The widespread adoption of Building Information Modeling (BIM) and the recent emergence of Internet of Things (IoT) applications offer several new insights and decision-making capabilities throughout the life cycle of the built environment. In recent years, the ability of real-time connectivity to online sensors deployed in an environment has led to the emergence of the concept of the Digital Twin of the built environment. Digital Twins aim to achieve synchronization of the real world with a virtual platform for seamless management and control of the construction process, facility management, environment monitoring, and other life cycle processes in the built environment. However, research in Digital Twins for the built environment is still in its nascent stages and there is a need to understand the advances in the underlying enabling technologies and establish a convergent context for ongoing and future research. This paper conducted a systematic review to identify the development of the emerging technologies facilitating the evolution of BIM to Digital Twins in built environment applications. A total of 100 related papers including 23 review papers were selected and reviewed. In order to systematically classify the reviewed studies, the authors developed a five-level ladder categorization system based on the building life cycle to reflect the current state-of-the-art in Digital Twin applications. In each level of this taxonomy, applications were further categorized based on their research domains (e.g., construction process, building energy performance, indoor environment monitoring). In addition, the current state-of-art in technologies enabling Digital Twins was also summarized from the reviewed literature. It was found that most of the prior studies conducted thus far have not fully exploited or realized the envisioned concept of the Digital Twin, and thus classify under the earlier ladder categories. Based on the analysis of the reviewed work and the trends in ongoing research, the authors propose a concept of an advanced Digital Twin for building management as a baseline for further studies.

Construction robots continue to be increasingly deployed on construction sites to assist human workers in various tasks to improve safety, efficiency, and productivity. Due to the recent and ongoing growth in robot capabilities and functionalities, humans and robots are now able to work side-by-side and to share workspaces. The emerging field of human–robot collaboration has significant potential applications in construction and continues to advance the state of the art in defining the responsibilities of both humans and robots during collaborative work. This paper proposes a new taxonomy for collaborative human–robot work in construction teams. The evolution of construction robots during the last two decades is first reviewed, and relevant bodies of work are categorized into one of five levels of human–robot collaboration: Preprogramming, Adaptive Manipulation, Imitation Learning, Improvisatory Control, and Full Autonomy. The categories of the proposed taxonomy are defined based on the level of robot autonomy and the corresponding human effort in collaborative teamwork. Second, this paper uses the categories of the proposed taxonomy as a contextual framework to identify current challenges and knowledge gaps in collaborative human–robot construction work and recommends directions for future research.

Real-time plane extraction in 3D point clouds is crucial to many robotics applications. We present a novel algorithm for reliably detecting multiple planes in real time in organized point clouds obtained from devices such as Kinect sensors. By uniformly dividing such a point cloud into non-overlapping groups of points in the image space, we first construct a graph whose node and edge represent a group of points and their neighborhood respectively. We then perform an agglomerative hierarchical clustering on this graph to systematically merge nodes belonging to the same plane until the plane fitting mean squared error exceeds a threshold. Finally we refine the extracted planes using pixel-wise region growing. Our experiments demonstrate that the proposed algorithm can reliably detect all major planes in the scene at a frame rate of more than 35Hz for 640×480 point clouds, which to the best of our knowledge is much faster than state-of-the-art algorithms.