Search papers

2022 Proceedings of the 39th ISARC, Bogotá, Colombia

Front matter and table of contents

Thomas Linner, Borja García de Soto, Rongbo Hu and Ioannis Brilakis

Abstract: The International Association for Automation and Robotics in Construction (IAARC) and the 39th ISARC organizing committee are pleased to present the Proceedings of the 39th International Symposium on Automation and Robotics in Construction held, in a hybrid mode, on July 13-15, 2022, at Universidad de los Andes, Bogotá, Colombia. The ...

Keywords: No keywords

A framework for a comprehensive mobile data acquisition setting for the assessment of Urban Heat Island phenomenon

Monic Pena Acosta, Faridaddin Vahdatikhaki, Joao Santos and André Dorée
Pages 1-8

Abstract: The debates around the Urban Heat Island phenomenon (UHI) have gained momentum in the context of smart cities and sustainable development. It is crucial to understand the complex interaction between urban features and temperature variation in the city based on reliable and detailed data. Yet, the complex interaction between the ...

Keywords: Data-driven methods; data collection; smart and sustainable cities; mobile sensing systems; urban heat island

Using BIM and LCA to evaluate material circularity: Contributions to building design improvements

Haibo Feng, Qian Chen, Borja García de Soto and Mehrdad Arashpour
Pages 9-16

Abstract: The construction sector has suffered from low productivity and considerable waste due to the fragmentation of its value chain and inefficient design and material usage processes. The circular economy (CE) principles have gained significant attention among researchers and practitioners to help overcome these challenges. Construction materials such as timber and ...

Keywords: BIM; LCA; Circular economy; Design options; Secondary materials; Embodied carbon

Building Information Model Pre-Processing for Automated Geometric Quality Control

Martín Bueno and Frédéric Bosché
Pages 17-24

Abstract: Geometric quality control (QC) in a construction project is an important but time-consuming and not value-adding task. While significant progress is being made in construc-tion digitalisation, geometric QC processes remain highly manual and inefficient. This manuscript proposes a new methodology to pre-process initial information contained in the as-designed Building Information ...

Keywords: BIM; IFC; Quality Control; Geometric; Point Clouds; Digital Twin

Insights into automation of construction process using parallel-kinematic manipulators

Maike Klöckner, Mathias Haage, Helena Eriksson, Henrik Malm, Klas Nilsson, Anders Robertsson and Ronny Andersson
Pages 25-32

Abstract: This paper discusses challenges, experiences and lessons learned so far while transforming a masonry build system based mostly on manual labour into a robot automated build system. Our motivation for selection of this masonry process is to try out how robot automation could impact the architects in their design work ...

Keywords: Construction robotics; Parallel-kinematic manipulator; Masonry; Concrete build system

Predictive Maintenance Optimization Framework for Pavement Management

Amit Kumar and Omidreza Shoghli
Pages 33-40

Abstract: The preservation of highway infrastructure is essential for maintaining its capacity, safety, and efficiency for commerce and defense. Pavements are among the most important elements of highway systems that deteriorate over time. Hence, the goal of pavement asset management is to seek efficient investments where the methods applied will aid ...

Keywords: Asset Management; Life Cycle Cost; Level of Service; Multi-objective Optimization

Weakly supervised pseudo label generation for construction vehicle segmentation

Wei-Chih Chern, Vijayan Asari, Tam Nguyen and Hongjo Kim
Pages 41-46

Abstract: Segmentation tasks in computer vision have been adopted in various studies in the civil engineering domain to provide accurate object locations in images. However, preparing an-notation to train segmentation models is a time consuming and costly process, which hinders the use of segmentation models in vision-based applications. To address the ...

Keywords: Weakly supervised learning; Semantic segmentation; Pseudo labels; Training data preparation

Teaching Construction Robotics for Higher Education Students: "Imagine and Make"

Zoubeir Lafhaj, Wassim Al Balkhy and Thomas Linner
Pages 47-54

Abstract: The use of robotics in construction projects is still in its infancy despite the opportunities that robots can present to the improvement of construction practices. One of the strategies to effectively increase the reliance on robots in construction is increasing the knowledge and improving the educational programs about robotics for ...

Keywords: Robotics; Construction management techniques; Construction 4.0; Robotics teaching; France

Integrating VR and Simulation for Enhanced Planning of Asphalt Compaction

Andre Renato Revollo Dalence, Faridaddin Vahdatikhaki, Seirgei Miller and André Dorée
Pages 55-62

Abstract: The current decision-making practices in road construction, are largely based on tacit knowledge, craftsmanship, tradition, and custom. This results in considerable variability in the execution of projects and deviation between as-planned and as-executed practices. The current simulation-based planning techniques are limited because they tend to present spatial and temporal characteristics ...

Keywords: Simulation; Virtual Reality; Compaction; Planning

Direction of Arrival of Equipment Sound in the Construction Industry

Kehinde Elelu, Tuyen Le and Chau Le
Pages 63-70

Abstract: The construction industry is often affected by unanticipated struck-by accidents, which often cause severe injuries and fatalities to the workers. Therefore, monitoring and tracking struck-by hazards in terms of the spatial relationship between a worker and a heavy vehicle is crucial to prevent such accidents. Current studies focus on using ...

Keywords: Direction of Arrival; Machine Equipment; Struck-by Accident; Local coordinate

Towards BIM-based robot localization: a real-world case study

Huan Yin, Jia Min Liew, Wai Leong Lee, Marcelo H Ang Jr and Justin Ker-Wei Yeoh
Pages 71-77

Abstract: Conventional mobile robots rely on pre-built point cloud maps for online localization. These map points are generally built using specialized mapping techniques, which involve high labor and computational costs. While in the archi-tectural, engineering and construction (AEC) industry, as-planned building information modelings (BIM) are available for management and operation. In ...

Keywords: BIM; Robot Localization; LiDAR; Deviation

Current State and Future Opportunities of Data Mining for Construction 4.0

Keyi Wu and Borja García de Soto
Pages 78-85

Abstract: In the context of Construction 4.0, the data-intensive nature of the AEC/FM industry puts data-related issues at its core. The powerful ability of data mining to process and utilize data makes it the preferred option for solving data-related problems. Currently, there is no summary of data mining applications in terms ...

