Towards a Graphical Cognitive Architecture for Virtual Humans, Intelligent Agents and Robots
- When:
- Friday, March 23, 2012, 11:00 am - 11:00 am
- Where:
- 11th floor large conference room
- Speaker:
- Paul Rosenbloom
- Description:
- Towards a Graphical Cognitive Architecture for Virtual Humans, Intelligent Agents and RobotsA cognitive architecture provides a hypothesis about the fixed structure (and its integration) underlying intelligent behavior, whether in natural or artificial systems. The long-term goal of this effort is quite ambitious. It is to develop a new cognitive architecture, based on the broad yet elegant capabilities of graphical models, that: (1) is highly functional yet theoretically simple and elegant; (2) uniformly and tightly integrates cognition with perception and motor control; (3) enables easy creation of the simplest systems, with smooth growth to the most sophisticated; (4) supports unified modeling of human cognition; and (5) yields effective and robust virtual humans, intelligent agents and robots. Where things currently stand is with the implementation of a nascent architecture supporting varieties of memory, problem solving and decision making; plus some work on mental imagery, and the very beginnings of capabilities in perception, natural language and learning. This talk will discuss the desiderata for the architecture, explain the basics of its operation, and highlight progress on some of these capabilities.Bio:
Paul S. Rosenbloom is a Professor of Computer Science at the University of Southern California (USC) and a Project Leader at USC's Institute for Creative Technologies. He spent twenty years at USC's Information Sciences Institute, including a decade leading new directions and a stint as Deputy Director. Earlier he was an Assistant Professor of Computer Science and Psychology at Stanford University, and a Research Computer Scientist at Carnegie Mellon University. He received his B.S. in Mathematical Sciences (with distinction) from Stanford University and his M.S. and Ph.D. in Computer Science from Carnegie Mellon University. He is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI). Prof. Rosenbloom’s research focuses on cognitive architectures; he was a co-PI of the Soar Project for fifteen years, and is currently developing a new approach based on graphical models. He has also been working to understand the nature and structure of computing as a scientific domain.
