B. Chandrasekaran: “An Architecture for Diagrammatic Representation and Reasoning”

September 28, 2006 | Laboratory for AI Research, Ohio State University, Columbus, OH

Speaker: B. Chandrasekaran

An Architecture for Diagrammatic Representation and Reasoning B. Chandrasekaran Laboratory for AI Research The Ohio State University Columbus, OH Though AI and cognitive science almost exclusively focus on predicate-symbolic representation as the medium of the “Language of Thought,” perceptual representations are a significant component of cognitive states. Diagrammatic representations are especially common inproblem solving. In this talk, I describe a bi-modal architecture for problem solving, in which diagrams and predicate symbolic representations are co-equal representational modes. Problem solving proceeds opportunistically – whichever modality can solve a subgoal makes its contribution at each cycle. A set of perceptual routines recognize emergent objects and evaluate a set of generic spatial relations between objects in a diagram; and a set of action routines create or modify the diagram in the service of problem solving goals. I describe application of the architecture to problems in Army situation understanding and planning.While the work described is potentially useful as technology, it also has implications for cognitive architecture. Perceptual and kinesthetic representations play a deeper role in thinking than the traditional roles assigned to perception as getting information from the world, andto action as executing decisions. The work on diagrammatic representations suggests what a more fully developed multi-modal cognitive architecture would look like.Biography B. Chandrasekaran is Professor Emeritus Computer Science and Engineering and Director of the Laboratory of Artificial Intelligence Research in the Department of Computer Science and Engineering at The Ohio State University. He is a Fellow of the Institute of Electrical and Electronic Engineers, Association for Computing Machinery and American Association for Artificial Intelligence. His major research activities are in diagrammatic reasoning, causal understanding, knowledge systems,decision support architectures and cognitive architectures. He and David Brown authored “Design Problem Solving,” (Morgan Kaufmann), and he is co-editor of Diagrammatic Reasoning: Cognitive and Computational Perspectives (MIT Press). Chandrasekaran was Editor-in-Chief of IEEEExpert/Intelligent Systems from 1990 to 1994. He is currently a technical leader in an ARL-supported Government-Industry-University Collaborative Technology Alliance on Advanced Decision Architectures.