An official website of the United States government
Safety training has long been considered a promising method to enhance workers’ hazard identification skills within construction sites. To improve the effectiveness of safety training, such varied features as a training environment, individuals’ learning ability, and lesson personalization have been investigated. However, as records show workers still miss hazards even after receiving safety training, understanding the fundamental cognitive reasons for unrecognized hazards becomes a crucial step toward developing effective personalized safety training. This study used various 360° panoramas of construction scenarios to empirically examine 30 workers’ visual search strategies and assess workers’ hazard identification skills. Results suggest several cognitive limitations caused failures in hazard recognition, including attentional failure, inattentional blindness, and low perceived risk. Based on these findings, this study proposes a personalized safety training framework to address such cognitive limitations to improve occupational safety in the construction industry
more »
« less
This content will become publicly available on July 1, 2026
GPT Applications for Construction Safety: A Use Case Analysis
This study explores the use of Large Language Models (LLMs), specifically GPT, for different safety management applications in the construction industry. Many studies have explored the integration of GPT in construction safety for various applications; their primary focus has been on the feasibility of such integration, often using GPT models for specific applications rather than a thorough evaluation of GPT’s limitations and capabilities. In contrast, this study aims to provide a comprehensive assessment of GPT’s performance based on established key criteria. Using structured use cases, this study explores GPT’s strength and weaknesses in four construction safety areas: (1) delivering personalized safety training and educational content tailored to individual learner needs; (2) automatically analyzing post-accident reports to identify root causes and suggest preventive measures; (3) generating customized safety guidelines and checklists to support site compliance; and (4) providing real-time assistance for managing daily safety tasks and decision-making on construction sites. LLMs and NLP have already been employed in each of these four areas for improvement, making them suitable areas for further investigation. GPT demonstrated acceptable performance in delivering evidence-based, regulation-aligned responses, making it valuable for scaling personalized training, automating accident analyses, and developing safety protocols. Additionally, it provided real-time safety support through interactive dialogues. However, the model showed limitations in deeper critical analysis, extrapolating information, and adapting to dynamic environments. The study concludes that while GPT holds significant promise for enhancing construction safety, further refinement is necessary. This includes fine-tuning for more relevant safety-specific outcomes, integrating real-time data for contextual awareness, and developing a nuanced understanding of safety risks. These improvements, coupled with human oversight, could make GPT a robust tool for safety management.
more »
« less
- Award ID(s):
- 2417157
- PAR ID:
- 10625196
- Publisher / Repository:
- Buildings
- Date Published:
- Journal Name:
- Buildings
- Volume:
- 15
- Issue:
- 14
- ISSN:
- 2075-5309
- Page Range / eLocation ID:
- 2410
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The density and complexity of urban environments present significant challenges for autonomous vehicles. Moreover, ensuring pedestrians’ safety and protecting personal privacy are crucial considerations in these environments. Smart city intersections and AI-powered traffic management systems will be essential for addressing these challenges. Therefore, our research focuses on creating an experimental framework for the design of applications that support the secure and efficient management of traffic intersections in urban areas. We integrated two cameras (street-level and bird’s eye view), both viewing an intersection, and a programmable edge computing node, deployed within the COSMOS testbed in New York City, with a central management platform provided by Kentyou. We designed a pipeline to collect and analyze the video streams from both cameras and obtain real-time traffic/pedestrian-related information to support smart city applications. The obtained information from both cameras is merged, and the results are sent to a dedicated dashboard for real-time visualization and further assessment (e.g., accident prevention). The process does not require sending the raw videos in order to avoid violating pedestrians’ privacy. In this demo, we present the designed video analytic pipelines and their integration with Kentyou central management platform.more » « less
-
The density and complexity of urban environments present significant challenges for autonomous vehicles. Moreover, ensuring pedestrians’ safety and protecting personal privacy are crucial considerations in these environments. Smart city intersections and AI-powered traffic management systems will be essential for addressing these challenges. Therefore, our research focuses on creating an experimental framework for the design of applications that support the secure and efficient management of traffic intersections in urban areas. We integrated two cameras (street-level and bird’s eye view), both viewing an intersection, and a programmable edge computing node, deployed within the COSMOS testbed in New York City, with a central management platform provided by Kentyou. We designed a pipeline to collect and analyze the video streams from both cameras and obtain real-time traffic/pedestrian-related information to support smart city applications. The obtained information from both cameras is merged, and the results are sent to a dedicated dashboard for real-time visualization and further assessment (e.g., accident prevention). The process does not require sending the raw videos in order to avoid violating pedestrians’ privacy. In this demo, we present the designed video analytic pipelines and their integration with Kentyou central management platform. Index Terms—object detection and tracking, camera networks, smart intersection, real-time visualizationmore » « less
-
Seppänen, O; Koskela, L; Murata, K (Ed.)Generative Artificial Intelligence (AI), specifically Large Language Models (LLMs), has the potential to reshape construction management practices. These novel solutions can transform lean construction by enabling real-time data analysis, streamlined communication, and automated decision-making across project teams. They can facilitate enhanced collaboration by generating insights from vast construction data sets, improving workflow efficiency, and reducing waste. Additionally, LLMs can support predictive modeling, proactive risk management, and knowledge sharing, aligning with lean principles of maximizing value and minimizing inefficiencies. Given the recent advancements in generative AI, it is critical to systematically shape future research directions by building on the existing body of knowledge and addressing key knowledge gaps. The first step toward identifying knowledge gaps and uncovering critical areas that remain underexplored is to systematically analyze the existing body of knowledge. Therefore, this study conducts a scoping review to synthesize the extent, range, and nature of existing studies that have proposed novel solutions using generative AI and LLMs for various aspects of construction management. The outcomes of this systematic scoping review will help identify potential research directions for future studies in this domain.more » « less
-
Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora used for safety alignment of LLMs are solely interpreted by semantics. This assumption, however, does not hold in real-world applications, which leads to severe vulnerabilities in LLMs. For example, users of forums often use ASCII art, a form of text-based art, to convey image information. In this paper, we propose a novel ASCII art-based jailbreak attack and introduce a comprehensive benchmark Vision-in-Text Challenge (VITC) to evaluate the capabilities of LLMs in recognizing prompts that cannot be solely interpreted by semantics. We show that five SOTA LLMs (GPT-3.5, GPT-4, Gemini, Claude, and Llama2) struggle to recognize prompts provided in the form of ASCII art. Based on this observation, we develop the jailbreak attack ArtPrompt, which leverages the poor performance of LLMs in recognizing ASCII art to bypass safety measures and elicit undesired behaviors from LLMs. ArtPrompt only requires black-box access to the victim LLMs, making it a practical attack. We evaluate ArtPrompt on five SOTA LLMs, and show that ArtPrompt can effectively and efficiently induce undesired behaviors from all five LLMs. Our code is available at https: //github.com/uw-nsl/ArtPrompt.more » « less
