Architectural intelligence最新文献

{"title":"Tool to teammate: a systematic review on human–robot collaboration in architectural fabrication","authors":"Tahmures Ghiyasi,&nbsp;Ali Ghazvinian","doi":"10.1007/s44223-026-00121-x","DOIUrl":"10.1007/s44223-026-00121-x","url":null,"abstract":"<div><p>The evolving field of Human–Robot Collaboration (HRC) in the Architecture, Engineering, Fabrication, and Construction (AEFC) academia and Industry requires new approaches that reconcile human cognitive adaptability with robotic precision to address the unpredictability of construction environments. Architectural fabrication operates under site-specific conditions, material irregularities, and design uniqueness that limit the effectiveness of conventional automation, especially in comparison to the controlled manufacturing settings. This review investigates how frameworks of HRC in architecture have evolved from tool-based automation toward shared and adaptive systems, and what challenges persist in translating these developments into real-world construction practices. A systematic review was conducted on 110 peer-reviewed studies, each analyzed across various analytical dimensions: level of collaboration, materials, fabrication scale, digital and physical methods. To organize this diversity, the review introduces a six-level classification of human–robot collaboration, starting from manual control to supervised autonomy, collaborative control, adaptive collaboration, fully autonomous systems, and finally collective human–robot collaboration. Each level builds upon and evolves from the insights of the preceding ones. This framework enables a consistent comparison of technological capabilities, degrees of autonomy, and modes of human involvement across studies. The synthesis indicates gradual evolution in HRC frameworks. The more basic levels retain strong connections to craft and material intuition but remain constrained in scalability and repeatability. Intermediate levels incorporate real-time feedback and learning-based responsiveness, enabling more balanced task sharing between humans and robots. The advanced levels demonstrate emerging capacities for distributed intelligence and coordinated multi-agent behavior, yet they encounter significant technical, operational, and economic limitations that restrict their deployment beyond experimental settings. Across all levels, advances in sensing, simulation, and human–machine interface design are steadily expanding the domain of robotic construction while revealing persistent gaps between research and practice. The trajectory of HRC in architecture represents a broader socio-technical transformation that redefines the relationship between design, labor, and automation. Future progress depends on integrating collaborative robotics into construction workflows, fostering democratization of technology, and establishing robust frameworks for safety, training, and regulation that support human–robot coexistence on site. Bridging the divide between experimental success and scalable application will require sustained interdisciplinary collaboration among architects, engineers, robotic experts, and social scientists to advance a more adaptive and human-centered construction future.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00121-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148782673","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From shape grammars to machine learning: a plea for the neuro-symbolic approach to generative AI","authors":"Mario Carpo","doi":"10.1007/s44223-026-00129-3","DOIUrl":"10.1007/s44223-026-00129-3","url":null,"abstract":"<div><p>A comparison between examples of style transfer and stylistic imitation as envisaged by the theory of Shape Grammars in the 1970s and those enabled by Generative AI today (with case studies and student work from a research seminar). The essay emphasizes the limits of Generative AI as a pure imitation machine, and argues for a merger of old-school rule-based systems and contemporary LLM-based machine learning.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00129-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148751704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multilevel computing framework for behavior recognition and interaction in mixed reality workspaces","authors":"Menghang Liu,&nbsp;Ruyi Yang,&nbsp;Luqi Feng,&nbsp;Yanzi Jin,&nbsp;Wenjie Wang,&nbsp;Chao Yan","doi":"10.1007/s44223-026-00127-5","DOIUrl":"10.1007/s44223-026-00127-5","url":null,"abstract":"<div><p>Mixed Reality (MR) technology, as an emerging interactive medium, has seen widespread application in various everyday fields in recent years, offering significant convenience for intelligent interactions between humans and spaces. However, current MR environments primarily rely on single-input interaction methods, where specific behaviors or body movements are recognized to drive changes in the virtual environment. Such approaches often overlook the comprehensive and interrelated nature of human behaviors, potentially diminishing the immersive user experience. This paper proposes an improved interaction model that aims to comprehensively perceive multi-scale human behaviors, including social, global-postural, local-gestural, and facial scales. Using a smart office space as the design prototype, the system integrates body tracking and affective computing techniques, and employs Grasshopper and Unity for real-time spatial modeling and rendering. This allows the MR environment to dynamically respond to user behaviors and support flexible spatial transformations. An experimental study provides initial evidence that the proposed framework can effectively sense user behaviors and dynamically adapt environmental changes. The results suggest potential improvements in spatial immersion and interaction naturalness, providing a reference for further exploration of behavior-driven interaction in intelligent MR environments.