Biologically Inspired Design: A New Paradigm For AI Research On Computational Sustainability?
Biologically Inspired Design: A New Paradigm For AI Research On Computational Sustainability?
Biologically Inspired Design: A New Paradigm For AI Research On Computational Sustainability?
Abstract
Much AI research on computational sustainability has
focused on monitoring, modeling, analysis, and
optimization of existing systems and processes. In this
article, we present another exciting and promising paradigm
for AI research on computational sustainability that
emphasizes design of new systems and processes, and, in
particular, on biologically inspired design. We first
characterize biologically inspired design, then examine its
relationship with environmental sustainability, next present
a computational model of the process of biologically
inspired design, and finally describe a few computational
systems for supporting biologically inspired design practice.
49
<-#%#7-0+%
8.+%#7*&6
;&&:
!"#$%&'(
)#"'*%+,-#.
!"#$%&'(
3&4#"'*%+,-#.
<-#%#7-0+%
8.+%#7*&6
/#.0&1,
2&.&"+,-#.
5&6-7.(
8.+%96-6
/#.0&1,*+%(
5&6-7.
3&:&6-7.
<-#%#7-0+%
8.+%#7*&6
<-#%#7-0+%
8.+%#7*&6
Figure 2: A data flow diagram for a simplified version of the general process of preliminary design: ovals depict
functions, rectangles depict inputs and outputs, and parallel horizontal lines denote data sources. The process starts with
a need and results in one or more conceptual designs. It consists of the functions of problem formulation, concept
generation and design analysis. Generation of a design concept may lead to problem reformulation and design analysis
may lead to redesign. As indicated by the data sources in blue, biological analogies are useful for several functions in
biologically inspired design including concept generation, design analysis, redesign and problem reformulation.
50
!"#$%&'(
@1&0-4-0+,-#.
=.#>%&:7&(
80?*-6-,-#.
A.,&"+0,-B&
3&,"-&B+%
E.%-.&F(
5-7-,+%
G-$"+"-&6
@96,&'
C.:&"6,+.:-.7
!+,,&".(
8$6,"+0,-#.
H#:&%-.7F
@-'*%+,-#.
A.4#"'+,-#.(
3&,"-&B+%
!+,,&".(
D"+.64&"
G&+".-.7
5&6-7.
/#.0&1,
!"#$%&'
@#%B-.7
Figure 3: A data flow diagram of the process of problem-driven concept generation in biologically inspired design.
The process consists of interactive retrieval of biological analogues online, understanding the biological systems,
abstracting design patterns, and transferring the patterns to the given design problem. The design process is iterative. The
red boxes denote some of the roles AI can play in systematizing the design process and the biological knowledge.
technologies for water desalination are inefficient and
costly. Yet, if we search for water desalination in, say,
Google, then although we get a few million hits, all the
millions of hits appear to refer to current technologies. This
is a missed opportunity because there are a large number of
biological organisms that perform water desalination quite
efficiently, e.g., some kinds of desert plants, snails and
mice. Nature provides the worlds largest library of
sustainable designs for many design problems. Thus, we
want to build digital libraries of natures design as well as
design a new generation of search engines that enable
access to natures designs online.
To help designers address scenarios such as the two
described above, AskNature provides interactive access to
a functionally indexed digital library of high-level design
strategies (Deldin & Schuknecht 2014; Biomimicry 3.8
Institute 2008; http://www.asknature.org/). Idea-Inspire
(Chakrabarti et al. 2005) and DANE (Goel et al. 2012;
http://dilab.cc.gatech.edu/dane/) provide interactive access
to digital libraries of functional models of biological and
technological systems. Shu (2010) describes a natural
language technique for accessing biology articles relevant
to a design problem from a database. Nagle (2014) presents
an engineering-to-biology thesaurus for mapping functions
in engineering to functions in biology. Vattam & Goel
(2013) describe Biologue that is both an interactive tool for
collaborative semantic annotation of biology articles and a
search engine for semantically annotated biology articles
relevant to a design problem from a knowledgebase as
illustrated in Figure 4. DSL is a digital library of the 78
case studies we described earlier (Goel et a. 2014).
Conclusions
As our analysis of teaching and learning of biologically
inspired design indicated, much of biologically inspired
design is motivated by environmental sustainability. A new
case study of biological inspired design that led to an
51
Figure 4: A screenshot from Biologue (Vattam & Goel 2013). The main window, (a), shows a listing of biology
articles in a database. The two side windows, (b) and (c), illustrate the semantic annotations on a biology articles that
express the function and the causal process of the biological system described in the article, respectively. Biologue
uses the semantic annotations to access biology articles relevant to a design problem.
Acknowledgements
52
References
Lepora, N., Verschure, P., & Prescott, T. (2013) The state of the
art in biomimetics. Bioinspiration & Biomimetics 8(1).
Baumeister, D., Tocke, R., Dwyer, J., Ritter, S., & Benyus, J.
(2012) Biomimicry Resource Handbook. Biomimicry 3.8,
Missoula, MT, USA.
Fish, F., Weber, P., Murray, M., & Howles, L. (2011) The
Tubercles of Humpback Whale Fillers: Application of
Bioinspired Technology. Integrative and Comparative Biology
51(1): 203-213.
53