MIT Engineer Develops AI-Powered Drones for Safer Airfield Assessments

Cambridge, MA – Randall Pietersen, a civil engineer and PhD candidate at MIT, is revolutionizing airfield assessments with drone-based automated systems. His research aims to replace the current time-intensive, painstaking, and potentially dangerous manual processes used by the U.S. Air Force.

Pietersen’s work, supported by a MathWorks Fellowship, focuses on developing drone systems capable of assessing airfield damage and detecting unexploded munitions remotely. This innovative approach leverages deep learning, small uncrewed aerial systems, and hyperspectral imaging. Hyperspectral imaging, which captures electromagnetic radiation across a broad spectrum of wavelengths, is becoming more accessible and could significantly enhance the accuracy and efficiency of airfield assessments.

“That experience was really eye-opening,” Pietersen says, reflecting on a training mission where his team spent hours assessing a simulated attack site in chemical protection gear. “We’ve been told for almost a decade that a new, drone-based system is in the works, but it is still limited by an inability to identify unexploded ordnances; from the air, they look too much like rocks or debris. Rapid and remote airfield assessment is not the standard practice yet. We’re still only prepared to do this on foot, and that’s where my research comes in.”

Pietersen’s journey began at the Air Force Academy, where he majored in civil engineering and discovered his interest in computer programming and research. Projects involving airfield pavement assessments and threat detection led him to explore hyperspectral imaging and machine learning. MIT’s multidisciplinary approach and strong research partnerships made it the ideal place for his advanced studies.

Beyond his academic pursuits, Pietersen is an avid athlete, participating in ultra-marathons, skydiving, and rock climbing. He also spent time deployed in Saudi Arabia, where he even wrote one of his PhD journal publications from a tent in the desert.

An internship with the HALO Trust in 2020 further solidified Pietersen’s commitment to using his research for humanitarian purposes. Clearing landmines and unexploded ordnance in post-conflict regions is another area where his drone-based assessment systems could significantly improve safety and efficiency. He emphasized Ukraine is a good example of this in the news today. There are always remnants of war left behind. Right now, people have to go into these potentially dangerous areas and clear them, but new remote-sensing techniques could speed that process up and make it far safer.

“If the runway is attacked, there would be bombs and craters all over it,” Pietersen says. “This makes for a challenging environment to assess. Different types of sensors extract different kinds of information and each has its pros and cons. There is still a lot of work to be done on both the hardware and software side of things, but so far, hyperspectral data appears to be a promising discriminator for deep learning object detectors.”

Upon completing his doctorate, Pietersen will be stationed in Guam, where he hopes to implement his drone-based assessment systems, making airfield assessments safer and more efficient.

“Right now, we rely on visible lines of site,” Pietersen says. “If we can move to spectral imaging and deep-learning solutions, we can finally conduct remote assessments that make everyone safer.”