Keywords: Knowledge discovery; Digitalization; Automation; Virtualization; Decentralization; Artificial intelligence; BIM; Robot

The Use of Boston Dynamics SPOT in Support of LiDAR Scanning on Active Construction Sites

Eric Wetzel, Junshan Liu, Tom Leathem and Anoop Sattineni
Pages 86-92

Abstract: With the recent commercial availability of autonomous mobility platforms, construction researchers have focused their attention to the application of advanced robotic tools on jobsites. One such mobility platform is Boston Dynamic's robot, "SPOT." The software development kit (SDK) enabled, quadruped robot has the infrastructure to attach interchangeable payloads including LiDAR ...

Keywords: Autonomous Robots; Construction Robotics; Construction Site Monitoring; Data Capture; LiDAR Scanning

Autonomous operation of a robot dog for point cloud data acquisition of scaffolds

Duho Chung, Sunwoong Paik, Juhyeon Kim and Hyungkwan Kim
Pages 93-98

Abstract: Scaffolds are essential temporary structures on construction sites. Since scaffolds are frequently installed and dismantled, the inspection needs to be performed in real-time. This paper proposes a framework to automate the acquisition process of scaffold point cloud data using a robot dog. First, a Simultaneous Localization and Mapping (SLAM) algorithm ...

Keywords: Autonomous Operation; Mobile Laser Scanning; Robot Dog; Real-time Detection; Scaffold

Cluster-based Deterioration Prediction of Composite Pavements with Incorporation of Flooding

Ishan Neema, Fatemeh Banani Ardecani and Omidreza Shoghli
Pages 99-106

Abstract: Natural disasters lead to severe deterioration of valuable highway assets, including pavements that should quickly return to service after extreme events such as flooding. Various prediction models were developed to predict pavement performance for several purposes, including maintenance management, budget allocation, and investment strategy. However, limited studies focused on developing ...

Keywords: Pavement deterioration; Markov Chain; Monte Carlo simulation; Composite pavements; LTPP

Predicting construction productivity with machine learning approaches

Laura Florez-Perez, Zhiyuan Song and Jean C. Cortissoz
Pages 107-114

Abstract: Machine learning (ML) is a purpose technology already starting to transform the global economy and has the potential to transform the construction industry with the use of data-driven solutions to improve the way projects are delivered. Unrealistic productivity predictions cause increased delivery cost and time. This study shows the application ...

Keywords: Machine learning; Labour productivity; Construction; Crew management

Automated Checking of Scaffold Safety Regulations using Multi-Class 3D Segmentation

Jeehoon Kim, Juhyeon Kim, Nahye Koo and Hyoungkwan Kim
Pages 115-119

Abstract: Scaffolds, one of the most widely used temporary structures, are prone to safety-related accidents. Despite the fact, checking regulations for a scaffold is manually being conducted, which is inefficient, especially for a large construction site. This paper proposes an automated method to check safety regulations regarding scaffolds on sites. 3D ...

Keywords: Deep learning; Scaffold; Point cloud; Semantic Segmentation; Safety regulation checking; Terrestrial Laser Scanning (TLS)

A Systematic Classification and Evaluation of Automated Progress Monitoring Technologies in Construction

Varun Kumar Reja, Megha S Pradeep and Koshy Varghese
Pages 120-127

Abstract: Progress monitoring is one of the essential tasks while executing a construction project. Effective monitoring will lead to an accurate and timely analysis of the project's progress which is required to make vital decisions for project control. On the other hand, inefficient and delayed updates regarding the project's progress, which ...

Keywords: Progress monitoring technologies; Data acquisition; BIM; Internet of Things (IoT); Sensors; Computer vision; Extended reality; Literature review; Challenges; Limitations

Reducing spatial error in mobile laser scanning by real-time uncertainty visualization and human-machine interaction

Maciej Trzeciak, Chris Burgoyne and Ioannis Brilakis
Pages 128-135

Abstract: Scanning is a key element for many applications in the AECO industry. It provides point clouds used for construction quality assurance, scan-to-BIM workflows and construction surveys. However, data acquisition using static laser scanners or photogrammetry methods is lengthy and requires even lengthier subsequent processing. A quick and apparent escape from ...

Keywords: Mobile mapping; SLAM; Digitization; Pose graph; Uncertainty visualization; Uncertainty propagation; Human-machine interaction

Toward Automation in Crack Detection and Measurements: Benchmarking of CNN-based Algorithms

Donghoon Ji, Yelda Turkan and Paolo Calvi
Pages 136-143

Abstract: Cracks are one of the main defect features on concrete surfaces, and indicators of concrete structures' condition regarding their state of health. Since traditional methods to identify and assess cracks rely on manual measurements, a significant number of studies to date have focused on identifying ways to automate this process. ...

Keywords: Crack Detection; Crack Measurement; Image Morphological Operation; Convolutional Neural Network (CNN); Skeletonization

Innovative Model for Forecasting Trailer Usage for Prefabricated Exterior Wall Panels

Andrew Rener, Aslihan Karatas and Matthew Cole
Pages 144-151

Abstract: With growing demand for large scale exterior envelope prefabrication solutions beyond precast concrete, Engineer-to-Order (ETO) prefabrication firms must develop reliable methodologies to manage finish goods inventory of large components. The imbalance between fabrication time and installation requires ETOs to forecast likely consumption of transportation resources at the proposal stage with ...

Keywords: Prefabrication; Offsite Construction; Exterior Wall Panels; Logistics; Estimating; Supply Chain

Automated Wall Detection in 2D CAD Drawings to Create Digital 3D Models

Chialing Wei, Mohit Gupta and Thomas Czerniawski
Pages 152-158

Abstract: Generating digital 3D buildings models from scratch is time consuming and labor intensive. In this paper, we present an automated detection process leveraging computer vision and the information available in 2D drawings to reduce 3D modeling time. The recognition system is limited to walls and has two parts: (1) Image ...

Keywords: Deep Learning; Image Classification; Object Detection; 2D Drawings; 3D Building Models

IFC-based Information Extraction and Analysis of HVAC Objects to Support Building Energy Modeling

Hang Li and Jiansong Zhang
Pages 159-166

Abstract: The heating, ventilation, and air conditioning (HVAC) system is a highly complex part of a building that requires high specialty and expertise to understand and analyze for energy modelling and simulation purposes. Significant manual effort is needed for information extraction from the mechanical designs, to support the creation of an ...

