AI in Construction: How Arizona State University Prepares Engineers for Safer, Smarter Jobsites

Construction sites generate an extraordinary amount of variable data: rising temperatures, shifting schedules, worker fatigue levels, equipment movement, and evolving site conditions. For decades, managing these variables depended almost entirely on human observation and hard-won experience. Artificial intelligence is changing that. Today, AI systems can process jobsite data in real time, flag risks before they become incidents, and give project teams a level of awareness that was previously impossible.

Arizona State University has become one of the places where this shift is being studied, tested, and taught. Within the Ira A. Fulton Schools of Engineering, faculty members in the School of Sustainable Engineering and the Built Environment and the Del E. Webb School of Construction are building AI tools for jobsite safety, testing immersive training methods, and redesigning coursework so that graduates arrive on the jobsite ready to work alongside these technologies.

Have questions about how AI fits into a modern construction education? Write to us through the comments below or contact the programs directly to start a conversation.

Why Artificial Intelligence Matters on the Construction Jobsite

Some of the most serious risks in construction are the hardest to see coming. Heat stress, physical fatigue, and psychological strain develop gradually, and by the time symptoms are visible, a worker may already be in danger. Traditional safety management relies on supervisors noticing warning signs — an approach that is limited by how many people one person can watch and how subtle the early indicators are.

This is exactly where AI changes the equation. Machine learning systems can continuously monitor conditions that no human observer could realistically track, compare each worker’s data against personal baselines, and shift safety management from reacting to incidents toward preventing them. In an industry where decisions carry physical consequences, that difference matters.

A Heat Stress Early-Warning System Built With Industry Partners

One of the clearest examples comes from the Safety Automation and Visualization Environment Laboratory, or SAVE Lab, led by Siyuan Song, an associate professor of construction engineering in the Fulton Schools. Working with Achen-Gardner Construction, Willmeng Construction, and CHASSE Building Team, the lab developed a heat stress early-warning system designed for real jobsite conditions — a pressing concern in Arizona, where summer temperatures put construction workers among the most vulnerable to heat-related illness.

The system combines data from wearable biosensors worn by workers with environmental monitoring of the site itself. When the AI detects early signs of fatigue or heat strain, it sends personalized, real-time alerts — before the worker experiences symptoms. The goal is straightforward: make sure every construction worker goes home safe and healthy at the end of the day.

Personalized Alerts, Not One-Size-Fits-All Rules

What makes this approach notable is its recognition of individual variability. Two workers in identical conditions can respond very differently to heat and exertion. A static safety rule treats them the same; an AI-assisted system can account for those differences and tailor its warnings accordingly. That personalization is what moves safety programs from generic compliance checklists to genuine prevention.

SAVE Lab researchers also create immersive virtual reality safety training environments to study how workers learn and respond to hazards, and they use large language models to analyze accident reports, examine the impact of extreme weather, and evaluate the effectiveness of safety training.

Human-Centered Construction Technology and Immersive Learning

AI in construction is not limited to safety monitoring. At ASU, several research groups are examining how technology and people interact on the jobsite and in training environments.

Shiva Pooladvand, an assistant professor of construction engineering, leads a research group that develops human-centered construction technologies by connecting construction engineering with robotics, computer science, cognitive science, human factors, and immersive environments. Her team uses AI to analyze multimodal data captured from workers and their surroundings, looking for patterns in decision-making, behavior, and safety. The aim is to anticipate unsafe working conditions or identify workers who may be at risk, enabling interventions that are tailored to the person and the situation rather than applied broadly.

Ricardo Eiris, an assistant professor of construction management at the Construction Workforce and Technology Lab, takes a different angle: education and workforce training. His research combines AI with human-computer interaction, virtual reality, digital twins, and drones to help people understand construction sites and learn in settings that go beyond the limits of physical classrooms or active jobsites. In his words, AI serves as a tool for expanding how people learn, train, and interact with complex built environments — modeling human behavior and creating responsive systems that improve learner performance.

Kenn Sullivan, a professor of construction management, applies AI to the research process itself, using it for statistical modeling, visualization, testing analytical approaches, and documenting his team’s methods and decisions so future students can build on the work. This emphasis on practical, documented applications reflects a broader philosophy across the school: AI is a tool to be directed by construction expertise, not a replacement for it.

