Evidence-based design principles can help overcome legislative shortcomings and long-standing challenges in designing healthcare units. Leveraging these principles through transfer learning can utilize pre-trained knowledge to generate optimal spatial arrangements, yet the dataset-formulating factors remain scarcely investigated. Therefore, we employ mixed-methods research (including workflow analysis and behavioral mapping in an emergency care unit) to generate a highly contextual evidence-based database. Using four actor flow scenarios, we identified dead zones, nodes, collision points, approximate nursing distances, and zone mapping as key contextual factors. This study contributes to informing design considerations and the contextual training of transfer learning in generative healthcare architecture.
Current building modeling approaches treat geometry as primary and semantics as secondary, limiting knowledge-integrated building design where spatial reasoning informs iterative design decisions. This paper presents a space-driven knowledge framework integrating topological space partitioning with semantic triple generation, enabling immediate inference over spatial relationships. The workflow progresses through iterative stages of partitioning, algorithmic triple generation from topological queries and quantity calculations, axiomatic reasoning, and rule-based inference for requirements. A proof of concept demonstrates how storey classification, spatial adjacency, and fire safety requirements can be inferred during the modeling process using the BOT ontology extended with fire safety concepts from FiSa.
The construction industry faces high musculoskeletal disorder rates due to repetitive, awkward task-postures. Current manual corrections and static optimizations often ignore individual anthropometry and whole-body biomechanical interdependencies, leading to physically unfeasible results. This study explores Reinforcement Learning (RL) for tailored posture optimization by developing a pipeline that overcomes technical barriers like reward instability and high computational costs. The proposed technique predicts joint-space residuals via a distilled, risk-aware RL policy within a physics simulator. Testing in construction-like scenarios showed significantly reduced mean risk and high-risk spikes while maintaining task fidelity. These findings demonstrate that RL can provide personalized, executable ergonomic interventions.
Current robotic fleet management in construction primarily relies on 2D maps and geometry-based
planners, with limited integration of process context and machine capabilities. This restricts scalability and adaptability in complex, dynamic sites. This paper proposes a semantic voxelisation framework that combines 3D voxel models with knowledge of construction processes, resources, and capabilities using IOC, BOT, and CaSkMan ontologies. The knowledge for capability-aware planning and task scheduling is queried using SPARQL and translated into domains and
constraints for the planning framework. The contribution is a unified semantic-to-robotic pipeline enabling context-aware planning and scheduling for holistic fleet management.
Digitalisation expanded access to design, operational and environmental data, yet whole carbon-life assessment and climate risk prediction still evolve in separate, non-interoperable workflows. This fragmentation limits climate-responsive design, especially for urban flooding and heat. The paper develops a conceptual framework for digital climate indicators that link carbon performance with predictive flood and urban heat analytics. Using a structured review of recent work on BIM-integrated life cycle assessment, digital twins, machine-learning-based hazard modelling and resilience assessment, it derives key information requirements and illustrates their application. The contribution is a set of indicator families and research directions for robust, portable climate-resilience metrics
Building Information Modelling (BIM) and Augmented Reality (AR) integration has been widely proposed to improve construction coordination, yet evidence from live site deployments remains limited. This paper presents a qualitative case study of BIM–AR use with Gamma AR on an active university accommodation project in the UK. Site observations and interviews were used to examine workflow integration, benefits, and challenges. The findings indicate that BIM–AR enhances visualisation, coordination, and early error detection when applied selectively, but is constrained by alignment reliability, site conditions, and adoption factors. The study contributes practical deployment insights for BIM–AR implementation in construction.
The Netherlands faces an unprecedented infrastructure renewal assignment that cannot be addressed through traditional project-based delivery. Although industrialisation is widely promoted as a solution, its adoption remains limited due to a lack of system-level understanding of the conditions required for scaling. This study positions industrialisation as a coordinated transformation of infrastructure asset management and develops a principles-based perspective to support this transition. Using thematic analysis of literature and expert validation, five principles are identified. Together, these principles clarify why isolated technological initiatives struggle to scale, and establishes a foundation for developing action perspectives and policy directions to guide industrialisation.
Digital Twins (DTs) couple BIM and IoT for sustainable building operation, yet many implementations remain siloed, hard to scale, and difficult to interpret. This paper presents a stepwise DT prototype for an environmental-education facility, integrating indoor/outdoor sensing (CO₂, PM, temperature, humidity, occupancy) with a Revit BIM model. A Dynamo–Python pipeline maps cloud time-series to shared BIM parameters, enabling in-model visualization, threshold alerts, and KPI reporting. Initial deployment delivers the sensing-and-display setup and a reusable BIM data schema ready for automated synchronization. The lasting contribution is a replicable BIM-centric implementation method for room- and zone-level monitoring in sustainable cultural buildings.
This study uses the XGBoost algorithm to predict accident types in pipeline construction projects through a multi-class classification approach. The model was trained on 1,184 real accident records containing information such as accident time, type, and required treatment. Results showed 83% overall accuracy, 0.82 macro-average F1 score, and 0.81 weighted F1 score. While some classes achieved high recall, categories with limited data performed lower. The findings indicate that XGBoost can support accident type prediction and risk analysis in construction projects using historical incident data.
Building maintenance and renovation decisions rely heavily on expert judgment and contextual factors, often requiring manual assessment of conditions, accumulated experience, and locally applicable standards or regulations. This study introduces a multi-agent AI framework designed to automate recommendations for building maintenance and renovation by coordinating task classification, regulatory analysis, and solution generation through LLMs. Specifically, given inputs including a building’s location, type, and reported issues, the framework first uses a task identification agent to classify the case as maintenance or renovation. A knowledge agent then retrieves, structures, and reasons over applicable building codes, standards, and maintenance guidelines specific to the issue. Building on this contextualized knowledge, a solution generation agent produces maintenance recommendations or renovation strategies, or evaluates proposed renovation plans for regulatory compliance. The proposed multi-agent architecture enables the automation of key reasoning steps that are traditionally performed by human experts, including task classification, regulation interpretation, and recommendation formulation.
