Conference papers

Authors: Jhonattan G. Martinez, Timson Yeung, Rafael Sacks
University: Virtual Construction Laboratory (VClab), National Building Research Institute, Technion–Israel Institute of Technology, Haifa 3200003, Israel

Production planning in construction requires numerous agents, or production planners, to make operational decisions that affect the project outcomes. Decisions are based on information collected on the job site and in the project supply chain. However, difficulties accessing real-time information, the numerous production planners involved, and limitations on the planners’ degree of freedom of action can hinder decision-making. Digital Twin Construction (DTC) has emerged as a paradigm for systems that increase the situational awareness of the construction project among production planners and reduce uncertainty in the decision-making process. Under the DTC frame, this research seeks to determine the scope of action of production planners. To accomplish the research goal, semi-structured interviews and a literature review were carried out to identify production planners’ degree of freedom in decision-making when faced with the need for product or process changes. First, the research identifies the operational decisions that production planners make during a construction project in response to developments (as-built, as-performed information). Second, it presents a detailed analysis of production planners’ main limitations during decision-making. Finally, the freedom of action of production planners was defined according to their roles. The findings are summarized in a matrix that associates operational decisions, degree of freedom, and professional roles in the context of DTC. The study results showed that production planners’ scope of action is limited by the lack of real-time information concerning the construction project status and technical and legal limitations that affect their decision-making process.

Download full article

Authors: T. Yeung, J. Martinez, L. Sharoni, R. Sacks 
University: Virtual Construction Laboratory, Technion – Israel Institute of Technology, Israel

Fostered by advances in digital twin and onsite monitoring technologies, the paradigm of Digital Twin Construction (DTC) has emerged as a comprehensive mode of construction that proposes a data-driven lean production planning and control workflow, leveraging project status and design intent information to make proactive production system design changes. Simulation plays an essential role in the DTC paradigm as a provider of predictive situational awareness (SA), a mechanism for data-driven continuous improvement, and an enabler of future autonomous real-time production control systems in construction projects. In this paper, we outline these modes of use of simulation, discuss potential barriers to implementing simulation in DTC workflows, and propose a set of criteria to evaluate a simulation tool’s applicability to DTC.

Download full article

Authors: J. Schlenger, T. Yeung, S. Vilgertshofer, J. Martinez, R. Sacks, A. Borrmann
University: Technical University of Munich, Germany, Israel Institute of Technology, Israel

Lean construction, originating from lean management, aims to proactively improve the overall efficiency of construction processes. This requires continuous assessment of performance to identify key problems, which allows continuous improvement of construction processes. Novel digital twin approaches form an excellent technological foundation for performance assessment through regular updates with product and process information directly from the construction site. While some publications favour a schema-less approach to digital twins, we argue that well-defined data structures are required to represent complex information reliably and transparently. Existing process and product models are inadequate with respect to the requirements of a digital twin of the construction phase. As a result, we introduce a new process-oriented model that provides an improved basis for advanced process evaluation in the digital twin environment. This data schema, which is the main outcome of this paper, is presented in UML format together with a first approach to transfer it to an ontology usable in the Semantic Web context.

Download full article
Authors: Fiona Collins, Fabian Pfitzner, Jonas Schlenger
University: Chair of Computational Modeling and Simulation, TU Munich, Arcisstr. 21, 80333 Munich, Germany

Compared to other industry sectors, the construction sector’s productivity is relatively low. By collecting data directly from the construction site, the main bottlenecks can be identified and support decision-makers in making well-informed decisions. This is by no means a simple task because of the complexity and unpredictability of construction sites and the challenges of monitoring heterogeneous on-site data. While other researchers focus on elaborating specific steps or use-cases of the construction monitoring processes, we present a holistic workflow for scalable shell construction monitoring that uses state-of-the-art data processing techniques. The result of the proposed workflow is a per-instance database for on-site progress across time. Such a database has many possibilities for application. This can range from giving an overview to construction managers, providing a backbone for sophisticated analysis and digital twins, to the validation of computer vision approaches.

Download full article

Authors: Johansen K.W., Schultz C., Teizer J.
University: Department of Electrical and Computer Engineering, Aarhus University, Denmark –  Department of Civil and Mechanical Engineering, Technical University of Denmark, Denmark

Due to the continuous changes in its complex and dynamic work environment, work in the construction industry is one of the most dangerous. Many of the existing workplace safety planning techniques are still based on 2D drawings and manual expertise. This effort is cumbersome as the progressing work quickly results in outdated safety plans. Researchers have put much effort into  automating  the  planning  process,  but  their  result’s  soundness  and  completeness  are incomparable. This work describes our BIM-based ontology of construction hazards and mitigation interventions for fall from height hazards based on EU and US regulations. We extract the variations of the rules and capture the concepts in spatial artifacts. We carefully created a benchmark model that  allows  for  soundness  and  correctness  assessment  which  enables  comparison  of  different automated PTD approaches.

