AI heat-stress system targets construction worker safety

SAVE Lab, researchers monitor workers’ wearable biosensors and environmental conditions at a construction site. Image: SAVE Lab

The system, developed by ASU’s Safety Automation and Visualization Environment Laboratory (SAVE Lab) uses data from wearable biosensors and environmental monitors to assess individual worker risk in real time.

The project has been developed with US contractors Achen-Gardner Construction, Willmeng Construction and CHASSE Building Team.

ASU said the technology analyses physiological and environmental data to identify early signs of heat stress, fatigue and other risks, before sending personalised alerts to workers or supervisors.

Siyuan Song, associate professor of construction engineering at ASU and director of the SAVE Lab, said AI could help construction safety move from reacting to incidents to preventing them.

“Each of these is difficult to observe until it becomes dangerous, and that is exactly where AI helps,” she said. “It monitors conditions no human observer could track, recognises that two construction workers in identical conditions can respond differently, and shifts safety management from reacting to incidents toward preventing them.”

The work comes as construction companies face growing pressure to manage heat risk on jobsites, particularly in hotter US states.

ASU researchers are also using virtual reality, eye tracking and large language models to study how workers respond to hazards, analyse accident reports and improve safety training.

The university said its wider construction research programme is exploring how AI can be used in workforce training, digital twins, drones, robotics and human-centred construction technologies.

Shiva Pooladvand, assistant professor of construction engineering at ASU, said AI could be used to analyse data from workers and the jobsite environment to identify patterns linked to decision-making, behaviour and safety.

“This enables more personalised interventions to enhance safety, automation and productivity,” she said.