Date of Award
Master of Science
Department of Operational Sciences
Matthew J. Robbins, PhD
The United States Air Force is investing in artificial intelligence (AI) to speed analysis in efforts to modernize the use of autonomous unmanned combat aerial vehicles (AUCAVs) in strike coordination and reconnaissance (SCAR) missions. This research examines an AUCAVs ability to execute target strikes and provide reconnaissance in a SCAR mission. An orienteering problem is formulated as anMarkov decision process (MDP) model wherein a single AUCAV must optimize its target route to aid in eliminating time-sensitive targets and collect imagery of requested named areas of interest while evading surface-to-air missile (SAM) battery threats imposed as obstacles. The AUCAV adjusts its route depending on the arrival locations of the SAM batteries and targets into the battle-space. An approximate dynamic programming (ADP) solution approach is developed wherein mathematical programming techniques are utilized with a cost function approximate (CFA) policy to develop high quality AUCAV routing policies to improve SCAR mission performance. The CFA policy is compared to a deterministic repeated orienteering problem (DROP) benchmark policy across four instances that explores varied arrival behaviors of dynamic targets and SAM batteries. Overall, the proposed CFA policies perform nearly the same or better than the DROP policy in all four instances.
DTIC Accession Number
Gurnell, Kassie M., "Approximate Dynamic Programming for an Unmanned Aerial Vehicle Routing Problem with Obstacles and Stochastic Target Arrivals" (2022). Theses and Dissertations. 5343.