Knowledge-based interpretation of architectural drawings

Abstract

Architectural schematic drawings have been used to communicate building designs for centuries. The symbolic language used in these drawings efficiently represents much of the intricacy of the building process (e.g. implied business relationships, common building practice, and properties of construction materials). The drawing language is an accepted standard representation for building design, something that modern data languages have failed to achieve. In fact, the lack of an accepted standard electronic representation has hampered efforts at computer intergration and perhaps worsened industry fragmentation. In general, drawings must be interpreted, by a professional, and then reentered in order to transfer them from one CAD system to another. This work develops a method for machine interpretation of architectural (or other) schematic drawings. The central problem is to build an efficient drawing parser (i.e. a program that identifies the semantic entitites, characteristics, and relationships that are represented in the drawing). The parser is built from specifications of the drawing grammar and an underlying spatial model. The grammar describes what to look for, and the spatial model enables the parser to find it quickly. Coupled with existing optical recognition technology, this technique enables the use of drawings directly as: (1) a database to drive various AEC applications, (2) a communication protocol to integrate CAD systems, (3) a traditional user interface. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)