Keywords: Building Information Modeling (BIM); Building Energy Modelling (BEM); Heating, Ventilation, and Air Conditioninng (HVAC); Industry Foundation Classes (IFC); Automation; Information Extraction; Interoperability

Systematic Literature Review of Building Information Modelling and Green Building Certification Systems

Oludolapo Olanrewaju, Wallace Enegbuma and Michael Donn
Pages 167-174

Abstract: The rapid pace of technological transformation in sustainability assessment in the construction industry has directed the development of tools and policies. Building information modelling (BIM)-based documentation processes for green building certification systems (GBCS) credits continually require re-assessments. The relationship between BIM and GBCS is minimal in the current literature, which ...

Keywords: Building information modelling; BIM; Green building certification system; Net-zero buildings; Systematic literature review; Sustainability

Information Extraction from Text Documents for the Semantic Enrichment of Building Information Models of Bridges

Phillip Schönfelder, Tariq Al-Wesabi, Andreas Bach and Markus König
Pages 175-182

Abstract: The majority of innovative approaches in the realm of the retrospective generation of building information models for existing structures deal with geometry extraction from point clouds or engineering drawings. However, many building-specific or object-specific attributes for the enrichment of building models cannot be inferred from these geometric and visual data ...

Keywords: Building information modeling; Information extraction; Semantic enrichment; Natural language processing; Named entity recognition; Machine learning

BIM-Integration of Light Construction Equipment

Maximilian Schöberl, Sebastian Offinger, Theo Goldfuß, Stephan Kessler and Johannes Fottner
Pages 183-190

Abstract: BIM (Building Information Modeling) has become increasingly important in recent years. At the center of BIM is the digital information model of a building. While such information models are already used intensively in building construction for small-scale robotic applications, digital models are only used for large-scale measures and machines in ...

Keywords: BIM; DTM; civil engineering; digital construction; light construction equipment; information models

Visualisation and graph-based storage of customised changes in early design phases

Daniel Napps, Ata Zahedi, Markus König and Frank Petzold
Pages 191-198

Abstract: Building Information Modeling (BIM) was conceived as a working method for networked planning using software assistance. Multiple stakeholders in the construction industry are involved in the design and management of digital representations of the physical and functional characteristics of a facility in the BIM model. Design variant management coupled ...

Keywords: Building Information Modeling (BIM); Industry Foundation Classes (IFC); Early Design Phases; Design Decisions; Graph Representation; Design Episodes; Variant Types; Plugin

Conceptual Modeling of Lifecycle Digital Twin Architecture for Bridges: A Data Structure Approach

Inga Maria Giorgadze, Faridaddin Vahdatikhaki and Hans Voordijk
Pages 199-206

Abstract: The concept of Digital Twin (DT) has emerged in recent years to facilitate the use of Building Information Modeling during the entire projects' lifecycle. In the DT concept, cyber-physical system theory is utilized to collect condition data about an existing asset and then integrate this data into the digital model. ...

Keywords: Digital twin; Lifecycle digital twin; Bridge information modelling; Ontological modelling

Towards the development of a digital twin for subsoil monitoring and stability against overturning of a mobile drilling rig

Francisco Williams Riquer, Duy Anh Dao and Jürgen Grabe
Pages 207-214

Abstract: Mobile drilling rigs are particularly susceptible to over-turning due to the high location of their centre of mass. In some cases, overturning occurs due to a failure in the subsoil. Until now, machine operators are solely responsible for mon-itoring the machines' stability, and assessment of dangerous conditions is based mainly ...

Keywords: Digital Twin (DT); Multibody simulations (MBS); Stabil-ity of mobile drilling rigs; Settlement prediction; Monitoring of bearing capacity

Closing the Gap Between Concrete Maturity Monitoring and Nonlinear Time-dependent FEM Analysis through a Digital Twin. Case Study: Post-tensioned Concrete Slab of an Office Building, Barcelona, Spain

Héctor Posada, Rolando Chacón, Lucian-Constantin Ungureanu, David García
Pages 215-222

Abstract: This paper proposes a pipeline for the automation of data between two realms: i) simulation, in a fully nonlinear, and time-dependent structural analysis model and, ii)concrete maturity monitoring data from the construction site. The connection enables an information construct understood for its use within the Digital Twin of the ...

Keywords: Digital Twin; Concrete Maturity; BIM; Sensor-based Data; Mobile App; Nonlinear Finite Element Analysis

ColombiaClass: proposal for a BIM Classification System for public buildings in Colombia

María Del Pilar Revuelta Mendoza, Nelly Paola Garcia Lopez and Luis Arturo Salazar Fica
Pages 223-230

Abstract: The use of standardized BIM Classification Systems helps to improve the efficiency of the tendering, planning, and control of construction projects. The Colombian government has identified BIM as a key strategy to help increase the construction industry's productivity and improve value for money in public works projects. At the core ...

Keywords: Building Information Modelling; BIM Classification Systems; Colombian BIM Classification System; Public works; National BIM strategy; ColombiaClass

Towards Automated Pipelines for Processing Load Test Data on a HS Railway Bridge in Spain using a Digital Twin

Carlos Ramonell and Rolando Chacón
Pages 231-237

Abstract: This document presents an automated pipeline to process sensor-based data produced during load tests on digitally twinned HS railway bridges. The research is developed within the frame of the H2020 European project ASHVIN, related to Assistants for Healthy, Safe, and Productive Virtual Construction, Design, Operation & Maintenance using Digital ...

Keywords: Digital Twin; IoT; Load Tests; BIM; Automated Pipeline; Data processing; Event-based Microservice Architecture

Potentials of 5D BIM with Blockchain-enabled Smart Contracts for Expediting Cash Flow in Construction Projects

Jong Han Yoon and Pardis Pishdad-Bozorgi
Pages 238-245

Abstract: The low level of digitization in sharing information and the fragmented processes in the construction supply chain negatively affects cash flow across the supply chain, resulting in non- and late-payment issues. Even though a cloud-based 5D BIM platform and Blockchain-enabled smart contracts have the potential to address the issues, their ...

Keywords: 5D BIM; Automation; Blockchain; Smart Contract; Construction Payment

Integrating Digital Twins in Construction Education Through Hands-on Experiential Learning

Steven Kangisser, Javier Irrazary, Kelly Watt, Richard Borger and Amadeus Burger
Pages 246-252

Abstract: This paper examines the value of including digital twin technology as a hands-on learning activity in a graduate-level building construction course. The methodology of teaching digital twins as a unit is presented, and the benefits of introducing this topic are examined within the framework of several learning objectives. The campus ...

