30 Must-Read Publications on Digital and Circular Building
The science behind the Tech4EUConstruction cluster's innovations
Compared to other sectors, the European construction industry faces significant challenges in sustainability, innovation adoption and labour shortages, with nearly half of the industry’s jobs in short supply. Transforming this sector into a smarter and greener industry will enhance competitiveness, resource efficiency, and attractiveness for young generations.
Eight European-funded projects, tackling these issues, have united in the Tech4EUConstruction cluster, and today are sharing 30 must-read publications that offer fresh insights for researchers and industry professionals.
The cluster is dedicated to creating a lasting impact by exchanging expertise and technical innovations. This article delves into the science behind next-generation technologies and innovations in areas such as building renovation, sustainability monitoring, digital innovation technologies, energy efficiency, renewable energy, and materials and design.
What will be the advancements in AI and robotics shaping the future of the construction industry? Find them out!
Monitoring the Sustainability of Building Renovation Projects by the Incube project
Incube envisions to unlock the EU renovation wave through cutting-edge standardised and integrated processes based on industrialisation, innovative renewable energy technologies, digitalisation, and new market entrants. This publication integrates a Tailored Key Performance Indicator Repository, monitoring the sustainability performance of building renovation projects.
Towards the digitalization and automation of circular and sustainable construction and demolition waste management by the RECONMATIC project
This publication is a presentation of the RECONMATIC project, a Horizon Europe Research and Innovation Action project, that aims to develop novel tools, technologies and methodologies that can contribute in such a manner in multiple construction phases and project types or material and product life cycle stages.
Assessing the CDW volume for a typical Mediterranean residential building
Released by RECONMATIC, the publication is a documented estimation of the demolition waste quantities of typical multistorey urban buildings which constitute the great majority of the Greek building stock. Such buildings, constructed between 1955-1965, will need to be demolished, since their required structural support and energy performance upgrade is continuously less feasible when seen under the framework of the EU’s 2050 targets.
From 3D surveying data to BIM to BEM: the INCUBE dataset
This paper introduces the InCUBE dataset, resulting from the activities of the project, focused on unlocking the EU building renovation through integrated strategies and processes for efficient built-environment management (including the use of innovative renewable energy technologies and digitalization). The set of data collects raw and processed data produced for the Italian demo site in the Santa Chiara district of Trento (Italy). The diversity of the shared data enables multiple possible uses, investigations and developments, and some of them are presented in this contribution.
Introducing Noise for AirSim’s 3D Lidar Sensor to Reduce the Sim2real Gap by the BEEYONDERS project
BEEYONDERS core ambition is to address challenges by producing, commercializing and integrating beyond the state-of-the-art solutions into real construction scenarios. To do so, they will make extensive use of AI, automation, and digitisation. This publication presents a modeling sensor noise for better simulations of robotic systems.
Online Ergonomic Evaluation in Realistic Manual Material Handling Task: Proof of Concept
This publication released by BEEYONDERS presents an online algorithm to assess work task ergonomics and prevent accidents.
REINCARNATE: Shaping a sustainable future in construction through digital innovation
The Reincarnate project is working on a platform that aims to provide information on the life cycle and reuse potential of construction materials and methods to predict and extend product lifetime. This publication highlights the project’s aim to promote circular practices by extending material durability through digital methods, integrating NDT techniques and AI methods for recycling.
Presenting SLAMD – A Sequential Learning Based Software for the Inverse Design of Sustainable Cementitious Materials
The publication introduces the concept of Inverse Design and demonstrates how an open-source app “SLAMD” developed by Reincarnate provides all necessary steps of the workflow to adapt it in the laboratory, lowering the application barriers.
Single Frame Semantic Segmentation Using Multi-Modal Spherical Images by the HumanTech project
HumanTech is advancing innovative human-centred technologies – from robotic devices and exoskeletons to a new generation of digital twins – to help make the construction industry safer, greener, more efficient and attractive to a new generation of highly skilled workers.