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00127-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148750947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of image control workflows in generative AI for architectural design: a FLUX.1-based study","authors":"Yang Yu,&nbsp;Ding Wen Bao,&nbsp;Yuqian Liu","doi":"10.1007/s44223-026-00134-6","DOIUrl":"10.1007/s44223-026-00134-6","url":null,"abstract":"<div><p>Text-to-image generative models often struggle to maintain visual consistency across outputs, which limits their applicability in professional architectural rendering workflows. This study examines three FLUX.1-based image-to-image workflows for architectural aerial renderings. These approaches include generation using prompts with Florence-2 providing descriptions, fine-tuning using LoRA on datasets specific to the domain, and FLUX.1 REDUX that uses image conditioning. Analysis using measures reveals that FLUX.1 REDUX shows the most consistency and maintains architectural details in the data, while generation using prompts shows high variation and fine-tuning using LoRA shows limited improvement in results. The results indicate that image-conditioned approaches provide stronger overall reference-image fidelity than text-only prompting and LoRA-based adaptation, offering a practical basis for more reliable generative workflows in architectural design.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00134-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148613704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An empirical framework for sustainable building materials selection in residential construction: evidence from Tanzania","authors":"Constant Mahame,&nbsp;Geraldine J. Kikwasi,&nbsp;Modest M. Baruti,&nbsp;Olukanni O. David","doi":"10.1007/s44223-026-00132-8","DOIUrl":"10.1007/s44223-026-00132-8","url":null,"abstract":"<div><p>Across developing countries, the selection of building materials still relies on short-term costs and practitioners’ familiarity rather than structured sustainability assessments (SSAs), despite rapid urbanisation and rising housing demand. A prior systematic review identified 19 factors across environmental, economic, and socio-cultural dimensions; however, it did not establish their relative importance in any specific context or provide an operational tool to translate these factors into structured guidance for early-stage material evaluation. This study addresses both gaps in Tanzania, a rapidly urbanising developing country, through a structured questionnaire survey distributed to 326 registered construction professionals, yielding 156 usable responses from architects, engineers, and quantity surveyors with residential project experience. The reliability of the 19-factor instrument was confirmed using Cronbach’s alpha, which showed good to excellent internal consistency. Factor importance was evaluated using the Relative Importance Index (RII) within a triple bottom line framework. The results indicate that environmental factors dominate professional priorities. Material environmental impact, ecosystem protection, and waste management were the highest-ranked factors. Economic factors follow, with the life-cycle cost ranked above the initial cost, showing attention to the long-term value. Socio-cultural factors ranked lower overall, although health and safety remained important. These findings challenge the assumption that cost dominates decision-making in developing countries and align with the sustainability objectives of Tanzanian professionals. This study developed a weighted evaluation matrix that translates ranked factors into a practical tool for early stage material selection, where detailed data are often limited. Future work should apply multi-criteria methods, such as the Analytic Hierarchy Process, and validate the framework through case-based applications, including testing the transferability of these priorities to other developing-country residential construction sectors.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00132-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148613813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Responsive discrete deposition modelling for environment-situated additive manufacturing","authors":"Lucas Helle,&nbsp;Joseph Naguib,&nbsp;Roberto Naboni","doi":"10.1007/s44223-026-00133-7","DOIUrl":"10.1007/s44223-026-00133-7","url":null,"abstract":"<div><p>Conventional additive manufacturing relies on precomputed toolpaths and assumes stable material and environmental conditions, limiting its capacity to adapt during fabrication. This study introduces Responsive Discrete Deposition Modelling (R-DDM), a fabrication framework that replaces continuous extrusion with bead-scale deposition recalculated during fabrication through environmental sensing and agent-based decision-making. R-DDM formalises a closed sensing–response–action loop in which each material placement responds to live input, demonstrated here through light-seeking behaviours inspired by phototropism. A calibration study supports precise dosage control, while a parallel simulation environment enables behavioural definition and preliminary outcome exploration. Physical experiments show that branching, merging, and hybrid trajectories can be reliably produced without predefined geometry, and exhibit strong correspondence with simulation. By structuring fabrication as a sequence of local, stimulus-informed actions, R-DDM enables adaptive material organisation and offers a model for situated, environment-aware construction systems, particularly relevant for unstructured or variable contexts where standard toolpath logic fails.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00133-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148613922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Braided mycelium composites: an integrated robotic design-to-fabrication method for bio-based fibrous building components","authors":"Tiziano Derme,&nbsp;Alim Battal,&nbsp;Nicolas Boscoboinik,&nbsp;Francis W. M. R. Schwarze,&nbsp;Benjamin Dillenburger","doi":"10.1007/s44223-026-00126-6","DOIUrl":"10.1007/s44223-026-00126-6","url":null,"abstract":"<div><p>Mycelium-based composites offer a bio-derived alternative for transform-ing lignocellulosic substrates into lightweight building components. However, architectural-scale implementation remains constrained by mold-based form-giving, limited reinforcement continuity, discontinuous fabrication methods, and limited repeatability under conditions of high customization. This paper presents an integrated robotic design-to-fabrication method for Braided Mycelium Com-posites, a class of mycelium composites in which robotically braided, rope-scale hemp scaffolds are consolidated by mycelium to form contaminant-free and formwork-free building components. The paper presents three elements: The method comprises three elements: (i) a deposition-relevant braid specification method that converts a target boundary into ordered rope trajectories with turning and collision constraints; (ii) a