Keywords: Digital Twins; BIM; Asset Management; Facility Management; Preventative Maintenance; Digital Transformation

Benefits of Open Infra BIM - Finland Experience

Rauno Heikkilä, Tanja Kolli and Teppo Rauhala
Pages 253-260

Abstract: The achieved benefits of Open Infrastructure BIM in Finland have been studied. The newest concept of Open InfraBIM in Finland is introduced. Industrial experiences and observed remarkable benefits in three large-size infrastructure design and construction projects carried out in 2012-2022 are presented and evaluated. Based on the observations and achieved ...

Keywords: Benefits; Model Sharing; Open InfraBIM; InfraBIM Requirements

The Neural Basis of Risk Attitude in Decision-Making Under Risk: fNIRS investigation of the Simulated Electrical Construction Task

Shiva Pooladvand, Deha Ay and Sogand Hasanzadeh
Pages 261-267

Abstract: Risk propensity, or individuals' attitude toward risk, can highly impact individuals' decision-making in high-risk environments since those who merely focus on positive consequences associated with high-risk acts are more likely to engage in risk-taking behaviors. Previous studies identified activation in the prefrontal cortex during decision-making under risk to be a ...

Keywords: Risk attitude; Construction safety; Decision-making; Risk-taking behavior; fNIRS neuroimaging; Mixed-reality (MR)

Toward Personalized Safety Training: Automating the Classification of Construction Workers' Cognitive Failures

Kyeongsuk Lee, Yugandhar Shinde, Sogand Hasanzadeh and Behzad Esmaeili
Pages 268-275

Abstract: Safety training has long been considered a promising method to enhance workers' hazard identification skills within construction sites. To improve the effectiveness of safety training, such varied features as a training environment, individuals' learning ability, and lesson personalization have been investigated. However, as records show workers still miss hazards even ...

Keywords: Hazard identification; Construction safety; Cognitive failures; Personalized safety training; Attentional failure; Inattentional blindness; Risk Perception

iVisit-Collaborate: Online Multiuser Virtual Site Visits Using 360-Degree Panoramas and Virtual Humans

Ricardo Eiris and Masoud Gheisari
Pages 276-282

Abstract: Construction professionals need to understand collaboration within the context of jobsites. Consequently, many construction programs utilize learning activities to enable student learning of collaboration. One of those key learning activities used by construction programs is site visits. Although site visits are greatly beneficial for students, these present several challenges to ...

Keywords: Site Visits; Collaboration; 360-degree Panoramas; Virtual Reality; Construction Education

Vulnerability Assessment of Construction Equipment: An Example for an Autonomous Site Monitoring System

Muammer Semih Sonkor, Xinghui Xu, Samuel A. Prieto and Borja García de Soto
Pages 283-290

Abstract: The digital transformation of the construction industry is accelerating with the advances in information technology (IT) and operational technology (OT) and their convergence. While the benefits of such transformation in construction are apparent, cybersecurity aspects are usually overlooked. Cyber-attacks against project information can cause the exposure of confidential project data, ...

Keywords: Construction 4.0; Cybersecurity; Cyber-Physical Systems; Vulnerability Assessment; Construction Robots

Fire Evacuation and Management Model Based on Building Information Modeling and Virtual Reality

Ren-Jie Gao, Kun-Chi Wang, Xiang-Hao Lai and Wei-Hsiang Hung
Pages 291-296

Abstract: Fire management is a key aspect of building management. During a fire, the primary reason why evacuees cannot evacuate in time and causalities occur is their lack of familiarity with the evacuation route. In practice, two dimensional images or videos are used as aids for firefighting educational training. However, they ...

Keywords: Fire evacuation; Building information modeling (BIM); Virtual reality (VR)

Evaluation of Construction Site Layout Using Virtual Reality Linked with 3D CAD and Body Tracking

Hidetoshi Tsuda and Kosei Ishida
Pages 297-303

Abstract: Lately, virtual reality (VR) is being investigated for the field of construction. VR enables investigation from a stage where there is no actual object. The most common approach in VR is interaction with a controller. Therefore, the sense of body movements is often far from reality. Reflecting actual body ...

Keywords: Virtual Reality; Construction Training; Tracking; Simulation; Parametric Modeling; Buildability

Automated Recognition of Hand Gestures for Crane Rigging using Data Gloves in Virtual Reality

Aparna Harichandran and Jochen Teizer
Pages 304-311

Abstract: Construction safety training through Virtual Reality (VR) environments offers workers an interactive and immersive experience. Many complex interactions and realistic scenarios are possible in VR using accessories such as data gloves and trackers which allow data recording on incidents. For example, misinterpretation of hand signals construction workers give during operations ...

Keywords: Gesture recognition; Virtual reality; Construction safety; Safety training; Data gloves; Hand motion tracking

A Knowledge Graph for Automated Construction Workers' Safety Violation Identification

Yifan Zhu and Xiaowei Luo
Pages 312-319

Abstract: Identifying workers' safety violations on construction job sites is critical for improving construction safety performance. The advancement of sensing technologies makes automatic safety violation detection possible by encoding the safety knowledge into computer programs. However, it requires intensive human efforts in turning safety knowledge into computer rules, and the hard-coded ...

Keywords: nowledge Graph; Natural Language Processing; Construction Safety; Workers' Safety Violation

Wearable Technology for Highway Maintenance and Operation Safety: A Survey of Workers' Perception and Preferences

Sepehr Sabeti, Omidreza Shoghli, Nichole Morris and Hamed Tabkhi
Pages 320-327

Abstract: Securing the safety of highway work zones is one of the most pressing issues in the highway maintenance and oper-ation community. Recent studies have indicated that high-way workers keep suffering from fatal injuries and death caused by traffic, long-night shifts, and limited space for ma-neuvering. In the meantime, recent advances ...

Keywords: Wearable Technology; Highway Work Zones; Safety; User Experience; Worker-centered Design

Integrated Sensor-Based Interface for Human-Robot Collaboration in Construction

Xin Wang, Dharmaraj Veeramani and Zhenhua Zhu
Pages 328-335

Abstract: Construction robots have the potential to increase construction productivity at job sites and can help overcome industry challenges such as labor shortage and safety risks. User-friendly interfaces are critical for advancing human-robot work collaboration and increasing use of construction robots. However, human-robot interfaces in the context of construction industry applications ...

