EvoArch: An evolutionary algorithm for architectural layout design

The architectural layout design problem, which is concerned with the finding of the best adjacencies between functional spaces among many possible ones under given constraints, can be formulated as a combinatorial optimization problem and can be solved with an Evolutionary Algorithm (EA). We present functional spaces and their adjacencies in form of graphs and propose an EA called EvoArch that works with a graph-encoding scheme. EvoArch encodes topological configuration in the adjacency matrices of the graphs that they represent and its reproduction operators operate on these adjacency matrices. In order to explore the large search space of graph topologies, these reproduction operators are designed to be unbiased so that all nodes in a graph have equal chances of being selected to be swapped or mutated. To evaluate the fitness of a graph, EvoArch makes use of a fitness function that takes into consideration preferences for adjacencies between different functional spaces, budget and other design constraints. By means of different experiments, we show that EvoArch can be a very useful tool for architectural layout design tasks.

[1]  Hsueh-I Lu,et al.  Compact floor-planning via orderly spanning trees , 2003, J. Algorithms.

[2]  Bernard Yannou,et al.  Separating topology and geometry in space planning , 2013, Comput. Aided Des..

[3]  M. Rosenman.  The Generation of Form Using an Evolutionary Approach , 1997 .

[4]  Fay Sudweeks,et al.  Artificial Intelligence in Design ’96 , 1996, Springer Netherlands.

[5]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[6]  A. Lindenmayer.  Mathematical models for cellular interactions in development. I. Filaments with one-sided inputs. , 1968, Journal of theoretical biology.

[7]  Ricardo H. C. Takahashi,et al.  A preliminary comparison of tree encoding schemes for evolutionary algorithms , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.

[8]  Julia Ruch.  Interactive Space Layout: A Graph Theoretical Approach , 1978, 15th Design Automation Conference.

[9]  Frédéric Gruau.  Cellular encoding as a graph grammar , 1993 .

[10]  Peter M. Todd,et al.  Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[11]  John R. Koza,et al.  Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems , 1990 .

[12]  Hitoshi Iba,et al.  Learning polynomial feedforward neural networks by genetic programming and backpropagation , 2003, IEEE Trans. Neural Networks.

[13]  Hiroshi Nagamochi,et al.  A simple recognition of maximal planar graphs , 2004, Inf. Process. Lett..

[14]  Sean Luke,et al.  Two fast tree-creation algorithms for genetic programming , 2000, IEEE Trans. Evol. Comput..

[15]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[16]  Xin Yao,et al.  A Memetic Algorithm for VLSI Floorplanning , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[18]  John R. Koza,et al.  Genetic generation of both the weights and architecture for a neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[19]  Jeremy J. Michalek,et al.  Architectural layout design optimization , 2002 .

[20]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[21]  Gerta Rücker,et al.  Exploring the Limits of Graph Invariant- and Spectrum-Based Discrimination of (Sub)structures , 2002, J. Chem. Inf. Comput. Sci..

[22]  A. Lindenmayer.  Mathematical models for cellular interactions in development. II. Simple and branching filaments with two-sided inputs. , 1968, Journal of theoretical biology.

[23]  John S. Gero,et al.  Evolving design genes in space layout planning problems , 1998, Artif. Intell. Eng..

[24]  O. Wing,et al.  Computer Recognition and Extraction of Planar Graphs from the Incidence Matrix , 1966 .

[25]  Kenneth A. De Jong,et al.  An Analysis of the Interacting Roles of Population Size and Crossover in Genetic Algorithms , 1990, PPSN.

[26]  T. Schnier,et al.  Learning Genetic Representations as Alternative to Hand-Coded Shape Grammars , 1996 .

[27]  D. Parisi,et al.  “Genotypes” for neural networks , 1998 .

[28]  T. Schnier,et al.  Genetic Engineering and Design Problems , 1997 .

[29]  J. Cagan,et al.  An Extended Pattern Search Algorithm for Three-Dimensional Component Layout , 2000 .

[30]  Zbigniew Michalewicz,et al.  Evolutionary Algorithms in Engineering Applications , 1997, Springer Berlin Heidelberg.

[31]  Anees Shaikh,et al.  Destination-Driven Routing for Low-Cost Multicast , 1997, IEEE J. Sel. Areas Commun..

[32]  Li Xiao,et al.  Improving unstructured peer-to-peer systems by adaptive connection establishment , 2005, IEEE Transactions on Computers.

[33]  W. Spears,et al.  On the Virtues of Parameterized Uniform Crossover , 1995 .

[34]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.