The project RASCALLI aims at the development of responsive artificial situated cognitive agents that live and learn on the Internet (Rascalli). Rascalli represent a growing class of cooperative agents that do not have a physical presence, but nevertheless are equipped with major ingredients of cognition including situated correlates of physical embodiment to become adaptive, cooperative and self improving in a certain environment (Internet) given certain tasks.
Their task-based processing of Web content requires an action-based model of interpretative perception. Because of the size and importance of their memory, special attention is paid to the associative structuring of the acquired information based on interests and experience, and to models of an active, permanently structure-creating and restructuring memory. With Rascalli we aim at artificial agents that are able to combine human and computer skills in such a way that both kinds of abilities can be optimally employed for the benefit of the human user.
We develop and implement a system that integrates a cognitive model and architecture with modules such as digital memory, knowledge representation and special purpose components as realized in question-answering systems and music search engines. The system allows a user to create a digital presence functioning like an avatar or agent that lives in the Internet and can be instructed by the user to collect information on certain user defined topics, to engage on behalf of the user in Web communities, to establish contact with other digital presences, avatars and users, etc. In the human-computer interface, Rascalli appear as embodied conversational characters.
The feasibility of the approach is demonstrated via two application scenarios: a scenario where users train their Rascalli to successfully compete in a quiz game, and a scenario where Rascalli assist the human user in gathering and organizing information related to music.
Funding SchemeSTREP - Specific Targeted Research Project