Keywords: Wearable Sensors; Eye Tracking; Hand Gesture Recognition; Human-Robot Interface

Requirements analysis of additive manufacturing for concrete printing - A systematic review

Patricia Peralta Abadia and Kay Smarsly
Pages 336-343

Abstract: The acceptance of concrete printing as a viable construction method is limited because of a lack of expertise and due to the heterogeneous and non-standardized nature of additive manufacturing (AM) data modeling, affecting the reliability and the interoperability of the concrete printing process. To advance standardization of AM data modeling ...

Keywords: Additive manufacturing (AM); Concrete printing; Data modeling; Information exchange requirements; Requirement analysis

Safety Risk Assessment of Drones on Construction Sites using 4D Simulation

Zixian Zhu, Idris Jeelani and Masoud Gheisari
Pages 344-351

Abstract: The use of drones in the construction industry has been dramatically growing in different areas such as building inspection, site mapping, and safety monitoring. The increasing deployment of drones in construction leads to more collaboration and interaction between human workers and drones. This raises novel occupational safety issues, especially for ...

Keywords: Drones; 4D Simulation; Safety; Risk Assessment; Construction Sites

Progress Estimation of an Excavation Pit

Axel Vierling, Tobias Groll, Dennis Meckel, Kristina Heim, Daniel Walter, Lukas Scheidhauer, Karsten Körkemeyer and Karsten Berns
Pages 352-358

Abstract: This paper presents a method for automated excavation speed and progress estimation. First, a measure for the progress speed of an excavation pit is taken from the lit-erature and evaluated regarding the possibility for automa-tion. For each possible parameter, an automated extraction algorithm is presented. The used system is an ...

Keywords: Excavation; Progress Estimation; Autonomous System; Sensors

Impact of Passive Back-Support Exoskeletons on Manual Material Handling Postures in Construction

Ali Golabchi, Linda Miller, Hossein Rouhani and Mahdi Tavakoli
Pages 359-366

Abstract: Work-Related Musculoskeletal Disorders (WMSDs) are a leading contributor to workplace injuries in the construction industry, with the lower back being the most affected body part. To mitigate WMSDs, exoskeletons have been developed and recently introduced to industrial job sites to provide workers with assistance and support, reducing exposure to ergonomic ...

Keywords: Exoskeleton; Exosuit; Wearable Robot; Manual Material Handling; Ergonomics; Posture; Construction

Stag hunt game-based approach for cooperative UAVs

Lanh Van Nguyen, Ignacio Torres Herrera, Trung Hoang Le, Duong Manh Phung, Ricardo Patricio Aguilera and Quang Phuc Ha
Pages 367-374

Abstract: Unmanned aerial vehicles (UAVs) are being employed in many areas such as photography, emergency, entertainment, defence, agriculture, forestry, mining and construction. Over the last decade, UAV technology has found applications in nu-merous construction project phases, ranging from site map-ping, progress monitoring, building inspection, damage as-sessments, and material delivery. While extensive ...

Keywords: Unmanned aerial vehicle; Cooperative path planning; Stag hunt game; Payoff-dominant equilibrium; Particle swarm optimization

Reinforcement learning with construction robots: A review of research areas, challenges and opportunities

Xinghui Xu and Borja García de Soto
Pages 375-382

Abstract: The interest in the use of robots in the construction industry has been around for several decades; however, the advancement of technology for related applications has been slow. Considering that most construction robots are not fully automated and require extra guidance and instructions from the operators, an autonomous way for ...

Keywords: Construction robot; Deep reinforcement learning; Multi-agent; Task allocation; Path planning

Constrained Control Scheme for the Manipulation of Heavy Pre-fabricated Elements with Lightweight Robotic Arm

Michele Ambrosino, Fabian Boucher, Pierre Mengeot and Emanuele Garone
Pages 383-390

Abstract: Building activities involving heavy suspended elements are one of the construction activities with the highest level of danger. Typically, during these activities, one or two masons work in conjunction with a machine such as a crane or a lift-ing machine. Several robotics solutions have been proposed to replace the masons ...

Keywords: Robotics; Cooperative Robotic Systems; Building Activity; Robots for Construction; Constrained Control Scheme

Importance of a 5G Network for Construction Sites: Limitation of WLAN in 3D Sensing Applications

Hyung Joo Lee, Ajith Krishnan, Sigrid Brell-Cokcan, Janina Knußmann, Maximilian Brochhaus, Robert H. Schmitt, Johannes J. Emontsbotz and Johannes Sieger
Pages 391-398

Abstract: Teleoperated construction machinery dominates construction sites, as it can, with relatively little effort, prevent operators from working in dangerous conditions by keeping them in the control loop. However, the operators usually have to execute tasks with limited situational information due to poor depth perception from 2D camera images, reducing local ...

Keywords: Robot-Assisted Construction; Construction Robots; Auto-mated Construction; 5G Network

Path Generation for Foam Additive Manufacturing of Large Parts with a Cable-Driven Parallel Robot

Elodie Paquet, Marceau Metillon, Kevin Subrin, Benoit Furet and Stéphane Caro
Pages 399-405

Abstract: In this paper, a framework for foam printing with a Cable-Driven Parallel Robot (CDPR) is described for building large parts. Compared with the traditional robotic systems, CD-PRs have a large workspace that can include the printing area. In addition, the potential reconfigurability of CDPRs is an asset to get rid ...

Keywords: Additive Manufacturing; Cable-Driven Parallel Robot; Innovative Construction

Automated material selection based on detected construction progress

Tyler Stephans, Austin McClymonds, Robert Leicht and Alan Wagner
Pages 406-413

Abstract: One of the many ways in which automation may help the construction industry is on-site material management. This paper presents an automated process where materials are selected for staging by detecting construction progress from site images. The materials are then delivered to their re-spective workface locations by a robot. The ...

Keywords: Automated material delivery; Progress detection; BIM; Robot

Solution Kits for automated and robotic façade upgrading

Kepa Iturralde, Thomas Bock, Philip Zimmermann, Renzo G. Bazan Santos, Samanti Das, Wenlan Shen, Mahruk Malik, Steven Maio, Agi Hidri and Juncheng Shen
Pages 414-421

Abstract: In order to reach zero energy consumption of the current building stock, adding a new insulating envelope with Renewable Energy Sources onto the existing building is necessary. This can be achieved by using prefabricated modules, automation and robotics. Since the topic is complex, three main subcategories were defined: Data Flow, ...

