Automated building inspections using robots are increasingly employed to enhance safety standards and optimize maintenance processes. However, robot-based inspection methods lack adaptability in inspection planning and BIM integration for context-aware navigation. This paper presents a BIM-based inspection framework, leveraging behavior trees for automated planning and execution of robot tasks. The framework extracts spatial and semantic data from BIM models to advance automated inspection. The BIM-based inspection framework is implemented using quadruped robots, and the framework is validated by performing inspection tasks in indoor office environments. The results demonstrate that coupling BIM and behavior trees improves the accuracy and reliability of automated building inspections.
Fused filament fabrication (FFF) is an additive manufacturing technique, popular due to its versatility and cost-effectiveness. However, FFF machines, such as 3D printers, are prone to runtime errors, wasting time and material, while requiring constant human supervision. This paper presents a defect detection approach for FFF processes based on artificial intelligence, combining convolutional neural networks and computer vision. The defect detection approach is validated using 3D prints designed to mimic common FFF defects. The results demonstrate the capability of the proposed approach to automatically detect defects in FFF processes, thereby reducing time and material waste as well as the need for human supervision.
Tower cranes play an essential role in lifting heavy building elements, which often poses significant hazards to workers. However, automated methods for crane monitoring remain underdeveloped. This paper introduces a data-driven method to track crane trolley trajectories and identify associated hazards. The method utilizes RTK-GNSS to capture spatial movements of the trolley. By analyzing changes in height and speed, a lifting operation can be divided into distinct stages. Integrating the trajectory of the workers and trolley with the site model and schedule allows for incident detection. The proposed method offers a cost-effective and implementable alternative for crane safety monitoring.
Recent large language models (LLMs) with enhanced multimodal capabilities can interpret drawings and generate building descriptions, yet their capabilities are still limited to simple two-dimensional spatial configurations. This study proposes a method to automatically generate natural language descriptions of spatial programs and the connections between spaces from building information models (BIMs) using threshold-enhanced triangle intersection (TETI) algorithm and reasoning LLMs (OpenAI-o1 and DeepSeek-R1). For validation, the inclusion rate of spaces and the correctness of topological extraction are assessed. Results show that the extracted BIM data effectively capture key features, supporting the potential for natural language-based automated BIM description generation.
This paper presents an agent-based model to simulate household decisions transitioning from gas-reliant heating. Households consider three options: installing a gas-free heat pump, adopting district heating, or doing nothing. The model integrates the Theory of Planned Behavior and Bayesian updating of household beliefs. It also accommodates four decision-making styles—rational, satisficing, social, and conservative—that govern how households interpret information and manage risk. Results show how these styles, combined with social influence and evolving beliefs, shape the rate and pattern of adoption, influencing the pace of the gas-free transition. These insights can inform policies and interventions to accelerate sustainable heating technology uptake.
Decentralized project delivery in architecture faces challenges related to transparency, accountability, and role definition. This paper explores the application of Soulbound Tokens (SBTs) as a governance and record-keeping mechanism within decentralized autonomous organizations (DAOs). Using a systematic review of practice, the paper identifies five opportunities for SBTs, proposes an operating framework for SBTs with respect to record-keeping (e.g., skills, contributions) and project governance (e.g, voting power, reputation), and describes one case of technical implementation of SBTs. Future research can improve on this technical implementation or develop additional decentralised applications for SBT skills verification and governance mechanisms.
The implementation of BIM in the AEC industry faces challenges due to misalignment between project needs and team capabilities. Current BIM maturity assessments focus on organizational qualifications rather than project-specific needs. This research addresses this gap through an ethnographic case study of two projects, emphasizing strategies for aligning project needs with BIM uses, assigning responsibilities, and assessing maturity. The first case demonstrates how collaborative models like IPD foster team support in implementing BIM. The second case illustrates how teams with lower organizational BIM maturity can still efficiently contribute by leveraging capabilities aligned with project-specific requirements.
Digital technologies play a crucial role in efficiency and integration across industries. BIM has become a key enabler of digital transformation. Despite the increasing use of BIM, traditional practices remain prevalent, and construction lags in digitalization compared to other sectors. This highlights the need for measuring digital maturity. This paper reviews the outcomes of a digital maturity measurement tool applied to a selection of 256 European construction projects across nine offices using Exploratory Data Analysis. It further provides an analysis of the indicators used to calculate the digital maturity score and examines how the results vary across different European countries.
