Title : Modeling Situation-Awareness in Human-Like agents using Mental Models
| Presenter | Rianne van Lambalgen |
| Abstract | Within the field of serious gaming, human-like agents are used to create realistic circumstances that allow for training of real-life situations. As a first necessary step, such an agent should become aware of the current situation in the environment. In this talk I will present a model that allows an agent to select the appropriate observations and combine them into one coherent picture to obtain situation awareness. Also, I will show the model's application in the domain of F-16 fighter pilot training. |
Title : Metadata-driven integration of object-level knowledge.
| Presenter | Szymon Klarman |
| Abstract | Object-level knowledge is the knowledge about an application domain, represented e.g. in the form of OWL ontologies. Metadata is then a formal description of these ontologies, regarding e.g. their provenance or context of applicability. Due to the growing interest in applications based on such a two-level architecture, defining and understanding the possible forms of interaction between the meta- and the object-level constraints is becoming an important research problem. In this talk I will present a formal framework which captures the simplest form of such interaction and discuss our ongoing work on applying it to the problem of provenance-driven selection of mappings for ontology integration. All feedback is highly appreciated. |