Material Disruption

This paper examines the role of computational simulation of material processes with robotics fabrication, with the intent of examining its implications for architectural design and construction. Simulation techniques have been adopted in the automotive industry amongst others, advancing their design and manufacturing outputs. At present, architecture is yet to explore the full potential of this technology and their techniques. The need for simulation is evident in exploring the behaviours of materials and their relative properties. Currently, there is a distinct disconnect between the virtual model and its fabricated counterpart. Through research in simulation, we can begin to understand and clearly visualize the relationship between material behaviours and properties that can lead to a closer correlation between the digital design and its fabricated outcome. As the first phase of investigation, the material of clay is used due to its volatile qualities embedded within the material behaviour. The input geometry is constrained to rudimentary extruded forms in order to not obscure the behaviour of the material, but rather allow for it to drive the machine-making process.

Working with Uncertainties: An Adaptive Fabrication Workflow for Bamboo Structures

This paper presents and investigates a cyber-physical fabrication workflow, which can respond to the deviations between built- and designed form in real-time with vision augmentation. We apply this method for large scale structures built from natural bamboo poles. Raw bamboo poles obtain evolutionarily optimized fibrous layouts ideally suitable for lightweight and sustainable building construction. Nevertheless, their intrinsically imprecise geometries pose a challenge for reliable, automated construction processes. Despite recent digital advancements, building with bamboo poles is still a labor-intensive task and restricted to building typologies where accuracy is of minor importance. The integration of structural bamboo poles with other building layers is often limited by tolerance issues at the interfaces, especially for large scale structures where deviations accumulate incrementally. To address these challenges, an adaptive fabrication process is developed, in which existing deviations can be compensated by changing the geometry of subsequent joints to iteratively correct the pose of further elements. A vision-based sensing system is employed to three-dimensionally scan the bamboo elements before and during construction. Computer vision algorithms are used to process and interpret the sensory data. The updated conditions are streamed to the computational model which computes tailor-made bending stiff joint geometries that can then be directly fabricated on-the-fly. In this paper, we contextualize our research and investigate the performance domains of the proposed workflow through initial fabrication tests. Several application scenarios are further proposed for full scale vision-augmented bamboo construction systems.

A Preliminary Study on the Formation of the General Layouts on the Northern Neighborhood Community Based on GauGAN Diversity Output Generator

Recently, the mainstream gradually has become replacing neighborhood-style communities with high-density residences. The original pleasant scale and enclosed residential spaces have been broken, and the traditional neighborhood relations are going away. This research uses machine learning to train the model to generate a new plan, which is used in today’s residential design. First, in order to obtain a better generation effect, this study extracts the transcendental information of the neighborhood community in north of China, using roads, buildings etc. as morphological representations; GauGAN, compared to the pix2pix and pix2pixHD, used by predecessors, can achieve a clearer and a more diversified output and also fit irregular contours more realistically. ANN model trained by 167 general layout samples of a neighborhood community in north of China from 1950s to 1970s can generate various general layouts in different shapes and scales. The experiment proves that GauGAN is more suitable for general layout generation than pix2pix (pix2pixHD); Distributed training can improve the clarity of the generation and allow later vectorization to be more convenient.

Pipes of AI – Machine Learning Assisted 3D Modeling Design

Style transfer is a design technique that is based on Artificial Intelligence and Machine Learning, which is an innovative way to generate new images with the intervention of style images. The output image will carry the characteristic of style image and maintain the content of the input image. However, the design technique is employed in generating 2D images, which has a limited range in practical use. Thus, the goal of the project is to utilize style transfer as a toolset for architectural design and find out the possibility for a 3D modeling design. To implement style transfer into the research, floor plans of different heights are selected from a given design boundary and set as the content images, while a framework of a truss structure is set as the style image. Transferred images are obtained after processing the style transfer neural network, then the geometric images are translated into floor plans for new structure design. After the selection of the tilt angle and the degree of density, vertical components that connecting two adjacent layers are generated to be the pillars of the structure. At this stage, 2D style transferred images are successfully transformed into 3D geometries, which can be applied to the architectural design processes. Generally speaking, style transfer is an intelligent design tool that provides architects with a variety of choices of idea-generating. It has the potential to inspire architects at an early stage of design with not only 2D but also 3D format.

Growing Shapes with a Generalised Model from Neural Correlates of Visual Discrimination

This paper focuses on the application of visual Event-Related Potentials (ERP) in better generalisations for design and architectural modelling. It makes use of previously built techniques and trained models on EEG signals of a singular individual and observes the robustness of advanced classification models to initiate the development of presentation and classification techniques for enriched visual environments by developing an iterative and generative design process of growing shapes. The pursued interest is to observe if visual ERP as correlates of visual discrimination can hold in structurally similar, but semantically different, experiments and support the discrimination of meaningful design solutions. Following bayesian terms, we will coin this endeavour a Design Belief and elaborate a method to explore and exploit such features decoded from human visual cognition.

