Cognitive, collaborative, conceptual and creative — Four characteristics of the next generation of knowledge-based CAD systems: A study in biologically inspired design
Highlights
► Biologically inspired design uses analogies to biological systems. ► In SBF models, functions act as indices to knowledge of structure and behaviors. ► We deployed DANE in a course on biologically inspired design. ► DANE’s SBF models could be useful for conceptualizing biological systems. ► The value of SBF models may lie in enabling designers to organize their knowledge.
Section snippets
Next generation CAD systems
Computer-aided design (CAD) encompasses a broad area of scholarship focused on supporting design processes that shift and adapt even as the underlying computational technology is evolving. Given the challenge of defining the next generation of CAD, we prefer to focus on intelligent CAD, i.e., CAD that develops and deploys artificial intelligence (AI) techniques. In particular, we want to focus on knowledge-based CAD that investigates the content, representation, organization, access, use,
Cognitive studies of biologically inspired design
Biologically inspired design, also sometimes referred to as biomimicry or bionics, is a design paradigm that uses analogies to biological systems to suggest creative design ideas for difficult engineering problems [109], [110]. The paradigm attempts to leverage the billions of design solutions already existing in nature by exposing engineers to the biological world. Examples of biologically inspired designs range from bio-inspired clothing to biomimetic robots [111], [112]. One specific example
From cognitive studies to design of CAD tools
From the observations made in our in situ cognitive studies, we abstracted functional requirements for a knowledge-based CAD tool called DANE for supporting the process of biologically inspired design. We then designed features for the software tool iteratively to meet these functional requirements. For example, we used variations of Structure-Behavior-Function models [45], [46], [47] to represent knowledge of biological systems. As is always the case, there are many more functional
Functional modeling of biological systems
To represent functional models of biological and technological systems in our prototype CAD software, DANE, we used the Structure-Behavior-Function (SBF) knowledge representation scheme [45], [46], [47]. Briefly, (1) the structure portion of an SBF model of a complex system specifies the “what” of the system, namely, the components of the system as well as the connections among them. (2) Behaviors specify the “how” of the complex system, namely, the causal processes or mechanisms occurring in
Design and development of DANE
In this section we describe our prototype CAD technology. Not only is DANE designed to address the issues our cognitive studies identified in biologically inspired design, but it is also represents our first attempt at building a next generation CAD system. As the name implies, the Design by Analogy to Nature Engine (DANE) is intended in the long term to be a semi-automated engine for design. However, at present, DANE interactively facilitates biologically inspired design by (1) helping
Deployment and assessment of DANE
We deployed DANE in the Fall 2009 semester session of the project-based, senior-level, undergraduate ME/ISyE/MSE/PTFe/BIOL 4740 course on biologically inspired design taught by Georgia Institute of Technology’s Center for Biologically Inspired Design. Although student teams were offered extra credit for adding a model to DANE, we did not connect the software with any specific learning objective. Our goal was exploratory: how, if at all, would teams integrate our CAD system into their design
DANE as a case study in the 4C’s of next generation CAD systems
We presented in this paper a knowledge-based CAD system called DANE for functional modeling of biological systems in the context of biologically inspired design. The design literature describes a small but increasing number of interactive computational tools for supporting biologically inspired design (e.g., [132], [133], [134], [135], [136], [137]). The Biomimicry Institute [132], for example, has developed an online web portal called AskNature for accessing a functionally-indexed database of
Acknowledgements
We are grateful to Professor Jeannette Yen, Director of Georgia Tech’s Center for Biologically Inspired Design (www.cbid.gatech.edu), for her strong support and encouragement for this work. Yen also coordinated the ME/ISyE/MSE/PTFe/BIOL 4740 class in Fall 2006, Fall 2007, Fall 2008 and Fall 2009, when we conducted our cognitive studies of design teams engaged in biologically inspired design. We developed the interactive knowledge-based design tool DANE during 2008–09, where the design of DANE
Ashok K. Goel is an Associate Professor of Computer Science & Cognitive Science in the School of Interactive Computing at the Georgia Institute of Technology. He is Director of the School’s Design & Intelligence Laboratory, and a Co-Director of Georgia Tech’s Center for Biologically Inspired Design. He is an Associate Editor of IEEE Intelligent Systems and ASME Journal of Computing and Information Science in Engineering. His research has been supported by NSF, DARPA, ONR, DHS and IES, and he
References (137)
R1: a rule-based configurer of computer systems
Artificial Intelligence
(1982)- et al.
Automated reuse of design plans
Artificial Intelligence in Engineering
(1989) - et al.
Assembly sequence planning using case-based reasoning techniques
Knowledge-Based Systems
(1991) - et al.
