Computing floor plan

The main issue we are after here is space layout planning, space layout planning which examine the capability to better utilization of architecture space, this paper will investigate the potentials of evolutionary computation in solving the combinatorial problem of space layout planning; it will focus on the topological level of problems, topological allocation concern with the relationships between two spaces, i.e. the adjacency and proximity between two spaces.

Artificial Intelligence Research, 2012

Floor planning is an important problem in very large scale integrated-circuit (VLSI) design automation domain as it evaluates the performance, size, yield and reliability of ICs. Due to rapid increase in number of components on a chip, floor planning has gained its importance further in determining the quality of the design achieved. In this paper we have devised an approach for placement of modules in a given area with bounding constraints in terms of minimum placement area imposed. We have used Modified Genetic Algorithm (MGA) technique for determining and obtaining an optimal placement using an iterative approach.

Floor Layout Planning Using Artificial Intelligence Technique, 2017

In the era of e-commerce while buying furniture online the customers obviously feel the need for visual representation of the arrangement of their furniture. Even when doing interiors of the house it's difficult to just rely on assumptions about best layouts possible and professional help may become quite expensive. In this project, we make use of Genetic Algorithm (GA) which is an Artificial Intelligence technique to display various optimal arrangements of furniture. The basic idea behind using GA is developing an evolutionary design model. This is done by generating chromosomes for each possible solution and then performing a crossover between them in each generation until an optimum fitness function is reached. Modification in chromosome representation may also be done for better results. The proposed system will generate different layout designs for the furniture keeping in consideration the structure of a master bedroom.

2017

Is it feasible for an algorithm to comprehend the complexity of zone allocation in architectural design? Is it possible to quantify and use traits of existing designs to create new ones? The following thesis explores how existing floorplans can be used to define qualities of spaces and design; as well as how these qualities can help generate future typologies. The objective is to develop a space layout algorithm that understands qualities of spaces such as proportion, area, connectivity, adjacency etc. from existing designs to later apply that knowledge into automatized floorplan generation. This would be achieved by analysing a database of floorplan designs of a particular socioeconomic, cultural, and historic background and then use that knowledge to identify consistent traits which are replicated in automatized generated floorplans. While the majority of previous attempts in computational space layout design have focused on hardcoding rules and qualities defined by a programmer, and then optimize these qualities by a generative algorithm this attempt aims to discover which qualities are consistent in existing floorplans by examining room traits in existing typologies and later on use this information to generate new designs. A method of automatized design that is founded on previous designs may be useful because it can depict many subtle qualities which would be inefficient or impossible to identify manually by a programmer, and furthermore understand more in debt the traits that are intrinsic in a design of a specific context. The results obtained suggest that the designs generated by the algorithm resemble the designs from the databases. Nevertheless, more work could be done to obtain more unique databases.

ACADIA proceedings

This paper proposes a novel design space model that can be used in applications of generative space planning in architecture. The model is based on a novel data structure that allows fast subdivision and merge operations on planar regions in a floor plan. It is controlled by a relatively small set of input parameters and evaluated for performance using a set of congestion metrics, which allows it to be optimized by a metaheuristic such as a genetic algorithm (GA). The paper also presents a set of guidelines and methods for analyzing and visualizing the quality of the model through low-resolution sampling of the design space. The model and analysis methods are demonstrated through an application in the design of an exhibit hall layout. The paper concludes by speculating on the potential of such models to disrupt the architectural profession by allowing designers to break free of common "heuristics" or rules of thumb and explore a wider range of design options than would be possible using traditional methods.

Computer-Aided Design, 2013

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. Highlights • A new hybrid evolutionary computation methodology and mathematical model are presented. • The algorithm is tested in its validation and performance. • The proposed technique generates floor plans to be used in the early architectural design stage.

Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 2014

We present and compare two evolutionary algorithm based methods for rectangular architectural layout generation: dense packing and subdivision algorithms. We analyze the characteristics of the two methods on the basis of three floor plan scenarios. Our analyses include the speed with which solutions are generated, the reliability with which optimal solutions can be found, and the number of different solutions that can be found overall. In a following step, we discuss the methods with respect to their different user interaction capabilities. In addition, we show that each method has the capability to generate more complex L-shaped layouts. Finally, we conclude that neither of the methods is superior but that each of them is suitable for use in distinct application scenarios because of its different properties.

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1998

Existing algorithms for floorplan topology generation by rectangular dualization usually do not consider sizing issues. In this paper, given a rectangularly dualizable adjacency graph and a set of aspect ratios of the modules, a topology which is likely to yield an optimally sized floorplan, is produced first in a top-down fashion by an AI-based search technique with novel heuristic estimates based on size parameters. It is shown that for any rectangular graph, there exists a feasible topology using only either straight or Z-cutlines recursively within a bounding rectangle. The significance of this result is four-fold: 1) considerable acceleration of the heuristic search, 2) topology generation with minimal number of nonslice cores, 3) guaranteed safe routing order without addition of pseudo modules, and 4) design of an efficient bottom-up heuristic for optimal sizing. Experimental results show that this integrated method elegantly solves floorplan optimization problem for general including inherently nonslicible adjacency graphs.

