Architecture & Design

AITopics > Applications > AI Applications Areas > Architecture & Design

"The general design process is often characterized as mapping needs to function to structure. It is carried out using many different types of reasoning and many different sources of knowledge. In general, design is the process of specifying a description of an artifact that satisfies a collection of constraints. These constraints may arise from a variety of sources." -David C. Brown

Introductory Readings

An `AI in Design' View of Design. By David C. Brown & Dan L. Grecu. "The goals of this paper are to introduce a selection from the AI in Design literature; to present a perspective of design based on that literature; and to provide a set of questions that can be used for pedagogical purposes to analyse and categorize computational research into design."

Intelligent Computer-Aided Design. By David C. Brown. (September 1998) A very thorough overview with an extensive bibliography.

"What Benefits Can Intelligent Tools Bring to the Construction Industry? Making expert knowledge available throughout your organisation, thus allowing your experts to consider only the complex issues." From AIAI. A nice collection of real world projects.

General Readings

Special issues of IEEE Intelligent Systems & Their Applications:

• Vol. 12, No. 2, March/April 1997: AI in Design - Guest Editors Introduction: Understanding the Nature of Design, David C. Brown and William P. Birmingham; Issues in Multiagent Design Systems, Susan E. Lander; Grammatical Design, Ken Brown; Case-Based Reasoning in Design, Mary Lou Maher and Andres Gomez de Silva Garza; Functional Reasoning in Design, Yasushi Umeda and Tetsuo Tomiyama; Configuration-design problem solving, Bob Wielinga and Guus Schreiber.
• Vol. 12, No. 3, May/June 1997: AI in Design, Ashok K. Goel; The "What" and "How" of Learning in Design, Alex H.B. Duffy; Design Rationale Systems: Understanding the Issues, Jintae Lee; and two articles by Yumi Iwasaki

Smart software makes sense of rough sketches. By Celeste Biever. New Scientist (September 12, 2003). "Intelligent software that brings rough sketches to life in a virtual world is promising to revolutionise the way children learn and to help engineers visualise their designs. ... The MIT software monitors the image as it is being drawn on to a computer screen and allocates probabilities to various interpretations of what it might represent. As the user adds more detail, the software adjusts these weightings. To do this, it uses a technique known as Bayesian analysis, which is normally used to compute the likelihood of specific causes, given certain effects. 'With our software, the 'causes' are what the user had in mind to draw, and the 'effects' are what was actually drawn,' says Randall Davis, who has developed the code with Christine Alvarado at MIT's Artificial Intelligence Laboratory."

• Visit the The Design Rationale Group: "Our approach to rationale capture is inspired by this set of observations and claims that a successful process must be less trouble than it is worth. The key in turn to making it less trouble is to provide natural interaction with design tools. We want designers to be able to sketch, gesture, and talk with the computer about their work in the same way they would with another designer. Our vision is a design environment with intelligence embedded in the environment, allowing designers to work in familiar ways in familiar media (e.g., whiteboards), yet give those media new and powerful capabilities (e.g., the ability to understand a sketch, ask intelligent questions about a design, etc.)."

Automatic Design and Manufacture of Robotic Lifeforms. H. Lipson and J. B. Pollack. 2000. Nature 406, pp. 974-978. "Our central claim is that to realize artificial life, full autonomy must be attained not only at the level of power and behaviour (the goal of robotics today), but also at the levels of design and fabrication. Only then can we expect synthetic creatures to sustain their own evolution. ... The experiments described here use evolutionary computation for design, and additive fabrication for reproduction."

• Care to visit their lab?

Boeing Soars with Digital Design. From Intelligent Manufacturing (December 1996). "The 777 was 100% digitally designed and preassembled on a computer. Digitally defining the 777 parts, plans and tools allowed engineers to detect over 10,000 part interferences in the initial computer modeling. Under the old system, tooling and assembly plans for 2 million separate parts would not be validated until the first airplane began assembly in the plant. ... The technologies and processes utilized for the 777, such as the 3-D solid modeling, digital preassembly and artificial intelligence, are now used to develop the company's next-generation 737 airplane."