Download full article

Authors: Karsten W. Johansen, Rui Pimentel de Figueiredo, Olga Golovina and Jochen Teizer
University: Civil and Architectural Engineering, Aarhus University, Denmark – Electrical and Computer Engineering, Aarhus University, Denmark

Construction sites are dynamic, and the environment is changing fast, which means the collective safety equipment, such as fall protection barriers, should also be changed to keep it compliant with the construction codes. However, the safety equipment can become non-compliant for several reasons, e.g., temporal removal in combination with incorrect or omitted re-installation or changes in the building. Thus, there is a demand for frequent inspection of the equipment, which is time- and labor-intensive as this is currently done through manual examination by safety experts. In this work, we utilize an unmanned aerial vehicle (UAV) to detect the presence, absence, and defects of safety equipment in construction work-site environments. Furthermore, the UAV continuously inspects and provides safety object location information that human collaborators can use to improve safety within the environment. We utilize an 3D occupancy grid representation to map the environment and compact point pair feature representations for efficient and robust object recognition and pose estimation. To assess the applicability and accuracy of our methods for model-based pose estimation of BIM structures, we created a realistic simulation construction environment. A set of experiments demonstrate the applicability and precision of drone-aided localization and inspection of safety equipment in the construction industries.

Download full article

Journal papers/book chapters

Authors: J. Teizer; K. W. Johansen; and C. Schultz
University: Dept. of Civil and Architectural Engineering – Dept. of Electrical and Computer Engineering, Aarhus Univ., Denmark

“Digital twins” as models for information-driven management and control of physical systems have emerged over the past years in multiple industrial sectors and recently also in construction. However, in the domain of construction safety, a digital twin remains undefined, with little or no consensus among researchers and practitioners of two essential aspects: (1) the connection between the physical reality of a construction site (the “physical” twin) and the corresponding computer model (the “digital” twin), and (2) the most effective selection and exploitation of real-life data for supporting safe design, planning, and execution of construction. This paper outlines the concept for a Digital Twin for Construction Safety (DTCS), defining three essential steps in the digital twin workflow: (1) safe design and planning for hazard prevention, (2) risk monitoring and control for proactive prediction and warning, and (3) continuous performance improvement for personalized- or project-based learning. DTCS should be viewed as a system-based approach enhancing the overall safety performance rather than exclusively integrating sensing information or safety knowledge in Building Information Modeling (BIM) for safety purposes. The result is an outline of our vision of the DTCS and a description of its components. Additionally, we point toward future research on the topic.

Download full article

Authors: Li B., Nielsen R.O., Johansen K.W., Teizer J. , Larsen P.G., Schultz C.
University: Department of Electrical and Computer Engineering – Department of Civil and Architecture Engineering, Aarhus University, Denmark

Civil engineering has only recently started the digitalisation journey by standardising around Building Information Models (BIMs). In the process of construction a dimension of time is added in what is called 4D BIM and this can serve as the basis for a digital twin. It is predicted that such a digital twin can enhance the overall overview of status of the construction of a new building by means of different types of sensors, and interpreting these in relation to a BIM. In the construction phase there are rules and regulations targeting the safety of the different kinds of construction workers at the construction site. In this paper we provide a vision of how digital twins can assist with spotting potential violations of the constraints stated by the rules and regulations, and empirically evaluate a proof-of-concept software tool on a large scale, real-world 4D BIM.

Download full article

Authors: Johansen, K.W., Nielsen, R.O., Teizer, J. , Schultz, C.

Current standard approaches for monitoring site progress for lean construction favor weekly or bi-weekly meetings. All trade and construction site management representatives meet to synchronize the forthcoming schedule. Up-to-date information is often not available, causing poor coordination and resulting in delays, rework and waste of monetary resources. Furthermore, infrequent updates on work performance impact scheduling of critical activities. This paper investigates the possibility to automate some tasks in progress monitoring by applying an AI-system with abductive reasoning on real-time localization sensing data (RTLS) and domain expert knowledge. The work proposes a framework, consisting of three modules (data preparation, processing, and update) that utilize abductive reasoning. An experiment was conducted on previously collected data Teizer et al. (2013) to compare progress inferred from the framework with actual progress recorded. The preliminary results indicate the framework is able to reason about progress with high degree of similarity to the paper of Teizer et al. (2013), however, solely based on RTLS data and without any manual input. The future of the framework is promising since it supports the analysis of time series, allowing it to be applied nearly simultaneously to data collection, and thereby significantly increasing the update rate for information.