In 2022, Randall Pietersen, a construction engineer of the American Air Force, set up a training mission to assess damage to the runway at the airport, practicing the “Base Recovery” protocol after a simulated attack. For many hours, his team went through the area in chemical equipment, a radio in Geocoordinates, when they documented damage and sought threats such as unexploded ammunition.
The works are standard for all air force engineers before their placement, but it was of particular importance for Pietersen, who spent the last five years faster, a safer approach to the evaluation of airports as a master’s degree, and now a doctoral student and works of Mathworks in myth. For Pietorsen, intensive, tedious and potentially perilous work emphasized the potential of his research to enable remote assessments of the airport.
“This experience was really open,” says Pietersen. “For almost a decade, we have been told that the new system, based on drones, is during work, but is still limited to the inability to identify unexploded bust; They look too similar to rocks or debris from the air. Even ultra-high resolution cameras simply do not work well enough. Fast and remote assessment of the airport is not yet a standard practice. We are still prepared for it only on foot and that’s where my research appears. “
The goal of Pietersen is to create automated drones based on the evaluation of airport damage and detection of ammunition unexploded. This brought him a number of research paths, from deep learning to tiny unrestricted air systems to “hyperspertural” imaging, which reflects passive electromagnetic radiation in a wide spectrum of wavelength. Hyperspertural imaging becomes cheaper, faster and more robust, which can make Pietersen research more and more useful in terms of applications, including agriculture, crisis reacting, extraction and building assessments.
Finding computer science and community
Growing up in the suburbs of Sacramento in California, Pietersen bowed to mathematics and physics at school. But he was also a running athlete and a scout Eagle and wanted to combine his interests.
“I liked the multi -faceted challenge of the Air Force Academy,” says Pietersen. “My family has no history of service, but the recruiters talked about holistic education, in which scientists were one part, but also sports performance and leadership. This is a well -rounded approach to experience in College, I liked it. “
Pietersen specialized in land engineering as a bachelor’s degree in Air Force Academy, where he first began to learn how to conduct academic research. This required him to learn some computer programming.
“Last year, Air Force research laboratories had some projects related to the surface that fell into my scope as a construction engineer,” recalls Pietersen. “Although my knowledge about the domain helped define initial problems, it was clear that developing appropriate solutions would require a deeper understanding of computer vision and music video.”
The projects that dealt with the assessments of pavements at the airport and the detection of threats also led Pietersen to start the employ of hyperspertral imaging and machine learning, to which he built when he came to the myth to continue his master and doctorate in 2020.
“The myth was a clear choice for my research, because the school has such a strong history of research partnerships and multidisciplinary thinking that helps to solve these unconventional problems,” says Pietersen. “There is no better place in the world than the myth for the most modern work.”
Before Pietersen reached the myth, he also dealt with extreme sports, such as ultra-marathons, a parachutist and rock climbing. Some of them result from his participation in infantry skills as a student. Multi -day competitions are races focused on the army, in which teams from around the world traverse mountains and classes, such as tactical fighting, orientation and behavior.
“The crowd with whom I ran in college was really in this thing, so it was a kind of natural consequence of building relationships,” says Pietersen. “These events would lead you for 48 or 72 hours, sometimes with a mixed sleep, and you can compete with your friends and have fun.”
Since the arrival in the myth with his wife and two children, Pietersen accepted the local running community, and even worked as a parachute jumping instructor in Novel Hampshire, although he admits that Winters East Wybrzeże was challenging for him and his family.
Pietersen took place from 2022 to 2024, but did not conduct research from the comfort of the home office. The training, which showed him the reality of the airport’s assessment, took place in Florida, and then was placed in Saudi Arabia. He happened to write one of his doctoral publications from a tent in the desert.
Now, in myth and the approaching doctorate this spring, Pietersen is grateful for all people who supported him during his journey.
“It was nice to discover various engineering disciplines, trying to come up with everything with all mentors in myth and resources available above these really niche problems,” says Pietersen.
Target research
In the summer of 2020, Pietersen completed an internship with Halo Trust, a humanitarian organization working on removing mines and other explosives from war affected. Experience showed another powerful application for his work in myth.
“We have regions after a conflict around the world, in which children try to play, and there are mines in their courtyards, and in their courtyards,” says Pietersen. “Ukraine is a good example in the news. The remains of war always remain. At the moment, people must enter these potentially dangerous areas and remove them, but new remote detection techniques can speed up this process and make it much safer. “
Although the work of Master Pietesen was mainly around the assessment of normal wear of the surface structures, his doctorate focused on how to detect unpredictable ordinances and sedate damage.
“If the runway were attacked, there will be bombs and craters on it,” says Pietersen. “This is a difficult environment to assess. Different types of sensors separate different types of information, and each of them has its own advantages and disadvantages. There is still a lot to do both on the hardware and software side, but so far hyperspertural data seem to be a promising discriminator for deep learning detectors. “
After graduating from studies, Pietersen will be stationed in Guam, where air force engineers regularly carry out the same simulations of the airport assessments in which he participated in Florida. He hopes that one day these assessments will be carried out not by people in protective equipment, but by drones.
“We are currently relying on visible lines of space,” says Pietersen. “If we manage to go to solutions for spectral imaging and deep learning, we can finally carry out remote grades that make everyone safer.”