Human-robot collaboration is becoming increasingly important as robots become more involved in various aspects of human life in the era of Artificial Intelligence. However, the issue of human operators’ trust in robots remains a significant concern, primarily due to the lack of adequate semantic understanding and communication between humans and robots. The emergence of Large Language Models (LLMs), such as ChatGPT, provides an opportunity to develop an interactive, communicative, and robust human-robot collaboration approach. This paper explores the impact of ChatGPT on trust in a human-robot collaboration assembly task. This study designs a robot control system called RoboGPT using ChatGPT to control a 7-degree-of-freedom robot arm to help human operators fetch, and place tools, while human operators can communicate with and control the robot arm using natural language. A human-subject experiment showed that incorporating ChatGPT in robots significantly increased trust in human-robot collaboration, which can be attributed to the robot’s ability to communicate more effectively with humans. Furthermore, ChatGPT’s ability to understand the nuances of human language and respond appropriately helps to build a more natural and intuitive human-robot interaction. The findings of this study have significant implications for the development of human-robot collaboration systems.

Inefficient communication among project stakeholders is one of the most critical issues in the architecture, engineering, and construction (AEC) industry. In reality, it is difficult to create a common understanding about a project among key stakeholders located remotely. The recent progress of virtual reality (VR) makes it a promising approach for interactive visualization of design, construction, and facility management. However, the lack of interactions in VR, such as data interaction, human-building interaction, and human-human interaction, has impeded the adoption of VR in the AEC industry. To fill the gaps, this paper introduces a cloud-based multiuser VR headset system called collaborative virtual reality (CoVR) that facilitates interpersonal project communication in an interactive VR environment. CoVR provides not only a shared immersive experience, but also allows interactions with the underlying simulated world and face-to-face conversations in the virtual world. A real case was used to test the usability of the CoVR system, followed by a building inspection experiment in which 71 subjects were recruited to test the comparative advantages of CoVR. Results indicate that CoVR improves interpersonal interactions in the immersive virtual environment and enhances communications in construction projects. Users of CoVR tended to perform better in a building inspection task than those who were using a single-person VR system. In practice, CoVR is expected to help project stakeholders create a shared vision before construction work commences.

Robot-based assembly in construction has emerged as a promising solution to address numerous challenges such as increasing costs, labor shortages, and the demand for safe and efficient construction processes. One of the main obstacles in realizing the full potential of these robotic systems is the need for effective and efficient sequence planning for construction tasks. Current approaches, including mathematical and heuristic techniques or machine learning methods, face limitations in their adaptability and scalability to dynamic construction environments. To expand the current robot system’s sequential understanding ability, this paper introduces RoboGPT, a novel system that leverages the advanced reasoning capabilities of ChatGPT, a large language model, for automated sequence planning in robot-based assembly applied to construction tasks. The proposed system adapts ChatGPT for construction sequence planning and demonstrates its feasibility and effectiveness through experimental evaluation including two case studies and 80 trials involving real construction tasks. The results show that RoboGPT-driven robots can handle complex construction operations and adapt to changes on the fly. This paper contributes to the ongoing efforts to enhance the capabilities and performance of robot-based assembly systems in the construction industry, and it paves the way for further integration of large language model technologies in the field of construction robotics.

Amid the rapid development of information communication technologies (ICTs), residents of future smart cities are expected to be exposed to unprecedented amounts of real-time information on a daily basis. The cognitive overload driven by an excess of complex information has become a potential issue. Nonetheless, standardized information systems are still widely used, despite individual differences in information intake. To set a foundation for the intelligent information systems of smart cities, this paper introduces methods and tools for a cognition-driven, personalized information system, which acknowledges individual differences in information preference and helps reduce the cognitive load in daily lives and at work. The proposed method includes the use of virtual reality (VR) to simulate complex tasks paired with the digital twin modeling of workers’ cognitive reactions to different information formats and contents in VR simulation. Collected data are then used to build a personal digital twins model of information-driven cognition, or Cog-DT. A human subject experiment was performed with a simulated industrial facility shutdown maintenance task as a proof of concept of Cog-DT. The latest neuroimaging technology and analysis methods were applied to model unique cognitive processes pertaining to information processing. Results indicate that cognitive activities driven by different information stimuli in the work context are distinguishable and modelable with Cog-DT methods and tools. This study is expected to contribute to digital twin literature by testing a human-centered, individual-level digital twin modeling method of cognitive activities. It also sets a preliminary foundation for developing personalized information systems for the smart cities of the future.