U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds
The paper by HumanTech proposes U-RED, an Unsupervised shape Retrieval and Deformation pipeline that takes an arbitrary object observation as input, typically captured by RGB images or scans, and jointly retrieves and deforms the geometrically similar CAD models from a pre-established database.
Annotation rules and classes for semantic segmentation of point clouds for digitalization of existing bridge structures
To bridge the gap between theoretical research on point cloud data and manual inspection, HumanTech proposes in this research a list of object-oriented classes for semantic segmentation.
OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection
In this publication, HumanTech shares a computer vision for transportation, deep learning for visual perception, object detection.
Ontology-Based Semantic Labelling for RGB-D and Point Cloud Datasets
Applications of deep learning have recently seen a surge in the field of construction. Supervised semantic segmentation of 2D or 3D data acquired from buildings requires the use of annotated data for training, validation, and testing. Although various datasets have been published targeting this application, they lack a common convention and definitions based on construction ontologies. In this work, HumanTech presents a guideline for ontology-based semantic annotation of RGB-D and point cloud datasets for buildings. Such a contribution facilitates the use of deep learning in construction by bridging the gap between this field and computer science.
When Machine Learning Meets Raft: How to Elect a Leader over a Network
Recent work in the RECONMATIC project, referring to the UTH (University of Thessaly) team work on design and enhancements of “HyperLedger Fabric”, the open-source technology that uses blockchain to enable trackability and immutability. They explain how we use “Machine Learning” to improve the “Ordering service”, its election process, when the components of this service are distributed to multiple sites. This is especially useful when the components of the RECONMATIC supply chain, used in Work Package 2, are geo-distributed over long distances.
Machine-learning-assisted classification of construction and demolition waste fragments using computer vision: Convolution versus extraction of selected features
Recent work in the RECONMATIC project, referring to the UTH (University of Thessaly) team work on design and enhancements of “HyperLedger Fabric”, the open-source technology that uses blockchain to enable trackability and immutability. They explain how we use “Machine Learning” to improve the “Ordering service”, in particular its election process, when the components of this service are distributed to multiple sites. This is especially useful when the components of the RECONMATIC supply chain, used in Work Package 2, are geo-distributed over long distances.
Review of Concepts for Construction and Demolition Waste and the Circular Economy
The aim of this paper released by RECONMATIC is to critically understand how CDW is classified, as well as to differentiate between the various methods employed in the waste management process. Additionally, it presents a discussion on the existing thought regarding the concept of CE in the context of the construction sector.
On using Hyperledger Fabric over Networks
One of the most prominent aspects of Hyperledger Fabric is its three-phase transaction flow architecture, which consists of the execution, ordering and validation phases. The ordering phase involves communication between the client and the ordering service, as the latter is responsible for the transaction assembly and distribution. This study released by RECONMATIC reconstructs the ordering phase and proposes a mechanism for faster communication between the client and the ordering service. Notably, the proposed mechanism can be easily integrated in a future Hyperledger Fabric release.
RoBétArmé Project: Human-robot collaborative construction system for shotcrete digitization and automation through advanced perception, cognition, mobility and additive manufacturing skills
The RoBétArmé European project targets the Construction 4.0 transformation of the construction with shotcrete with the adoption of breakthrough technologies such as sensors, augmented reality systems, high-performance computing, additive manufacturing, advanced materials, autonomous robots and simulation systems, technologies that have already been studied and applied so far in Industry 4.0. This paper showcases a case study on which novel robotic systems will be developed for the automation of shotecrete application. The outcomes of this research can be widely used in other application technologies related to the construction domain.
Adaptive BIM/CIM for Digital Twining of Automated Shotcreting Process by the RoBétArmé project
The use of Building/Civil-Construction Information Modeling (BIM/CIM) for the creation of a digital representation of the physical process and asset plays a vital role. The construction process considered for this research study is shotcrete application and surface finishing during the construction and finishing phases. The research from RoBétArmé presents the role of adaptive BIM/CIM models for the digital replication of automated shotcreting of civil infrastructure projects.
