Possessing a sufficient level of situation awareness is essential for effective decision making in dynamic environments. In video games, this includes being aware to some extent of the intentions of the opponents. Such high-level awareness hinges upon inferences over the lower-level situation awareness provided by the game state. Traditional plan recognizers are completely passive processes that leave all the initiative to the observed agent. In a situation where the opponent's intentions are unclear, the observer is forced to wait until further observations of the opponent's actions are made to disambiguate the pending goal hypotheses. With the plan recognizer we propose, in contrast, the observer would take the initiative and provoke the opponent, with the expectation that his reaction will give cues as to what his true intentions actually are.

This paper discusses the application of holonic control paradigm to sensor management in military surveillance operations. Sensor management is described both as part of the data fusion process and as a control problem. The choice of holonic control as the most adequate architecture for sensor management in the military environment is explained and its application to surveillance operations illustrated. Holonic control is then simulated using a littoral surveillance scenario to test sensor management with and without feedback from high-level fusion (closed-loop versus open-loop). The results show that closed-loop sensor management significantly enhances global surveillance performance, reduces detection time of threatening objects, and reduces platforms' load, thus increasing stealth and decreasing detectability.