Keywords: Renovation; Prefabrication; Accuracy; Time

Concept of a Robot Assisted On-Site Deconstruction Approach for Reusing Concrete Walls

Hyung Joo Lee, Christoph Heuer and Sigrid Brell-Cokcan
Pages 422-429

Abstract: Construction and Demolition Waste (CDW) is one of the major waste streams in the EU by mass, accounting for 374 million tons in 2016 (excluding excavated soil), and is made up of a variety of components. Many of them can include dangerous materials and pose specific concerns to the environment ...

Keywords: Robot-assisted deconstruction; Construction robots; Reusing construction material; Automated deconstruction

Subjective Evaluation of Passive Back-Support Wearable Robot for Simulated Rebar Work

Nihar Gonsalves, Mohamad Khalid, Abiola Akinniyi, Omobolanle Ogunseiju and Abiola Akanmu
Pages 430-436

Abstract: Work-related musculoskeletal disorders continue to be a severe problem in the construction industry. Rebar workers are exposed to ergonomic risks such as repetitive stooping and forward bending resulting in low back injuries. Wearable systems such as back support exoskeletons are emerging as potential solution to reducing the risk of low ...

Keywords: Wearable robot; Rebar work; Usability; Discomfort

Industry Perspectives of the Potential of Wearable Robot for Pipe Installation Work

Nihar Gonsalves, Mohamad Khalid, Abiola Akinniyi and Abiola Akanmu
Pages 437-443

Abstract: The physically demanding nature of construction work exposes workers to ergonomic risks resulting back-related musculoskeletal disorders. Back injuries amongst pipe installers increased by 2.3 times in the last year. Back support exoskeletons are emerging as a potential intervention to address back injuries. Without willingness of construction workers to use back-support ...

Keywords: Wearable robot; User assessment; Pipe installation; Exoskeletons

Development of Framework for Highway Lawn Condition Monitoring using UAV Images

Yeseul Kim, Seongyong Kim, Yosuke Yajima, Javier Irizary and Yong K. Cho
Pages 444-450

Abstract: Planning, monitoring, and maintenance of highway assets is an essential, long-term operation for successful civil infrastructure management. These monitoring and maintenance activities are usually carried out manually, suffering from time-consuming, costly, potentially dangerous tasks. The advancements in Unmanned Aerial Vehicles (UAVs) and computer vision technologies have demonstrated the potential to ...

Keywords: Civil infrastructure management; Computer-vision; UAVs; Deep Learning; Lawn mowing condition assessment

YAKE-Guided LDA approach for automatic classification of construction safety reports

Hrishikesh Gadekar and Nikhil Bugalia
Pages 451-458

Abstract: Identifying efficient processes for classifying text-based safety reports using Machine-Learning (ML) is an essential area of research. However, much of the previous work on the topic relies on supervised learning approaches, which are often manually intensive and require large volumes of pre-labeled data. To achieve reduced requirements for human intervention ...

Keywords: Unsupervised machine learning; Construction safety; Text classification; Topic modeling

Automated Construction Contract Summarization Using Natural Language Processing and Deep Learning

Xiaorui Xue, Yiru Hou and Jiansong Zhang
Pages 459-466

Abstract: The interpretation of construction contracts is crucial to the management and success of a project. Correct and accurate interpretation could support the smooth construction of high-quality built assets. Misunderstanding and omissions may lead to costly rework and delay. One main challenge of construction contract interpretation lies in the length of ...

Keywords: Deep Learning; Automated Construction Contract Summarization; Text Summarization; Natural Language Processing; Artificial Intelligence; Construction Management

Construction Progress Monitoring and Reporting using Digital Images and Computer Vision Techniques - A Review

Dena Shamsollahi, Osama Moselhi and Khashayar Khorasani
Pages 467-474

Abstract: In complex and dynamic construction sites, efficient progress monitoring and reporting play an important role in preventing schedule delays and cost overruns. Such reporting requires detailed and accurate records from job sites to help project managers in comparing project's current state to its as-planned state for enabling timely corrective actions. ...

Keywords: Progress Monitoring; Computer Vision; Object Detection; 3D Scene Reconstruction

BIM, Twin and Between: a Conceptual Engineering Approach to Formalize Digital Twins in Construction

Fabiano Correa
Pages 475-482

Abstract: Construction is looking closely as Industry 4.0 paradigm (I4.0) transforms many processes in Manufacturing. Technologies associated with I4.0 were born out of the ever-present necessity of automation (and integration) on the shop floor, as well as of better management in product lifecycle with computer-aided software. Although indeed relevant outside Manufacturing, ...

Keywords: BIM; Digital Twin; Simulation; Industry 4.0

Inspection Data Exchange and Visualization for Building Maintenance using AR-enabled BIM

Jisoo Park, Soowon Chang, Hyungi Lee and Yong Cho
Pages 483-490

Abstract: After the COVID-19 outbreak, a new concept of building maintenance (BM) systems is needed because current approaches highly rely on physical contact between workers, engineers, and managers. It imposes health and safety risks as increasing concerns about infections and spreads. This adds burdens to take unavoidable close contact and health ...

Keywords: BIM; AR; CPS; Building Maintenance System

Comparison of TLS and Photogrammetric 3D Data Acquisition Techniques: Considerations for Developing Countries

Eyob Mengiste, Samuel A. Prieto and Borja García de Soto
Pages 491-494

Abstract: With the use of digital data, in conjunction with technologies such as BIM and digital twin, construction professionals have the ability to monitor the progress efficiently and perform detailed quality assessments. The rapid development of multiple data acquisition technologies, such as terrestrial laser scanning (TLS) and photogrammetry techniques, has allowed ...

Keywords: Construction 4.0; Terrestrial Laser Scanning; Photogrammetry; BIM; Construction Robots

Mud Dauber: Prototype of the Mobile Gantry Architecture

Peter Staritz, Josiah McClurg, Caleb Miller, Moriah Schlenker and Shane Wozniak
Pages 495-499

Abstract: The Mobile Gantry is a robot architecture in which a rail-less gantry rolls directly on the unprepared planetary surface. Mud Dauber is a prototype of this architecture developed to enable testing of the concept and understand the capabilities and limitations of the architecture. This paper describes the major ...

