DEDAL

The goal of DEDAL is to facilitate the reuse of engineering design experience by providing an intelligent guide for browsing multimedia design documents.

Based on protocol analysis of design activities, DEDAL defines a language to describe the content and form of technical documents for mechanical design. This language is used to index pages containing text and graphics, meeting reports and transcripts of conversation among designers. DEDAL uses concepts from a model of the designed artifact to index and query design documents and also a set of heuristics that reason from the model to "guess" where the answers to a question may be documented when the retrieval fails. DEDAL is a compromise between domain-independent argumentation-based systems and pure model-based systems which assume a complete formalization of all design documents.

Current Work

We are currently focusing in two directions. One thrust is in improving the intelligence of the system and are currently working on applying machine learning techniques in order for DEDAL to automatically analyze the success/failure of retrieved documents and automatically modify the indexes on the basis of this analysis. The other effort is to provide an integrated environment for the designer in order to facilitate interactive domain model definition/modification and index acquisition.

Publications

  1. Baya, V.; Gevins, J.; Baudin, C.; Mabogunje, A.; Toye, G.; Leifer, L.; "An Experimental Study of Design Information Reuse" , In Proceedings of the 4th International Conference on Design Theory and Methodology, ASME, Sept. 13-16, Scottsdale, Arizona, pp 141-147, 1992.

  2. Baudin, Catherine; Kedar, Smadar; Underwood, Jody G.; Baya, Vinod; "Question-based Acquisition of Conceptual Indices for Multimedia Design Documentation" , In proceedings of the 11th National Conference on Artificial Intelligence AAAI-93, Washington D.C., pp 452-458, July 1993.

  3. Baudin, Catherine; Underwood, Jody G.; Baya, Vinod; "Using Device Models to Facilitate the Retrieval of Multimedia Design Information" , In proceedings of the 13th International Joint Conference on Artificial Intelligence, Chambery, France, pp 1237-1243, August 29-September 2,1993.

  4. Baudin, Catherine; Underwood, Jody G.; Baya, Vinod; Mabogunje, Ade; "Dedal: Using Domain Concepts to Index Engineering Design Information" , In proceedings of the Fourteenth Annual Conference of the Cognitive Science Society, Bloomington, Indiana, pp 702-707, July 19-August 1, 1992.

  5. Mabogunje, A., "Harnessing Questions in Mechanical Design", Engineer Thesis, Stanford University, Stanford, California, July 1993.