Wearable exoskeletons enhance mobility and support in demanding tasks but face challenges in adapting to dynamic construction environments, particularly in predicting locomotion modes for tasks such as ladder climbing, stair navigation, low-space movement, and obstacle navigation. This study investigates the effectiveness of integrating speech and vision data for locomotion prediction while evaluating the generalization capability of large language models, specifically GPT-4o, through zero-shot learning compared to supervised fine-tuning. Using a multimodal framework with field-of-view frames and speech commands captured by smart glasses, we tested contrastive language-image pre-training (CLIP), ImageBind, and GPT-4o. Fine-tuned CLIP achieved an F1-score of 90.05% , yet GPT-4o’s zero-shot of 87.87% closely rivaled it, demonstrating strong adaptability to construction’s complex demands without task-specific training, while fine-tuned ImageBind trailed at 78.84%. This comparison underscores GPT-4o’s substantial potential to enable scalable exoskeleton control by leveraging multimodal comprehension of vision and speech data in dynamic construction settings.

Building information modeling (BIM) and robotic technologies are revolutionizing the construction industry. The integration of BIM and robotics has the potential to enhance workforce skills, improve safety, and optimize construction processes. However, despite these promising benefits, a significant gap in systematic reviews on applying this integration within the industry is evident. This research addresses this crucial gap through a comprehensive and rigorous systematic literature review following the preferred reporting items for systematic review and meta-analysis (PRISMA) methodology. In our search within the Web of Science (WoS) database using a detailed search query, we identified 200 articles. After applying specific inclusion and exclusion criteria, we selected 22 papers for review. This paper thoroughly examines the current applications of BIM and robotics in construction, focusing on specific scenarios where these technologies converge. It also delves into the mechanisms of data transfer, both real-time and otherwise, highlighting how BIM and robotics interact, and the efficiency gains achieved through their integration. Additionally, the paper explores future research directions, challenges, and opportunities within this domain, aiming to provide insights into how these emerging technologies can continue to evolve and address the construction industry’s forthcoming needs.

Construction site safety is a paramount concern, given the high rate of accidents and fatalities in the sector. This study introduces a novel approach to analyzing construction accident reports by employing advanced large language models (LLMs), specifically generative pre-trained transformer (GPT)-3.5, GPT-4.0, Gemini Pro, and large language model Meta artificial intelligence (AI) (LLaMA) 3.1. Our research focuses on the classification of key attributes in accident reports: root cause, injury cause, affected body part, severity, and accident time. The results reveal that GPT-4.0 achieves significantly higher accuracy across most attributes. Gemini Pro demonstrates superior performance in the “injury cause” classification, while LLaMA 3.1 excels in classifying “severity” and “root cause”. GPT-3.5, although lagging behind GPT-4.0, exhibits commendable accuracy. The insights gained from this study are vital for the construction industry, as they indicate the potential for developing more precise and effective safety measures. These findings could lead to a reduction in the frequency and severity of accidents, thereby enhancing worker safety.