formulation to this problem for the simple case of two uninhabited aerial vehicles and two equidistant targets. We develop an online algorithm that uses this Linear Program as a building block to be applied to the more general case of multiple nonequidistant targets. We further show that by enforcing a minimum distance between the targets of each uninhabited aerial vehicle, we can guarantee that a schedule is always feasible and no targets are missed. Simulation results are presented that support the validity of the proposed strategy and its advantages over simpler approaches.