Ain Shams Engineering Journal, 2015

This paper presents a systematic pathway for the floor plan design when given the shape of required floor plan, the list of spaces, the dimensions of each space and the weighted matrix of required adjacencies between the spaces. The first step is to partition the given shape into say k possible rectangles. Then using the given adjacencies, divide the given spaces into k groups. Next is to construct a rectangular block for each group and at last adjoin all rectangular blocks to have the required floor plan. The obtained rectangular blocks are one of the best arrangement of spaces inside a rectangle from the point of view of connectivity.

This work introduces Evolutionary Architectural Space layout Explorer (EASE), a design tool that facilitates the optimization of 3D space layouts. EASE addresses architectural design exploration and the need to attend to many alternatives simultaneously in layout design. For this, we use evolutionary optimization to find a balance between divergent exploration and convergent exploitation. EASE comprises a novel sub-heuristic that constructs valid spatial layouts, a mathematical framework to quantify the satisfaction of constraints, and evolutionary operators to improve alternative layouts' fitness. We test EASE on the design of a library building. We evaluate EASE's performance for different building forms and different evolutionary algorithm parameters. The results suggest that EASE can generate valid layouts, quantify the constraints' degree of satisfaction and find a number of optimal layout solutions. The layouts that EASE generates are intended not as end results but design artifacts that provide insight into the solution space for further exploration.

Applied Sciences, 2021

In this paper, an evolutionary technique is proposed as a method for generating new design solutions for the floor layout problem. The genotypes are represented by the vectors of numerical values of points representing endpoints of room walls. Equivalents of genetic operators for such a representation are proposed. A case study of the design problem of one-story houses is presented from the initial requirements to the best solutions. An evaluation method using requirement-weighted fitness function for evolved plans is also proposed. The obtained results as well as the advantages and issues related to such an approach are also discussed.

Harvard Data Science Review, 2021

This article introduces and comments on some of the techniques currently used by designers to generate automatic building floor plans and spatial configurations in general, with emphasis on machine learning and neural networks models. This is a relatively new tendency in computational design that reflects a growing interest in advanced generative and optimization models by architects and building engineers. The first part of this work contextualizes self-organizing floor plans in architecture and computational design, highlighting their importance and potential for designers as well as software developers. The central part discusses some of the most common techniques with concrete examples, including Neuro Evolution of Augmenting Topologies (NEAT) and Generative Adversarial Networks (GAN). The final section of the article provides some general comments considering pitfalls and possible future developments, as well as speculating on the future of this trend.

Design Computing and Cognition ’10, 2011

The research project presented in this paper deals with the development of a creative evolutionary design methodology for layout problems in architecture and urban planning. To date many optimisation techniques for layout problems have already been developed. The first attempts to automate layout were undertaken back in the early 1960s. Since then, these ideas have been taken forward in various different manifestations, for example shape grammars, CBS, cellular automata and evolutionary approaches. These projects, however, are mostly restricted to very specific fields or neglect the creative, designerly component. Since pure optimisation methods are of little practical use for design purposes, there have been no useful attempts to derive a universally applicable method for computer aided layout design. For this we need to be aware that designing is a process that occurs at different levels and degrees of abstraction. The solution space is explored in the realm between intuition and rationality in a variety of ways. Good solutions can only arise through an intensive and fluid dialogue between the designer and the generating system. The goal of our project is to develop an adaptive design system for layout problems. To this end we examine different approaches to achieving the best possible general applicability of such a system and discuss criteria that are crucial for the development of such systems.

Journal of Civil Engineering and Management, 2003

Knowledge-based tools assisting the designer in engineering represent further improvement of expert systems. The present paper shows how such software can be developed in the particular domain of floor layout design for buildings. The recently developed paradigm of hierarchical graphs is taken as the knowledge representation scheme. The user of the system is encouraged to undertake the search for rational solution at two levels. First, an analysis of functionality requirements for the designed object is performed. This results in a graph capturing main functions and relations between them. Further, this graph is mapped onto another graph depicting the floor layout in terms of areas and rooms. Both graphs produced by the user are checked against the constraints resulting from the requirements of the relevant code of practice. The final result is converted into the format accepted by a commercial CAD-tool in order to proceed with the detailed design.

This paper explores the application of computational techniques in problem solving. Specifically, it examines the use of a software add-on in the realm of space layout planning, to enable customization in the housing industry. The paper first proposes a comprehensive system to enable mass customization of housing, based on analysis of diverse research precedents, in addition to current industry applications. Then, a generative design model is proposed for the problem of space layout design. The model derives its logic from the concept of physical simulation and then implemented through a computer application that enables easy exploration and visualization of solutions. This paper represents a phase from an ongoing research endeavor to enable efficient customization in the housing industry through employing computational methods in design and production.