Decision Support Planners for Military Operations

Planning under uncertainty is a research subject that has attracted big attention in the past few years. A planner that operates under uncertainty must take into consideration that actions may have several different outcomes, some of which may be more desirable than others. The first developed decision support planners (DSP), use conventional Operations Research (OR) tools such as decision theory for developing Courses of Actions (COAs). Besides the conventional planning methods, other planning methods based on more sophisticated OR techniques such as the Markov Decision Processes (MDP) and Partially Observable Markov Decision Processes (POMDP) have been considered recently as promising approaches to use in developing decision support planners. The OR oriented planners, which can be considered for planning military operations, will be classified into three categories: i) conventional planners (based on replanning), ii) planners using the MDP paradigm, and iii) planners using POMDP. It will be shown in this paper the superiority of the solution of the MDP based planner over the conventional planner based on replanning. However, the solution to the POMDP based planner cannot be compared to the conventional or the MDP solutions planners. POMDP planner deals with another type of problems where the state of the system is not well known.