Satisfying multiple rated-constraints in a knowledge based decision aid
Michael R. Benjamin, T. Viana, K. Corbett, A. Silva · 2002
The Maneuver Decision Aid (MDA) is a knowledge-based planner currently being developed at the US Naval Undersea Warfare Center. the goal of MDA is to generate an optimal next-maneuver recommendation, to support the submarine commander's decision making process which includes absorbing an extensive amount of complex information in the short time interval between maneuvers. The model for the maneuver generation process decomposes into three main parts: situation assessment, goal formulation, and constraint satisfaction. It is essential for an automated reasoning system in this domain to consider all factors and concerns in a given situation to put forth its best recommendation. A key aspect of this model is that all identified situation goals and constraints are represented and combined according to their varying degrees of importance. The authors describe how constraint ratings are evaluated and combined within an object-oriented blackboard framework. The focus is on how rated-constraints are formed, represented, and combined to provide optimal solutions.>