A Performance-Based Urban Block Generative Design Using Deep Reinforcement Learning and Computer Vision

In recent years, generative design methods are widely used to guide urban or architectural design. Some performance-based generative design methods also combine simulation and optimization algorithms to obtain optimal solutions. In this paper, a performance-based automatic generative design method was proposed to incorporate deep reinforcement learning (DRL) and computer vision for urban planning through a case study to generate an urban block based on its direct sunlight hours, solar heat gains as well as the aesthetics of the layout. The method was tested on the redesign of an old industrial district located in Shenyang, Liaoning Province, China. A DRL agent - deep deterministic policy gradient (DDPG) agent - was trained to guide the generation of the schemes. The agent arranges one building in the site at one time in a training episode according to the observation. Rhino/Grasshopper and a computer vision algorithm, Hough Transform, were used to evaluate the performance and aesthetics, respectively. After about 150 h of training, the proposed method generated 2179 satisfactory design solutions. Episode 1936 which had the highest reward has been chosen as the final solution after manual adjustment. The test results have proven that the method is a potentially effective way for assisting urban design.

Cyborgian Approach of Eco-interaction Design Based on Machine Intelligence and Embodied Experience

The proliferation of digital technology has swelled the amount of time people spent in cyberspace and weakened our sensibility of the physical world. Human beings in this digital era are already cyborgs as the smart devices have become an integral part of our life. Imagining a future where human totally give up mobile phones and embrace nature is neither realistic nor reasonable. What we should aim to explore is the opportunities and capabilities of digital technology in terms of fighting against its own negative effect - cyber addiction, and working as a catalyst that re-embeds human into outdoor world.Cyborgian systems behave through embedded intelligence in the environment and discrete wearable devices for human. In this way, cyborgian approach enables designers to take advantages of digital technologies to achieve two objectives: one is to improve the quality of environment by enhancing our understanding of non-human creatures; the other is to encourage a proper level of human participation without disturbing eco-balance.Finally, this paper proposed a cyborgian eco-interaction design model which combines top-down and bottom-up logics and is organized by the Internet of Things, so as to provide a possible solution to the concern that technologies are isolating human and nature.

Real-Time Defect Recognition and Optimized Decision Making for Structural Timber Jointing

Non-structural or out-of-grade timber framing material contains a large proportion of visual and natural defects. A common strategy to recover usable material from these timbers is the marking and removing of defects, with the generated intermediate lengths of clear wood then joined into a single piece of full-length structural timber. This paper presents a novel workflow that uses machine learning based image recognition and a computational decision-making algorithm to enhance the automation and efficiency of current defect identification and re-joining processes. The proposed workflow allows the knowledge of worker to be translated into a classifier that automatically recognizes and removes areas of defects based on image capture. In addition, a real-time optimization algorithm in decision making is developed to assign a joining sequence of fragmented timber from a dynamic inventory, creating a single piece of targeted length with a significant reduction in material waste. In addition to an industrial application, this workflow also allows for future inventory-constrained customizable fabrication, for example in production of non-standard architectural components or adaptive reuse or defect-avoidance in out-of-grade timber construction.

Optimization and Prediction of Design Variables Driven by Building Energy Performance—A Case Study of Office Building in Wuhan

This research focuses on the energy performance of office building in Wuhan. The research explored and predicted the optimal solution of design variables by Multi-Island Genetic Algorithm (MIGA) and RBF Artificial neural networks (RBF-ANNs). Research analyzed the cluster centers of design variable by K-means cluster method. In the study, the RBF-ANNs model was established by 1,000 simulation cases. The RMSE (root mean square error) of the RBF-ANNs model in different energy aspects does not exceed 15%. Comparing to the reference case (the largest energy consumption case in the optimization), the 214 elite cases in RBF-ANNs model save at least 37.5% energy. By the cluster centers of the design variables in the elite cases, the study summarized the benchmark of 14 design variables and also suggested a building energy guidance for Wuhan office building design.

On-Site BIM-Enabled Augmented Reality for Construction

We describe a prototype system for communicating building information and models directly to on-site general contractors and subcontractors. The system, developed by SHoP Architects, consists of a workflow of pre-processing information within Revit, post-processing information outside of Revit, combining data flows inside of a custom application built on top of Unity Reflect, and delivering the information through a mobile application on site with an intuitive user interface. This system incorporates augmented reality in combination with a dashboard of documentation views categorized by building element.