We are delighted to announce the 2024 Best Paper Awards from Architectural Intelligence.

Based on the review comments and editor nominations, along with considering the citation and download metrics of reference, 10 papers were initially selected as candidate papers. Following deliberation, five papers were chosen as recipients of the 2024 Best Paper Awards:

Human-machine collaboration using gesture recognition in mixed reality and robotic fabrication

Alexander Htet Kyaw, Lawson Spencer, Leslie Lok*

Abstract

This research presents an innovative approach that integrated gesture recognition into a Mixed Reality (MR) interface for human–machine collaboration in the quality control, fabrication, and assembly of the Unlog Tower. MR platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons within the interface for user interaction between virtual and physical environments. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the virtual environment. The research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update, or generate new digital information. This integration facilitates reciprocal stimuli between the physical and virtual environments, wherein the digital environment is generative of the user’s tactile interaction with physical objects. Thereby providing user with direct, seamless feedback during the fabrication process. Through this method, the research has developed and presents three distinct Gesture-Based Mixed Reality (GBMR) workflows: object localization, object identification, and object calibration. These workflows utilize gesture recognition to enhance the interaction between virtual and physical environments, allowing for precise localization of objects, intuitive identification processes, and accurate calibrations. The results of these methods are demonstrated through a comprehensive case study: the construction of the Unlog Tower, a 36’ tall robotically fabricated timber structure.

Alexander Htet Kyaw (first author)

Rural-Urban Building Innovation Lab (RUBI), College of Architecture, Cornell University, Art, and Planning, Ithaca, NY, 14853, USA

Leslie Lok (corresponding author)

Rural-Urban Building Innovation Lab (RUBI), College of Architecture, Cornell University, Art, and Planning, Ithaca, NY, 14853, USA

Email: wll36@cornell.edu

DeepCraft: imitation learning method in a cointelligent design to production process to deliver architectural scenarios

Peter Buš*, Zhiyong Dong*

Abstract

The recent advancements in digital technologies and artificial intelligence in the architecture, engineering, construction, and operation sector (AECO) have induced high demands on the digital skills of human experts, builders, and workers. At the same time, to satisfy the standards of the production-efficient AECO sector by reducing costs, energy, health risk, material resources, and labor demand through efficient production and construction methods such as design for manufacture and assembly (DfMA), it is necessary to resolve efficiency-related problems in mutual human‒machine collaborations. In this article, a method utilizing artificial intelligence (AI), namely, generative adversarial imitation learning (GAIL), is presented then evaluated in two independent experiments related to the processes of DfMA as an efficient human‒machine collaboration. These experiments include a) training the digital twin of a robot to execute a robotic toolpath according to human gestures and b) the generation of a spatial configuration driven by a human's design intent provided in a demonstration. The framework encompasses human intelligence and creativity, which the AI agent in the learning process observes, understands, learns, and imitates. For both experimental cases, the human demonstration, the agent's training, the toolpath execution, and the assembly configuration process are conducted digitally. Following the scenario generated by an AI agent in a digital space, physical assembly is undertaken by human builders as the next step. The implemented workflow successfully delivers the learned toolpath and scalable spatial assemblies, articulating human intelligence, intuition, and creativity in the cocreative design.

Peter Buš (first & corresponding author)

Institute of Future Human Habitats, Tsinghua Shenzhen International Graduate School, University Town of Shenzhen, Nanshan District, Shenzhen, 518055, P.R. China

Email: peter_bus@sz.tsinghua.edu.cn

Zhiyong Dong (corresponding author)

Institute of Future Human Habitats, Tsinghua Shenzhen International Graduate School, University Town of Shenzhen, Nanshan District, Shenzhen, 518055, P.R. China

Email: dongzy23@mails.tsinghua.edu.cn

Unreinforced concrete masonry for circular construction

Shajay Bhooshan*, A. Dell’Endice, F. Ranaudo, T. Van Mele, P. Block

Abstract

This paper proposes an effective approach to realise circular construction with concrete, and shows Unreinforced Masonry as a foundational building block for it.

The paper outlines the importance of circularity in building structures. It specifically focuses on the impact of circular construction with concrete on improving the sustainability of the built environment in a rapidly urbanising world economy. Subsequently, the relevance of principles of structural design and construction of unreinforced masonry to achieve circularity is articulated. Furthermore, the paper presents and summarises recent developments in the field of Unreinforced Concrete Masonry (URCM) including digital design tools to synthesise structurally efficient shapes, and low-waste digital fabrication techniques using lower-embodied-emission materials to realise the designed shapes. The paper exemplifies these using two physically realised, full-scale URCM footbridge prototypes and a commercially available, mass-customisable building floor element, called the Rippmann Floor System (RFS).