Keywords: 3D Printing; Sulfur Concrete; Mobile Gantry; Robot Architecture; Mars

Model driven method for crack detection in robotic inspection

Erika Pellegrino and Tania Stathaki
Pages 500-503

Abstract: Nowadays civil infrastructure is exposed to several chal-lenges such as daily vehicular traffic and extreme weather conditions. It is well known that these may determine struc-tural deterioration and damages, which can even cause catas-trophic collapses related to significant socio-economic losses. For this reason automatic inspection and maintenance are expected to ...

Keywords: Machine Vision; Smart Infrastructure; High Performance Computing

A Case Study: Conception of digitalizing prefabrication processes in the construction industry

Zhen Cai, Mohamed Ben Tarfaoui, Stephan Kessler and Johannes Fottner
Pages 504-507

Abstract: uring the last few years, the importance of prefabrication and its digitalization has grown significantly in the construc-tion industry. In this context, a German construction com-pany intended to extend an existing warehouse application into a system that additionally monitors production time to identify the bottleneck. In this case study, a ...

Keywords: Prefabrication; Modular Housing; Digitalization; RFID; Bluetooth

On the Bar Installation Order for the Automated Fabrication of Rebar Cages

Mahdi Momeni, Johan Relefors, Lars Pettersson, Alessandro Vittorio Papadopoulos and Thomas Nolte
Pages 508-511

Abstract: Robotics automation is a promising solution for the fab-rication of structures made out of reinforced concrete. The reinforcement is often installed directly in the form and bar-by-bar. Using bigger pre-fabricated units (cages) may be ben-eficial for saving construction time and better labor safety. In this paper, we focus on the ...

Keywords: Robotics for construction; Rebar installation; Automation

A Taxonomy for Connected Autonomous Plant

Cormac Browne, Ross Walker, Tim Embley, Muneer Akhtar, Amer Essa, Anette Pass, Simon Smith and Alex Wright
Pages 512-519

Abstract: National Highways commissioned the development of a Roadmap for Connected and Autonomous Plant (CAP), which proposed a programme of activities which would aim to deliver the widespread deployment of CAP. A particu-lar milestone activity identified as an early target within the Roadmap was the development of a taxonomy for under-standing ...

Keywords: Connected Autonomous Plant (CAP); Taxonomy; Au-tomation; Autonomy; Plant

Digital Commissioning Processes for the Oil and Gas Sector

Daniel Luiz de Mattos Nascimento, Alessandra Brancher Roeder, Diego Calvetti, Alexander Chavez Lopez, Fernando Rodrigues Gonzalez and Flavio Araujo
Pages 520-523

Abstract: Oil and Gas (O&G) projects have complex engineering endeavours. A digital information management process is vital to increasing efficiency due to projects' size and complexity. The industrial plants' commissioning is regarding on-site testing to check performance and ensure final compliance of all equipment and systems installed. On-site commissioning procedures are ...

Keywords: O&G; Commissioning; Digitalisation; Processes

Overview of the State-of-Practice of BIM in the AEC Industry in the United States

Hala Nassereddine, Makram Bou Hatoum and Awad Hanna
Pages 524-531

Abstract: The Architecture, Engineering, and Construction (AEC) industry has undergone a significant and radical transformation in its design and documentation process as it evolved from the days of the drafting board to today's Building Information Modeling (BIM) process. As BIM remains the center of this transformation, it is important to keep ...

Keywords: Building Information Modeling; BIM; AEC Industry; Construction Projects; Usage; Practices; Users; Construction 4.0; Construction Project Lifecyle

Machine Learning for Construction Process Control: Challenges and Opportunities

Bharath Sankaran
Pages 532-535

Abstract: One of the primary drivers of inefficiencies plaguing con-struction projects world over is the lack of efficient process control in the construction process. This paper explores the idea of construction process control through BIM based qual-ity control. It discusses the challenges of practically imple-menting BIM based quality control on a ...

Keywords: BIM; 3D Machine Learning; Laser Scanning; Process Control

5G Wireless Communication for Autonomous Excavation

Rauno Heikkilä, Matti Immonen, Heikki Keränen, Olli Liinamaa, Esa Piri and Tanja Kolli
Pages 536-541

Abstract: The applicability of wireless 5G network to the information communication needs of autonomous excavations is studied. An autonomous excavator developed by the University of Oulu is used for the experiments in a 5G test network at the Linnanmaa Campus of the University of Oulu. In the experiments, remote and autonomous ...

Keywords: Wireless network; Autonomous excavator; 5G

The Use of Drones in the Construction Industry: Applications and Implementation

Makram Bou Hatoum and Hala Nassereddine
Pages 542-549

Abstract: In a volatile, uncertain, complex, and ambiguous world, Industry 4.0 can be the silver lining of the construction industry which has been facing daunting chronic problems for decades. The transformative impact of Industry 4.0 which has been well documented in the industrial sector has spurred interested among construction researcher to ...

Keywords: Construction 4.0; Technology; Drones; Unmanned Aerial Vehicles; UAV; Unmanned Aerial System; UAS; Remotely Piloted Vehicles; RPV; 5W2H

Intelligent BIM-based spatial conflict simulators: A comparison with commercial 4D tools

Leonardo Messi, Borja García de Soto, Alessandro Carbonari and Berardo Naticchia
Pages 550-557

Abstract: In construction projects, the space required for executing each activity is unanimously recognized as a limited but renewable resource, like workers, equipment, and materials. Overloading a given resource space, as demonstrated by statistics, leads to efficiency losses and safety threats. Despite the valuable contributions provided by academics and the construction ...

Keywords: Construction Management; Workspace Scheduling; Spatial Conflicts; BIM; Game Engine; 4D tool

BIM-assisted, automated processes for commissioning in building services engineering

Ralf Becker, Christoph Blut, Christoph Emunds, Jérôme Frisch, Dirk Heidermann, Tristan Kinnen, Alexander Lenz, Michael Möller, Nicolas Pauen, Tobias Rettig, Dominik Schlütter, Matthias Wenthe, Jörg Blankenbach, Günter Bleimann-Gather, Johannes Fütterer, Jörg Jungedeitering and Christoph van Treeck
Pages 558-565

Abstract: State-of-the-art building energy systems exhibit a high technical complexity. In the commissioning phase, technical building elements (TBE) are put into operation trade-by-trade and as linked complete systems. Besides the correct wiring on component level, instantiating the building automation and detecting errors is a cumbersome process in practice. The paper addresses ...

