UC San Diego

Developing a model of the force distributions of an adversary has become an urgent need for military personnel, particularly in today's urban environment. In this thesis, we present and discuss the estimation of the adversarial strength and location using UAV-reconnaissance data from a simulated terrain. We will apply a stochastic model to our estimator and compare our results to our true data. We implement our model, obtain an error bound for our estimator, present several examples of observation-based estimator in conjunction with an urban combat simulator, and analyze the effects that our input parameters have on our resulting estimator