A Dynamic Bayesian Network and Markov Decision Process for Tactical UAV Decision Making in MUM-T Scenarios

The use of unmanned aerial vehicles (UAVs) has become commonplace in the military domain. They are used together with manned platforms (e.g. a helicopter) to form a tactical team. This concept is called manned-unmanned teaming (MUM - T). During the execution of a mission, pilots continuously assess the current situation and make decisions on how and where to deploy these UAVs. Thereby, the primary influence factor on this decision process is the threat assessment in the current situation. However, in high workload situations or due to the lack of situation awareness, the pilots may fail to deploy the UAVs effectively. In this article, we propose a software agent that performs a threat assessment on a given scenario and generates UAV task proposals to assist the pilots in the decision-making process. We conducted experiments with human operators who use the system in pre-defined scenarios to show that such an agent can be used to make decisions similar to the ones a human operator would make. The results presented in this article show that the system's outcomes on the threat assessment and UAV decisions are in alignment to the human operators' assessment and decision process outcomes in most cases. Finally, we analyze the results obtained from the experiment and outline future work.