A central problem in qualitative reasoning is understanding how people reason about space and shape with diagrams. We claim that progress in diagrammatic reasoning is being slowed by two problems: (1) Researchers tend to start from scratch, creating new spatial reasoners for each new problem area that they tackle, and (2) constraints from human visual processing are rarely considered. This paper describes GeoRep, a spatial reasoning engine that generates qualitative spatial descriptions from line drawings. GeoRep has been successfully used in several research projects, including cognitive simulation studies, which suggests that our approach can overcome these problems. This paper outlines the architecture of GeoRep, explaining the domainindependent and domain-specific aspects of its processing and the motivations for the representations it produces. How GeoRep has been used in three different projects
Ronald W. Ferguson, Kenneth D. Forbus