The paper also outlines the benefits of mainstream, industrial-scale adoption of the design and construction technologies for URCM, including accelerating the pathway to decarbonise the concrete industry. In summary, the paper argues that URCM provides a solution to significantly mitigate the carbon emissions associated with concrete and reduce the use of virgin resources whilst retaining its benefits such as widespread and cheap availability, endurance, fire safety, low maintenance requirements and recyclability.

Shajay Bhooshan (first & corresponding author)

Zaha Hadid Architects Computation and Design Group, London, UK

Email: Shajay.bhooshan@zaha-hadid.com

Wind tunnel and numerical study of outdoor particle dispersion around a low-rise building model

Runmin Zhao, Junjie Liu, Nan Jiang, Sumei Liu*

Abstract

The dispersion of particulate pollutants around buildings raises concerns due to adverse health impacts. Accurate prediction of particle dispersion is important for evaluating health risks in urban areas. However, rigorous validation data using particulate tracers is lacking for numerical models of urban dispersion. Many prior studies rely on gas dispersion data, questioning conclusions due to differences in transport physics. To address this gap, this study utilized a combined experimental and computational approach to generate comprehensive validation data on particulate dispersion. A wind tunnel experiment using particulate tracers measured airflow, turbulence, and particle concentrations around a single building, providing reliable but sparse data. Validated large eddy simulation expanded the data. This combined approach generated much-needed validation data to evaluate numerical particle dispersion models around buildings. Steady Reynolds-averaged Navier–Stokes (SRANS) simulations paired with Lagrangian particle tracking (LPT), and drift-flux (DF) models were validated. SRANS had lower accuracy compared to LES for airflow and turbulence. However, in this case, SRANS inaccuracies did not prevent accurate concentration prediction when LPT or a Stokes drift-flux model were used. The algebraic drift-flux model strongly overpredicted the concentration for large micron particles, indicating proper drift modeling was essential.

Runmin Zhao (first author)

Tianjin Key Laboratory of Indoor Air Environmental Quality Control, School of Environmental Science and Engineering, Tianjin University, Tianjin, 300072, China

Sumei Liu (corresponding author)

Tianjin Key Laboratory of Indoor Air Environmental Quality Control, School of Environmental Science and Engineering, Tianjin University, Tianjin, 300072, China

Email: smliu@tju.edu.cn

Making the Hypar Up pavilion:(in) efficiencies of upcycling surplus timber products

Sofia Colabella*, Alberto Pugnale, Jack Halls, Michael Minghi Park, László Mangliár, Markus Hudert

Abstract

This paper illustrates the design and fabrication processes of the Hypar Up pavilion, which served as a proof-of-concept to demonstrate the viability of a design-to-fabrication workflow for complex yet modular architectural geometries that utilise small and planar timber offcuts geometries discretised as Planar Quadrilateral (PQ) meshes. By integrating computational design and optimisation with efficient manufacturing processes, this research highlights the technical challenges of repurposing materials with unknown characteristics, notably detailing solutions, and evaluates the efficiency of design-to-manufacturing workflows with surplus timber products, using a quantitative cost analysis of the fabrication and assembly phases. While exploring the potential of repurposing scrap wood into hypar-shaped modular construction components, this work expands on existing research on segmented shells and investigates methods and means to move beyond the use of shell structures as monolithic and static artefacts. The pavilion is intended as a 1:1 modular prototype that can be resized to accommodate different dimensions of the timber panel offcuts and potential applications to be tested in future applications, such as load-bearing walls and facade retrofitting.

Sofia Colabella(first & corresponding author)

Faculty of Architecture, Building and Planning, The University of Melbourne, Melbourne, Australia

Email: s.colabella@unimelb.edu.au

These papers were awarded because of the following reasons:

1. the originality of approach, methods, or hypotheses.
2. contribution to the advancement of the field.
3. quality of the communication/presentation and clarity of the text and illustrations.
4. the soundness of science.

Selection Committee (in alphabetical order by surname):

Li Lan (Shanghai Jiao Tong University),

Dr. Dan Luo (The University of Queensland)，

Prof. Jianlin Liu (Donghua University), 

Dr. Weishun Xu (Zhejiang University),

Prof. Zhen Xu (Tianjin University),

We sincerely appreciate the outstanding contributions of all award-winning authors and their efforts in advancing the field of architectural intelligence. We look forward to the continued support and active participation of our readers and reviewers.