Abstract
A key problem in diagrammatic reasoning is understanding how people reason about qualitative relationships in diagrams. We claim that progress in diagrammatic reasoning is slowed by two problems: (1) researchers tend to start from scratch, creating new spatial reasoners for each new problem area, and (2) constraints from human visual processing are rarely considered. To address these problems, we created 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 of human vision. In this paper, we outline GeoRep's architecture, explain the domain-independent and domain-specific aspects of its processing, and motivate the representations it produces. We then survey how GeoRep has been used in three different projects-a model of symmetry, a model of understanding juxtaposition diagrams of physical situations, and a system for reasoning about military courses of action.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 17th National Conference on Artificial Intelligence and 12fth Conference on Innovative Applications ofArtificial Intelligence, AAAI 2000 |
| Publisher | AAAI Press |
| Pages | 510-516 |
| Number of pages | 7 |
| ISBN (Electronic) | 0262511126, 9780262511124 |
| State | Published - 2000 |
| Event | 17th National Conference on Artificial Intelligence, AAA1 2000 - Austin, United States Duration: Jul 30 2000 → Aug 3 2000 |
Publication series
| Name | Proceedings of the 17th National Conference on Artificial Intelligence and 12th Conference on Innovative Applications of Artificial Intelligence, AAAI 2000 |
|---|
Conference
| Conference | 17th National Conference on Artificial Intelligence, AAA1 2000 |
|---|---|
| Country/Territory | United States |
| City | Austin |
| Period | 7/30/00 → 8/3/00 |
Funding
This research was supported by the Cognitive Science and Computer Science programs of the Office of Naval Research, by the Defense Advanced Research Projects Agency, under the High Performance Knowledge Bases program, and by the National Science Foundation, under the Learning and Intelligent Systems program. Useful feedback and/or assistance was provided by Laura Allender, Jim Donlan, John Everett, George Lee, Yusuf Pisan, Rob Rasch, Bill Turmel, Jeff Usher and three anonymous reviewers.
ASJC Scopus subject areas
- Artificial Intelligence
- Software