Case- and Constraint-Based Project Planning for Apartment Construction. By Kyoung Jun Lee, Hyun Woo Kim, Jae Kyu Lee, and Tae Hwan Kim. AI Magazine 19(1): Spring 1998, 13-24. "To effectively generate a fast and consistent apartment construction project network, Hyundai Engineering and Construction and Korea Advanced Institute of Science and Technology developed a case- and constraint-based project-planning expert system for an apartment domain. The system, FAS-TRAK- APT, is inspired by the use of previous cases by a human expert project planner for planning a new project and the modification of these cases by the project planner using his/her knowledge of domain constraints."

Darwinian Design. Survival of the Fittest Spacecraft - evolving better spacecraft through artificial intelligence. NASA Space Science News (April 7, 1999). "Survival of the fittest, when applied to computer design, is one of the ingredients for artificial intelligence. 'What it boils down to is trying to get computers to recognize patterns and react,' says [David] Noever. 'We treat the designing choices of a mission like a biologist treats a genetic chromosome. We can cut and splice missions together with remarkable speed, compete them against each other, and then multiply the survivors.'"

Real-World Applications of Qualitative Reasoning and Qualitative Reasoning and the Science of Design. By Yumi Iwasaki. Versions of the articles that appeared in a special issue of IEEE Expert: Intelligent Systems (May/June 1997).

Related Resources

AI In Design Webliography. From David C. Brown at the Worcester Polytechnic Institute. "This is a collection of potentially useful sources of information about AI in Design, Knowledge Based Design, Intelligent CAD, Computational Approaches to Design, and Design Theory & Methodology. Included are pointers to projects and research centers (but not to individuals) organized by location. There are also separate sections for announcements, for general information about Engineering Design, for books, for university courses, and for prominent US-based design researchers."

• Don't miss AI in Design Webliography - Courses.

The Association for Computer Aided Architectural Design Research In Asia. "An association of those who teach and conduct research in computer-aided architectural design in schools of architecture throughout Asia. We were established on 26 April 1996 and have members throughout Asia."

EvoCAD, Evolution-Assisted Design, from DEMO [Dynamical & Evolutionary Machine Organization] Department of Computer Science, Volen National Center for Complex Systems, Brandeis University. "We have built a mini-CAD system to design 2D Lego structures. This application allows the user to manipulate Lego structures, and test their gravitational resistance using a simplified structural simulator. It also interfaces to an evolutionary algorithm that combines user-defined goals with simulation to evolve candidate solutions for the design problems. The results of evolution are sent back to the CAD front-end to allow for further re-design until a satisfactory solution is obtained." And the best part is that you can actually try this program online!

Other References Offline

Routine Design for Mechanical Engineering. By Axel Brinkop, Norbert Laudwein, and Rudiger Maasen. AI Magazine 16(1): Spring 1995, 74-85. "During the process of routine design, some design decisions have to be made with uncertainty. By including knowledge from process technology and company experience in the mechanical design, a sufficiently high degree of flexibility is achieved that the system can even assist in difficult design situations. The success of the system can be measured by the increase in the quantity and the quality of the submitted offers."

Automated Capture of Rationale for the Detailed Design Process, K. L. Myers, N. B. Zumel, and P. E. Garcia, SRI International(1999), in Proceedings of the Eleventh National Conference on Innovative Applications of Artificial Intelligence (IAAI-99), AAAI Press, Menlo Park, CA. "The value of comprehensive rationale information for documenting a design has long been recognized. However, detailed rationale is rarely produced in practice because of the substantial time investment required. Efforts to support the acquisition of rationale have focused on languages and tools for structuring the acquisition process, but still require substantial involvement on the part of the designer. This document describes an experimental system, the Rationale Construction Framework (RCF), that acquires rationale information for the detailed design process without disrupting a designer’s normal activities. The underlying approach involves monitoring designer interactions with a commercial CAD tool to produce a rich process history. This history is subsequently structured and interpreted relative to a background theory of design metaphors that enable explanation of certain aspects of the design process. Evaluation of RCF within a robotic arm design case has shown that the system can acquire meaningful rationale information in a time- and cost-effective manner, with minimal disruption to the designer."