The idea of developing a system that can converse and understand human languages has been around since the 1200 s. With the advancement in artificial intelligence (AI), Conversational AI came of age in 2010 with the launch of Apple’s Siri. Conversational AI systems leveraged Natural Language Processing (NLP) to understand and converse with humans via speech and text. These systems have been deployed in sectors such as aviation, tourism, and healthcare. However, the application of Conversational AI in the architecture engineering and construction (AEC) industry is lagging, and little is known about the state of research on Conversational AI. Thus, this study presents a systematic review of Conversational AI in the AEC industry to provide insights into the current development and conducted a Focus Group Discussion to highlight challenges and validate areas of opportunities. The findings reveal that Conversational AI applications hold immense benefits for the AEC industry, but it is currently underexplored. The major challenges for the under exploration were highlighted and discusses for intervention. Lastly, opportunities and future research directions of Conversational AI are projected and validated which would improve the productivity and efficiency of the industry. This study presents the status quo of a fast-emerging research area and serves as the first attempt in the AEC field. Its findings would provide insights into the new field which be of benefit to researchers and stakeholders in the AEC industry.

The reinforcement and imitation learning paradigms have the potential to revolutionise robotics. Many successful developments have been reported in literature; however, these approaches have not been explored widely in robotics for construction. The objective of this paper is to consolidate, structure, and summarise research knowledge at the intersection of robotics, reinforcement learning, and construction. A two-strand approach to literature review was employed. A bottom-up approach to analyse in detail a selected number of relevant publications, and a top-down approach in which a large number of papers were analysed to identify common relevant themes and research trends. This study found that research on robotics for construction has not increased significantly since the 1980s, in terms of number of publications. Also, robotics for construction lacks the development of dedicated systems, which limits their effectiveness. Moreover, unlike manufacturing, construction's unstructured and dynamic characteristics are a major challenge for reinforcement and imitation learning approaches. This paper provides a very useful starting point to understating research on robotics for construction by (i) identifying the strengths and limitations of the reinforcement and imitation learning approaches, and (ii) by contextualising the construction robotics problem; both of which will aid to kick-start research on the subject or boost existing research efforts.

The overall aim of this paper is to contribute to a better understanding of the Digital Twin (DT) paradigm in the built environment by drawing inspiration from existing DT research in manufacturing. The DT is a Product Life Management information construct that has migrated to the built environment while research on the subject has grown intensely in recent years. Common to early research phases, DT research in the built environment has developed organically, setting the basis for mature definitions and robust research frameworks. As DT research in manufacturing is the most developed, this paper seeks to advance the understanding of DTs in the built environment by analysing how the DT systems reported in manufacturing literature are structured and how they function. Firstly, this paper presents a thorough review and a comparison of DT, cyber-physical systems (CPS), and building information modelling (BIM). Then, the results of the review and categorisation of DT structural and functional descriptions are presented. Fifty-four academic publications and industry reports were reviewed, and their structural and functional descriptions were analysed in detail. Three types of structural models (i.e. conceptual models, system architectures, and data models) and three types of functional models (process and communication models) were identified. DT maturity models were reviewed as well. From the reviewed descriptions, four categories of DT conceptual models (prototypical, model-based, interface-oriented, and service-based) and six categories of DT process models (DT creation, DT synchronisation, asset monitoring, prognosis and simulation, optimal operations, and optimised design) were defined and its applicability to the AECO assessed. While model-based and service-based models are the most applicable to the built environment, amendments are still required. Prognosis and simulation process models are the most widely applicable for AECO use-cases. The main contribution to knowledge of this study is that it compiles the DT’s structural and functional descriptions used in manufacturing and it provides the basis to develop DT conceptual and process models specific to requirements of the built environment sectors.

This paper presents a study on the usage landscape of augmented reality (AR) and virtual reality (VR) in the architecture, engineering and construction sectors, and proposes a research agenda to address the existing gaps in required capabilities. A series of exploratory workshops and questionnaires were conducted with the participation of 54 experts from 36 organisations from industry and academia. Based on the data collected from the workshops, six AR and VR use-cases were defined: stakeholder engagement, design support, design review, construction support, operations and management support, and training. Three main research categories for a future research agenda have been proposed, i.e.: (i) engineering-grade devices, which encompasses research that enables robust devices that can be used in practice, e.g. the rough and complex conditions of construction sites; (ii) workflow and data management; to effectively manage data and processes required by AR and VR technologies; and (iii) new capabilities; which includes new research required that will add new features that are necessary for the specific construction industry demands. This study provides essential information for practitioners to inform adoption decisions. To researchers, it provides a research road map to inform their future research efforts. This is a foundational study that formalises and categorises the existing usage of AR and VR in the construction industry and provides a roadmap to guide future research efforts.

The emerging technologies of the Internet of Things (IoT) and big data can be utilised to derive knowledge and support applications for energy-efficient buildings. Effective prediction of heating and cooling demands is fundamental in building energy management. In this study, a 4-layer IoT-based big data platform is developed for day-ahead prediction of building energy demands, while the core part is the hybrid machine learning-based predictive model. The proposed energy demand predictive model is based on the hybrids of k -means clustering and artificial neural network (ANN). Due to different temperatures of walls, windows, grounds, roofs and indoor air, various IoT sensors are installed at different locations of the building. To determine the input variables to the hybrid machine learning-based predictive model, correlation analysis is adopted. Through clustering analysis, the characteristic patterns of daily weather profile are identified. Thus, the annual profile is classified into several featuring groups. Each group of weather profile, along with IoT sensor readings, building operating schedules as well as heating and cooling demands, is used to train the sub-ANN predictive models. Due to the involvement of IoT sensors, the overall prediction accuracy can be improved. It is found that the mean absolute percentage error of energy demands prediction is 3% and 8% in training and testing cases, respectively.