Computational Infrastructure for a Self-Aware Agent

Self-awareness is an aspect of consciousness that is highly developed in humans in comparison with other animals. A human being unaware of his or her personal characteristics, of what he or she knows and doesn’t know, can do and cannot do, wants and doesn’t want, has experienced and is experiencing, etc., would surely be difficult to communicate with naturally. Therefore we believe that consciousness plays a crucial role in building artificial dialog agents with human-level abilities. In this work we describe our effort in building the extension of the COMA/Epilog system, called Epi2Me/Epilog2 aimed at explicit self-awareness. A system is explicitly self-aware if it has a complex self-model, is transparent in its internal workings and explicitly displays self-awareness through its interaction with the users. The new system achieves a more than 100% improvement over the previous version of Epilog in reasoning speed on traditional first-order logic problems, providing at the same time more extensive support for the requirements of explicit self-awareness, including many of the introspective and metareasoning capabilities needed for explicit self-awareness. In addition its design will provide a solid base on which to build future developments.