Eleni Vasiliki Alexi

Traditional apprenticeship models struggle to scale as the construction industry faces a growing shortage of skilled workers and an aging workforce. This study evaluates the potential and strategies of Large Language Models (LLMs) to support apprentices in learning hands-on construction tasks through real-time, conversational instruction. Drawing on prior research in conversational AI and intelligent tutoring systems, we conduct a comparative analysis of LLM-based guidance versus traditional video demonstrations in controlled masonry tasks. Through a mixed-methods approach, we assess task performance, interaction patterns, and participants’ self-reported confidence and understanding. Findings from our exploratory comparative study suggest that LLMs can deliver relevant, adaptive, and context-aware procedural guidance. However, limitations emerged in conveying tacit knowledge and adapting tool use to the specific task context. The results underscore the importance of interface design and instructional modality in sustaining engagement. This work offers early insights into the design of scalable, AI-assisted learning systems for skilled trades.

This research presents a comprehensive methodology for designing and fabricating spatial timber assemblies using cooperative human–robot workflows, enabling the on-site construction of complex structures that exceed the capabilities of humans or robots alone. At the core of this approach is a rule-based design method—termed assembly grammar—which defines not only geometric configurations but also sequences of interdependent physical tasks for assembling reciprocal frame-like structures cooperatively. This methodology integrates user-defined design intentions with equilibrium conditions and fabrication constraints specific to both robotic and manual processes. The design is stored using a graph-based assembly model, which captures geometric information alongside task-related data such as task assignments, robotic fabrication parameters, and assembly sequences. Complementing the design workflow, the methodology also includes strategies for effectively coordinating and distributing tasks between humans and mobile robots, supported by a custom-developed mobile augmented reality (AR) application. To validate the approach, a fabrication-aware design tool was created and applied for generating complex reciprocal-like timber structuresfor scaffold-free in-situ cooperative assembly. The coordinated assembly methodology was then demonstrated through the successful construction of two architectural-scale timber demonstrators built cooperatively by multiple humans and robots. Evaluation criteria such as assembly accuracy and the effectiveness of human–robot interaction demonstrated the practical benefits and applicability of the methodology for real-world construction scenarios.

Recent years have witnessed significant advances in computational design and robotic fabrication for large-scale manufacturing. Although these advances have enhanced the speed, precision, and reproducibility of digital fabrication processes, they often lack adaptability and fail to integrate manual actions in a digital model. Addressing this challenge, the present study introduces cooperative augmented assembly (CAA), a phone-based mobile Augmented Reality (AR) application that facilitates cooperative assembly of complex timber structures between humans and robots. CAA enables augmented manual assembly, intuitive robot control and supervision, and task sharing between humans and robots, creating an adaptive digital fabrication process. To allocate tasks to manual or robotic actions, the mobile AR application allows multiple users to access a shared digital workspace. This is achieved through a flexible communication system that allows numerous users and robots to cooperate seamlessly. By harnessing a cloud-based augmented reality system in combination with an adaptive digital model, CAA aims to better incorporate human actions in robotic fabrication setups, facilitating human–machine cooperation workflows and establishing a highly intuitive, adaptable digital fabrication process within the Architecture, Engineering, and Construction sector.