Keywords: Building Information Modeling; Technical building equipment; Data capturing; Indoor positioning; Virtual and Augmented Reality

Blockchain-supported design tool on building element scale

Goran Sibenik, Marijana Sreckovic, Thomas Preindl, Martin Kjäer, and Wolfgang Kastner
Pages 566-573

Abstract: Sharing building data or building models still represents a problem within design practices in the architecture, engineering and construction industry. Additionally, digitalization, automation or traceability of processes face numerous workflows and changing stakeholder constellations, with multiple software tools escaping the scopes of common data environments or similar digital solutions. Vague ...

Keywords: Blockchain; Baseline; CDE; BIM; design workflow

Digital Transformation in Asset Management - A Case of BIM Adoption in New Zealand Local government

John Jiang, Theuns Henning and Yang Zou
Pages 574-581

Abstract: Digital technologies are taking place in all spheres of the society and affecting every business sector including the construction industry. As a key player of the industry, local government in New Zealand invests in numerous digitalised Asset Management Information Systems (AMIS) in order to efficiently and effectively manage its infrastructure ...

Keywords: Asset Management Information System; BIM; Digital Transformation; Common Data Environment; Local Government

Project-based curriculum for teaching construction robotics

Cynthia Brosque and Martin Fischer
Pages 582-589

Abstract: As innovations in construction robotics are being tested and deployed on site thanks to technological advancements in computing and sensing, Civil Engineering researchers must consider how to connect real-world innovations with research and teaching at a much faster pace. Observing the practice helps identify problems and test engineering solutions and ...

Keywords: Construction Robotics; Education; Automation; Construction Management

A case-based reasoning technique for evaluating performance improvement in automated construction projects

Krishnamoorthi Sundararaman and Benny Raphael
Pages 590-596

Abstract: Automation of construction processes facilitates increased productivity and overall higher project performance. This paper presents a methodology for comparative assessment of different construction processes and selection of an optimal solution based on appropriate automation implementation. Construction processes are quantitatively evaluated using a methodology combining case-based reasoning and compositional modeling. Through ...

Keywords: Case Based-Reasoning; Compositional Modeling; Discrete Event Simulation; Construction automation; Level of Automation; Therbligs; Project Performance Improvement

The Optimized Process for Effective Decision Makings to Minimize Fall From Height (FFH) Accidents on Construction Site

Qinghao Zeng and Jong Han Yoon
Pages 597-604

Abstract: As one of the most hazardous industries, the construction sector is specifically dangerous due to its dynamic and unexpected working conditions. Among all the occupational risks, Fall From Height (FFH) accidents remain the riskiest ones for a long time, resulting in a huge loss for projects. Although numerous technologies have ...

Keywords: Fall from height; Construction safety issues; Technological solutions; Improved system process flow

Construction Robotics Excellence Model: A framework to overcome existing barriers for the implementation of robotics in the construction industry

Jan-Iwo Jäkel, Shervin Rahnama and Katharina Klemt-Albert
Pages 605-613

Abstract: The construction industry is characterized by low productivity and inefficient processes. In addition, the level of digitalization and automation in this industry is low compared to other industries. Although the added values of using robots in the industry have been known for a long time and the technology has been ...

Keywords: Robotics; Barriers; Construction Robotics Excellence Model

State of Advances in Reality Capture for Construction Progress Monitoring and Documentation

Jordan Grogan, Anoop Sattineni and Jeff Kim
Pages 614-621

Abstract: Construction documentation is necessary on every project. Information captured must be accurate, timely and actionable. With several technologies and techniques available, the aim of this study is to determine the current state of the industry on this topic. The objectives of this study are to investigate the status of construction ...

Keywords: Progress Monitoring; Reality Capture; As-Built Documentation; 360 photography; Drones; Laser Scanning

An Approach for Estimation of Swing Angle and Digging Depth During Excavation Operation

Amirmasoud Molaei, Marcus Geimer and Antti Kolu
Pages 622-629

Abstract: This paper discusses the estimation of the swing angle and digging depth during the excavation operation. The abil-ity to calculate the excavator's productivity is an essential step toward autonomous excavators. The swing angle and digging depth have significant effects on the excavator's pro-ductivity and must be taken into account for ...

Keywords: Excavator; Swing Angle; Digging Depth; Productivity; Otsu's method

Automated Valve Detection in Piping and Instrumentation (P&ID) Diagrams

Mohit Gupta, Chialing Wei and Thomas Czerniawski
Pages 630-637

Abstract: For successfully training neural networks, developers often require large and carefully labelled datasets. However, gathering such high-quality data is often time-consuming and prohibitively expensive. Thus, synthetic data are used for developing AI (Artificial Intelligence) /ML (Machine Learning) models because their generation is comparatively faster and inexpensive. The paper presents a ...

Keywords: Piping and Instrumentation Drawings; Yolo; Symbol Detection; Convolution Neural Network; Engineering Drawings; Symbol Classification; Deep Learning

Suitability and Effectiveness of Visualization Platform-based Construction Safety Training modules

Kishor Bhagwat and Venkata Santosh Kumar Delhi
Pages 638-645

Abstract: The construction industry is one of the most hazardous industries in the world. In addition, past literature highlighted that about 50% of the hazard remains unrecognized in the construction work environment, resulting in catastrophic consequences. Construction Safety Training (CST) is one of the best safety interventions to deal with this. ...

Keywords: Construction; Hazard; Safety; Training; Visualization

Semiarid Terrain Alteration for Converting Dryland into Arable Land - Construction and Earthmoving Perspectives

Moshe Alamaro, Joseph Louis and Jochen Teizer
Pages 646-652

Abstract: Close to 15% of the world's surface area is semiarid where 1.1 billion of the most vulnerable people on earth live. In contrast to arid, semiarid regions have substantial rainfall albeit it quickly evaporates and therefore vegetation and biomass growth are limited. A new concept calls for terrain ...

Keywords: Cultivation; Earth moving equipment; Food and agriculture; Automatic and robotic construction

Action Sequencing in Construction Accident Reports using Probabilistic Language Model

Quan Do, Tuyen Le and Chau Le
Pages 653-660

Abstract: Construction remains among the most hazardous workplaces, thus a significant amount of time and effort in reporting and investigating the accident occurrences has been done in the past decades by government agencies. In light of construction safety, analyzing textual information in construction accident records may assist in our comprehension of ...

Keywords: Construction safety; Accident reports; Probabilistic Language Model; Natural Language Processing