Industry Collaboration at the AI for Construction Contractors Summit

Academic research only matters if it reaches the field. That is the thinking behind the AI for Construction 2026 Contractors Summit, hosted by the Del E. Webb School of Construction and the newly formed AI in Construction Consortium. At the event, construction leaders shared how their companies use AI in agent-based workflows for specific tasks: business development, virtual design and construction, safety, visual analysis, scanning, and project controls.

According to Tim Becker, programs chair of the school, the summit and consortium grew out of the school’s executive council as opportunities for construction companies, technology providers, faculty members, and students to learn from one another in a collaborative environment. For students, this kind of industry connection is invaluable — it means the tools they study in class are the same ones being deployed on active projects.

Want more examples of AI being applied in construction and engineering? Explore our related articles for further reading on construction technology, safety innovation, and workforce training.

Teaching Responsible AI Use in the Construction Classroom

The speed of AI adoption has forced educators to rethink how they teach. Sullivan offers a striking data point: over nine months, AI tools went from completing almost none of his class assignments to completing up to 60% of them. That shift prompted him to redesign both his assessments and his curriculum, and his AI in Construction course now asks students to analyze data, develop custom AI skills and agent-based workflows, build working applications, and create portfolio websites to showcase their solutions.

In Pooladvand’s courses, students discuss how AI is used on actual construction projects and, critically, learn to verify AI-generated information using their own engineering judgment. In Song’s Advanced Construction Safety Engineering and Management course, students study how computer vision, wearable sensing, machine learning, and virtual reality are reshaping safety practice, with SAVE Lab’s virtual reality training and jobsite sensing deployments serving as case studies and hands-on experiences.

The reasoning behind this emphasis is captured in Song’s own words: in construction, decisions have physical consequences. An unverified AI output in an essay is an academic problem. An unverified AI output in a safety plan, a cost estimate, or a schedule is a potential hazard to people and projects. Teaching students to catch those errors is as important as teaching them to use the tools at all.

Why Construction Fundamentals Matter More Than Ever

A common concern is that AI will make traditional construction knowledge obsolete. Faculty at ASU argue the opposite. Strong foundations in construction methods, estimating, scheduling, safety, contracts, and project management are what allow a professional to evaluate whether an AI output makes sense. In many ways, AI makes that foundational knowledge even more important, because someone has to be able to recognize when the machine is wrong.

For prospective students, this is a useful filter when comparing programs. The best construction engineering and construction management education does not treat AI as a shortcut around core skills — it treats AI as an amplifier of expertise that has been earned through fundamentals.

What Students and Professionals Should Look For

If you are evaluating construction programs or planning a career in the industry, the ASU model suggests several qualities worth seeking out:

• Hands-on laboratory experience. Programs with active research labs — like SAVE Lab or the Construction Workforce and Technology Lab — let students work with real sensing systems, VR environments, and live jobsite data rather than abstract examples.
• Industry partnerships. Summits, consortia, and collaborations with working contractors keep coursework aligned with what companies actually deploy in the field.
• Coursework that pairs AI skills with core knowledge. Look for curricula that combine data analysis and AI tools with estimating, scheduling, safety, and project management.
• Faculty who practice responsible use. Instruction in verifying AI outputs and applying engineering judgment is essential in a field where mistakes carry physical risk.

Ready to see these programs for yourself? Schedule a campus visit or an information session to meet faculty, tour the labs, and ask how AI is woven into the curriculum.

Taking the Next Step in Construction Education and Careers

AI adoption in construction is accelerating, and the gap between companies that use it well and those that do not is widening. The work happening at Arizona State University — from wearable heat stress systems tested with real contractors to courses that teach students to build and verify AI workflows — shows what a serious response to that shift looks like: research that solves field problems, industry collaboration that keeps it grounded, and education that prepares graduates to lead responsibly.

For students considering a career in construction engineering or management, and for professionals looking to deepen their expertise, the message is clear. The industry needs people who understand both the technology and the fundamentals behind it — and programs that teach both are the ones worth pursuing.

Interested in applying? Submit your application to a construction engineering or construction management program today, and share your own experiences with AI on the jobsite in the comments below — your perspective could help shape the conversation for the next generation of builders.