Operator Aided Decision Processes for UAVs in a Stochastic Environment

Abstract

In this chapter, we consider an Intelligence, Surveillance, and Reconnaissance (ISR) scenario where a human operator is tasked to provide feedback regarding the nature of some objects of interest (OOI). The feedback is relayed to the stochastic controller of an unmanned aerial vehicle (UAV), which must determine an appropriate mission plan. A small aerial vehicle (SAV) loiters at a high altitude where it may survey a large territory. An operator decides which objects in the SAV’s field of view are of interest and which are not. Then a team of micro aerial vehicles (MAVs) are assigned individual tours to survey the OOI at a low altitude. As a MAV flies over an OOI, the operator must decide if the OOI has a feature that defines it as a target. The key parameters are the operator’s response and the time taken for the operator to respond. The stochastic controller takes these into account and performs an analysis to compute expected information gain of a revisit. In previous studies automatic target recognition (ATR) was used for making some decisions in the SAV and the MAVs. This chapter investigates the use of human feedback alone for target recognition. Different methods for calculating expected information gain are examined and compared against a maximum operator delay revisit threshold.KeywordsDynamic ProgrammingStochasticISRTask Assignment