FIPM - ein operationales Interaktions- und Prozessmodell für Spielgeschehen im Fußball
Final Report Abstract
One of the key problems in the study of multi-agent systems in which the agents exhibit continuous behavior is the automatic recognition and analysis of intentional activities based on observable behavior. Such an analysis requires software systems to structure motions in episodes that are meaningful in the application domains, to acquire and maintain models of the activities, and to use such models to reason about multi-agent system behavior. In the FIPM project we have studied the acquisition of episodes and motion models for football games. We showed that these models allow for the realization of impressive application systems including interactive football TV agent systems that assist coaches in analyzing their teams. The extensible software system that was developed in this project was designed to represent human activities hierarchically in several abstraction layers. Due to the successful interpretation of this system is also applied to the intelligent kitchen project of the CoTeSys cluster. The human activity models in each abstraction layer are automatically built from the models of the lower layers, as described later in this section.
