Generating Situation Awareness for Time Critical Decision Making

摘要

The quality of situation awareness directly affects the decision making process for human soldiers in Military Operations on Urban Terrain (MOUT). It is important to accurately model situation awareness to generate realistic tactical behaviors for the non-player characters (also known as bots) in MOUT simulations. This is a very challenging problem due to the time constraints and the heterogeneous cue types in MOUT. Although there are some theoretical models on situation awareness, they generally do not provide computational mechanisms suitable for MOUT simulations. In this paper, we propose a computational model of situation awareness for the bots in MOUT simulations. The model forms up situation awareness quickly with key cues. It is also designed to work with some novel features. They include case-based reasoning, qualitative spatial representation and expectations. The effectiveness of the computational model is assessed with Twilight City, a virtual environment that we have built for MOUT simulations.