A Customizable Tactical Engine for Mission Planning with Probabilistic Inference

Military mission planning is a cognitively demanding process carried out in uncertain and dynamic environments. Current simulators and decision support tools often fail to keep pace with changing battlefield conditions, as their tactical logic is fixed and difficult to adapt when new insights emerge. This creates a gap between the expertise of planners and the rigid models embedded in existing systems. This gap is addressed with an integrated framework that combines a configurable Bayesian Belief Network (BBN), a mission simulator with terrain-informed routing, and an interactive map-based interface. In this framework, users can both explore alternative plans and operational conditions in the simulator and directly modify the BBN logic that governs outcome probabilities. Experiments show that changing assumptions or logic leads to observable and explainable differences in predicted outcomes and their visualization, demonstrating how the system captures and presents uncertainty as plans unfold. These results highlight the feasibility of user-configurable decision support based on probabilistic reasoning and simulation, offering a step toward tools that more directly reflect expert knowledge and support operational analysis.