This audio is automatically generated. Please let us know if you have any comments.
Cars outnumber workers all day on highway improvement projects.
The hazards at these highway construction sites are so constant that workers can even become somewhat desensitized to the danger over time. That split-second lapse in focus is all it takes for tragedy to strike.
From 2011 to 2021, hit-and-run incidents, which occur when a person is struck by a vehicle, equipment or other object, accounted for approximately 1,800 fatalities and more than 167,000 non-fatal injuriesaccording to the National Institute of Occupational Safety and Health.
But Namgyun Kim, an assistant professor in Texas A&M University’s construction science department, believes artificial intelligence can help workers stay alert.
Along with Texas A&M professor Brian Anderson and Yongcheol Lee of Louisiana State University, Kim is studying how workers perceive and respond to these hazards.
Through a series of studies including virtual reality simulations, brain activity monitoring, field observations, and AI-powered augmented reality systems, Kim seeks improve workers’ attention to risksaccording to a Texas A&M news release.
Here, Kim talks to Construction Dive about AI in construction safety training, the technology’s return on investment, and the impacts on construction activity in the coming years.
Editor’s Note: The following has been edited for brevity and clarity.
Construction Immersion: What is the biggest misconception contractors have about AI in construction today?
NAMGYUN KIM: One of the biggest misconceptions is that construction remains a low-tech, labor-intensive industry that has changed very little over the years. While construction will always rely on skilled workers, the industry has undergone a remarkable digital transformation over the past few decades.
Namgyun Kim
Courtesy of Texas A&M University
A major turning point was the adoption of Building Information Modeling, which created digital models that allow architects, engineers, contractors and owners to collaborate using the same information. This has significantly reduced communication errors, improved productivity and improved safety throughout the life cycle of a project, from design and construction to operation and maintenance.
Today, this transformation is accelerating due to advances in AI. It is becoming a practical tool in construction projects. It can help predict potential hazards before they lead to accidents, monitor workplace conditions and worker risk behaviors in real time, and provide customized safety training tailored to specific workers, tasks or project conditions.
What’s stopping this technology from becoming standard in workplaces?
I would tell a CEO that VR and AI-based safety training should no longer be seen as an experimental technology.
Researchers have spent more than a decade studying VR-based safety training, and many studies have shown that immersive training helps workers recognize hazards and respond more effectively than traditional classroom instruction. Commercial virtual reality training platforms are also widely available today.
However, VR safety training has a major limitation. Most VR programs are built around a fixed set of scenarios. Construction projects, on the other hand, are never exactly the same. Each project has different site conditions, schedules, equipment and risks. As a result, a generic VR scenario often fails to capture the unique hazards of a specific project or task.
How does AI help with this challenge?
This is where the latest advances in AI are changing the equation. Generative AI can dramatically reduce the time and cost required to create new training scenarios. Instead of relying on a handful of pre-built simulations, companies can develop training that reflects the actual project, the specific work being performed, and even the experience level of individual workers. AI can also analyze training data to identify knowledge gaps and recommend follow-up training where it’s most needed.
The biggest challenge for CEOs has always been to demonstrate return on investment. Safety incidents are relatively infrequent events, making it difficult to prove that any training program directly prevented an accident.
We believe the strongest business case is that virtual reality and artificial intelligence fill critical gaps that traditional methods cannot address, making security training more project-specific, data-driven and proactive. This is where the biggest return on investment comes from.
Your research focuses on workers who become desensitized to their surroundings, in a busy highway workplace, for example. How do you use AI there?
One trend that I think deserves more attention is that AI goes beyond identifying risks or unsafe worker behaviors in workplaces. Increasingly, researchers and industry are using AI to better understand why people make unsafe decisions in the first place.
For example, we know that construction workers can become so familiar with warning signs, alarms, or recurring hazards that they gradually stop noticing them, a phenomenon known as “habituation.”
This has traditionally been recognized through experience, but has been very difficult to measure objectively or address systematically. Today, artificial intelligence and wearable technologies make it possible to identify these patterns and provide personalized training before they contribute to an accident.
Any other trends you’re keeping an eye on around AI and construction safety?
We are also seeing research focused on understanding how different workers perceive risk. Some workers consistently overlook certain types of hazards, while others respond differently depending on their experience or the task they are performing. AI can help identify these patterns and deliver training tailored to the individual rather than assuming that everyone learns the same way.
Another interesting direction is using AI to better understand security culture. By analyzing conversations during toolbox conversations or other routine security meetings, AI can help organizations identify communication gaps, assess how security information is shared, and strengthen the company’s overall security culture.
Ultimately, I believe the next generation of AI in construction safety will be less about replacing people and more about understanding human behavior. If we can better understand how workers perceive risk, we can design much more effective safety and training programs than the current one-size-fits-all approach.