rope-scale robotic braiding and toolpath strategy that maintains executable placement across multi-radius fiber bun-dles; and (iii) a biogenic junction-locking protocol that immobilizes crossovers and consolidates the scaffold over 30–45 days. The method is evaluated for architectural use-cases through scalability metrics (time and phase-dependent mass/geometry change), three-point bending (rope-scale stiffness/strength and failure morphology), and impedance-tube acoustics (normal-incidence absorp-tion). Manufacturing feasibility is linked to service-relevant structural and environmental performance. The results indicate a junction-controlled composite response while the bending of the material is governed by localized indenta-tion and progressive rind cracking rather than brittle rope rupture. Acoustic absorption remains modest across the measured band. The findings presented herein substantiate the method as a replicable methodology for the production of mold-free, contaminant-free mycelium composites. Furthermore, these findings identify the pivotal factors (i.e., junction density, placement tolerances, and sta-bilization conditions) that can be utilized to enhance the structural and acoustic performance of interior building components.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00126-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148465680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Robotic biocementation spraying: a bioinspired fabrication method for architectural surfaces","authors":"Karen Antorveza Paez,&nbsp;Robert O. Kindler,&nbsp;Dimitrios Terzis,&nbsp;CheWei Lin,&nbsp;Fergal B. Coulter,&nbsp;Benjamin Dillenburger","doi":"10.1007/s44223-026-00131-9","DOIUrl":"10.1007/s44223-026-00131-9","url":null,"abstract":"","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00131-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148465611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From branch to fabrication: investigating natural tree bifurcation for structural node design","authors":"Raman Suliman,&nbsp;Kevin Moreno Gata,&nbsp;Martin Trautz","doi":"10.1007/s44223-026-00130-w","DOIUrl":"10.1007/s44223-026-00130-w","url":null,"abstract":"<div><p>The demand for sustainable construction is increasing rapidly. This is largely due to the growing interest in timber as a renewable material. However, current industry practices still favor standard straight lumber, more often overlooking the fact that naturally occurring irregular timber is a valuable resource. These irregular wood elements, specifically tree bifurcations, have great potential as a basis for sustainable construction methods. This research addresses resource efficiency by harnessing the unique properties of angular timber elements (ATEs) through computational design methods. Using 3D scanning, the geometry and grain alignment of raw wood components were examined. Digital libraries were created to document key traits. Data from the material library were analyzed, along with various considerations for the fabrication and construction of such elements. These later drove the design process, which was reinforced with parametric methods and optimization techniques. This optimization, in turn, directly affected the configuration and geometry of the node structures and their bespoke nodes. Through sample studies on different structural typologies, such as wall-, tower-, ceiling-, and bridge-like configurations, the integration of these natural materials into node-based systems was examined. The findings highlight a method for aligning the material’s inherent characteristics with structural goals, aiming to balance robust load-bearing performance with design flexibility. This study demonstrates the feasibility of combining computational design with the variability of raw timber to reduce waste and promote sustainability, opening new avenues for architectural expression.</p></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00130-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148465961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsteady mass transport mechanism in the pollutant removal of pumping ventilation in a multi-story residential building","authors":"Jiang-Nan Gui,&nbsp;Chao Lin,&nbsp;Xin-Ju Wang,&nbsp;Huai-Yu Zhong,&nbsp;Jie Sun,&nbsp;Fu-Ping Qian,&nbsp;Fu-Yun Zhao,&nbsp;Hideki Kikumoto","doi":"10.1007/s44223-026-00128-4","DOIUrl":"10.1007/s44223-026-00128-4","url":null,"abstract":"<div><p>Velocity fluctuations are predominant force of the indoor-outdoor air-exchange in pumping ventilation (PV). However, few studies have given a quantitative evaluation on their exact contribution to the ventilation rate or pollutant removal in PV. This study investigates airflow and concentration fields in rooms of an isolated three-story building under PV with different opening separations (normalized opening-center distances between two openings) using Large-Eddy Simulation (LES). The purpose is to validate numerical accuracy against previous wind tunnel experiments (WTE) and elucidate mass transport mechanisms governing ventilation efficiency of PV. LES analyzed mean and fluctuating stream-wise velocities in the building wake, indoor tracer gas concentrations, and effective ventilation rates, comparing them quantitatively with WTE data. Convective and unsteady mass fluxes were quantified to delineate their respective contributions to pollutant removal. Quadrant analysis of unsteady velocities and concentration at the opening center have been conducted to describe the unsteady mass transport characteristics through the opening in PV. The results demonstrated that LES accurately predicted mean and fluctuating velocity statistics (mean deviation &lt; 5%) and effective ventilation rates (within 10% error for center-point based purging flow rate). LES underestimated both the mean and fluctuating concentration with deviations generally below 20%. The unsteady mass flux accounted for over 90% of the total mass flux through the opening. Quadrant analysis indicated that the ejection and sweep were much more significant than the inward interaction and outward interaction. Larger opening separations could enhance unsteady mass flux and the ejection event at the opening. </p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":72270,"journal":{"name":"Architectural intelligence","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s44223-026-00128-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148465209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}