Leveraging Multimodal Sensing and Topometric Mapping for Human-Like Autonomous Navigation in Complex Environments
Autonomous vehicle navigation in complex and unpredictable outdoor environments requires extensive and detailed understanding of the surrounding area and compliance with the traffic rules. In this paper, RoBétArmé attempts to imitate human driver behavior towards autonomous navigation that is suitable for diverse, challenging environments, whether urban, semi-structured or rural-like.
Cognitive Fusion-based Path Planning for UAV Inspection of Power Towers
The utilization of Unmanned Aerial Vehicles (UAV) for the inspection of critical power infrastructure has made significant strides in recent years. Hardware and software advancements enabled the transition from manual to semi-autonomous and fully autonomous UAV operations, which are capable of traversing complex environments and identifying potential flaws. This paper from RoBétArmé presents a novel path planning method that leverages robot vision derived from LiDAR (Light Detection and Ranging) and RGB data for the inspection of insulators on power towers.
Comparative Study of Surface 3D Reconstruction Methods Applied in Construction Sites
The accurate and detailed 3D reconstruction of the construction sites plays a vital role in the digitalization of the construction domain, since accurate 3D models constitute the basis for the adaptation of advanced technologies from Industry 4.0 towards realizing Construction 4.0. This study from RoBétArmé provides a comprehensive assessment of key methodologies employed for 3D reconstruction in the construction sector.
Real-time 3D Reconstruction Adapted for Robotic Applications in Construction Sites
The integration of robot vision techniques, specifically focused on 3D reconstruction, assumes paramount significance in the construction sector, serving as a key enabler for fulfilling the imperative digitalization prerequisites inherent to the principles of Industry 4.0. This study from RoBétArmé proposes a real-time 3D reconstruction pipeline, based on common algorithms, that utilizes both RGB and depth information.
Dynamic Energy Analysis of Different Heat Pump Heating Systems Exploiting Renewable Energy.
In this publication, INCUBE investigates different heating configurations utilizing various renewable thermal sources in conjunction with an HP-based system in order to determine the optimal configuration in terms of efficiency, using an existing, fully functioning residential building in Zaragoza, Spain, as our case study, comprising 40 dwellings.
Αn integrated life cycle assessment and life cycle costing approach towards sustainable building renovation via a dynamic online tool.
In this publication, INCUBE shares building life cycle assessments/ innovative sustainable tools.
BIM-Based Construction Quality Assessment Using Graph Neural Networks.
In this publication, HUMANTECH introduces a novel approach to automated quality control that enhances element-wise quality assessments by exploiting semantics in BIM.
Data driven design of alkali-activated concrete using sequential learning
Released by the Reincarnate project, the publication introduces a novel approach for developing sustainable building materials through Sequential Learning.
LLMs can Design Sustainable Concrete -a Systematic Benchmark
The complexity of resource flows and the variability of material composition pose significant challenges. This study by Reincarnate demonstrates how Large Language Models (LLMs) can advance material design by adopting a Knowledge-Driven Design (KDD) approach that outperforms traditional Data-Driven Design (DDD) methods.
Beyond Theory: Pioneering AI-Driven Materials Design in the Sustainable Building Material Lab
This research development produced by Reincarnate focuses on Artificial Intelligence (AI)-driven materials design, addressing the challenge of improving the sustainability of building materials amid complex formulations.
14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
Large-language models (LLMs) such as GPT-4 caught the interest of many scientists. Recent studies suggested that these models could be useful in chemistry and materials science. To explore these possibilities, Reincarnate organised a hackathon. This article chronicles the projects built as part of this hackathon. Participants employed LLMs for various applications, including predicting properties of molecules and materials, designing novel interfaces for tools, extracting knowledge from unstructured data, and developing new educational applications.