CADRE: case-based geometric design
Artificial Intelligence in Engineering
(1996) - et al.
Use of design patterns in analogy-based design
Advanced Engineering Informatics
(2004) Functional representations and causal processes
- et al.
Functional modeling for enabling adaptive design of devices for new environments
Artificial Intelligence in Engineering
(1998) - et al.
Drawing on the back of an envelope: a framework for interacting with application programs by freehand drawing
Computers & Graphics
(2000) - et al.
Generating multiple new designs from a sketch
Artificial Intelligence
(1998) - et al.
A computational model of visual analogies in design
Journal of Cognitive Systems Research
(2009)
Two functions of analogical reasoning in design: a cognitive-psychology approach
Design Studies
Towards understanding and supporting creativity: analogies in a constrained cognitive environment
Knowledge-Based Systems
Expertise and the use of visual analogy: implications for design education
Design Studies
The nature and nurture of design ability
Design Studies
An approach to the analysis of design protocols
Design Studies
The structure of design problem spaces
Cognitive Science
On visual design thinking: the vis. kids of architecture
Design Studies
Design fixation
Design Studies
Design by re-representation: a model of visual reasoning in design
Design Studies
Metrics for measuring ideation effectiveness
Design Studies
Macroscopic analysis of design processes based on a scheme for coding designers’ cognitive actions
Design Studies
What do architects and students perceive in their design sketches? A protocol analysis
Design Studies
More or less following a plan during design: opportunistic deviations in specification
International Journal of Man-Machine Studies
Collaborative design: what is it?
Automation in Construction
An overview of knowledge-based configuration
AI Communications
Circuit design as problem solving
Design problem solving: knowledge structures and control strategies
PRIDE: an expert system for the design of paper handling systems
IEEE Computer
VT: an expert elevator designer that uses knowledge-based backtracking
AI Magazine
R1 (XCON) at age 12: lessons from an elementary school achiever
Artificial Intelligence
A review of mechanical engineering design—I
Research in Engineering Design
A review of mechanical engineering design—II
Research in Engineering Design
Artificial intelligence in engineering design
Engineering design: a synthesis of views
Case-based decision support: a case study in architectural design
IEEE Expert
Argo: a system for design by analogy
IEEE Expert, Fall
AskJef: integration of case-based and multimedia technologies for interface design support
CADET: a case-based synthesis tool for engineering design
International Journal of Expert Systems
Case-based reasoning in design
Case-based reasoning in CYCLOPS, a design problem solver
Hierarchical case-based reasoning: integrating case-based and decompositional problem-solving techniques for plant-control software design
IEEE Transactions on Knowledge and Data Engineering
Reasoning with complex cases
Cited by (208)
Challenges in topology optimization for hybrid additive–subtractive manufacturing: A review
2023, CAD Computer Aided DesignSemantic models of sound-driven design: Designing with listening in mind
2022, Design StudiesKnowledge graph construction for product designs from large CAD model repositories
2022, Advanced Engineering InformaticsFree-text inspiration search for systematic bio-inspiration support of engineering design
2023, Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM
Ashok K. Goel is an Associate Professor of Computer Science & Cognitive Science in the School of Interactive Computing at the Georgia Institute of Technology. He is Director of the School’s Design & Intelligence Laboratory, and a Co-Director of Georgia Tech’s Center for Biologically Inspired Design. He is an Associate Editor of IEEE Intelligent Systems and ASME Journal of Computing and Information Science in Engineering. His research has been supported by NSF, DARPA, ONR, DHS and IES, and he has been a technical consultant to NEC and NCR.
Swaroop Vattam is a candidate for Ph.D. in Computer Science at the Georgia Institute of Technology. He works in the Design & Intelligence Laboratory in the School of Interactive Computing, where he is investigating analogical reasoning and creativity in the context of biologically inspired design. His forthcoming Ph.D. thesis investigates mediated analogy, i.e., analogical problem-solving mediated by external information environments.
Bryan Wiltgen is a Ph.D. student in Computer Science at the Georgia Institute of Technology. He does research in the Design & Intelligence Laboratory in the School of Interactive Computing, studying creativity, analogical reasoning, and cognition in natural and social settings, such as biologically inspired design.
Michael Helms is a Ph.D. student in Computer Science at the Georgia Institute of Technology working in the Design & Intelligence Laboratory in the School of Interactive Computing. He has been an instructor in Biologically Inspired Design at Georgia Tech and at NASA, and is the graduate student coordinator at the Center for Biologically Inspired Design at Georgia Tech. Previous to his Ph.D. work, Michael worked as a business consultant with Teradata as well as holding various marketing and strategic planning positions with Zurich Financial Group.