Stochastic Dynamic rogramming for Uncertainty Handling in UAV Operations

We present strategies for decision making under uncertainty and adversary action modeling for small UAV operations. Uncertainty comes from the stochastic nature of the environment and from incomplete knowledge of adversary actions/behaviors. A stochastic dynamic programming approach is used to optimize (continuous) resource allocation (fuel reserves) in the face of uncertainty. Different scenarios for adversary responses are considered and analyzed in simulation.