An IPaT translational research team is working to advance aircraft maintenance.
 

In the dynamic world of aviation maintenance, precision, quickness, and meticulous documentation are essential. Maribeth Gandy Coleman, director of research and a Regents’ Researcher in Georgia Tech’s Institute for People and Technology (IPaT), has been leading an IPaT translational research team working to advance aircraft maintenance with PartWorks, an Atlanta-based aerospace engineering firm dedicated to extending the life and improving the operational efficiency and availability of commercial and military aircraft and spacecraft.

Coleman, a recognized augmented reality expert at Georgia Tech, has been working with the PartWorks’ engineering team to solve aircraft maintenance challenges, leading to measurable improvements in labor costs, training, repair quality, turnaround time, and maintenance process validation. This research partnership has led to the development of several patented and patent-pending solutions related to aircraft maintenance.

“I could not have hired anybody with the diverse skill sets that both Maribeth and the Georgia Tech team brought to bear,” said Scott Geller, CEO of PartWorks. “We’ve utilized different and complicated skill sets, sometimes in small quantities, that have made our project work very cost-effective. We’ve used an iterative research and development process that hasn’t had a shocking cost or huge surprises. And the Georgia Tech team has been both easy and fun to work with, too.”

This collaboration has led to PartWorks launching a new aircraft maintenance, repair, and overhaul (MRO) augmented reality solution called RepĀR™. Designed for both military and commercial aviation, RepĀR’s augmented reality overlay transforms structural repairs by ensuring accuracy, reducing labor costs, minimizing human error, and accelerating return-to-service timelines. 

RepĀR rapidly captures structural repair data, embedding spatial awareness and real-time validation into maintenance workflows. Novice technicians can achieve results beyond their operational experience, while seasoned technicians experience measurable productivity gains.

“RepĀR exemplifies how targeted computer vision applications can deliver immediate value in aerospace manufacturing and maintenance,” said Shelley Peterson, CEO of Wizard Wells. “By precisely identifying fastener locations and validating tool placement, it reduces rework, minimizes human error, and ensures tasks are performed right the first time.”

PartWorks demonstrated RepĀR at the Aviation Week Network’s MRO Americas, which took place April 8 – 10 at the Georgia World Congress Center in Atlanta.

“This collaborative research with industry demonstrates why Georgia Tech has interdisciplinary research institutes such as IPaT, and why you have research faculty,” said Coleman. “You’re probably not going to be able to get some Ph.D. students to do this work. The focus here with PartWorks is on translation. It’s cross-disciplinary collaboration and translation built on augmented reality work we’ve been doing for 25 years and implementing cutting-edge technology crafted to the right context to support aircraft maintenance.”

“This Georgia Tech collaboration and augmented reality MRO research and development are in conjunction with a multiyear contract we’re working on with the Air Force Research Lab (AFRL) in Dayton, Ohio,” said Geller. “We’re appreciative of their partnership and excited to be getting commercial interest in RepĀR from both military and commercial aviation OEMs and MROs as well as space industry companies.”

Inspired by the movements of a tiny parasitic worm, Georgia Tech engineers have created a 5-inch soft robot that can jump as high as a basketball hoop. 

Their device, a silicone rod with a carbon-fiber spine, can leap 10 feet high even though it doesn’t have legs. The researchers made it after watching high-speed video of nematodes pinching themselves into odd shapes to fling themselves forward and backward. 

The researchers described the soft robot April 23 in Science Robotics. They said their findings could help develop robots capable of jumping across various terrain, at different heights, in multiple directions. 

Read the entire story and see video of the jumping robot and small nematodes. 

For anyone who has only seen the movie on television, The Wizard of Oz is an incredible movie theater experience. Its larger-than-life characters, vivid colors, and memorable soundtrack were made for the big screen.

Now, a Georgia Tech professor and several alumni are helping bring the 1939 classic Hollywood film to what will likely be its largest screen ever: the Las Vegas Sphere's 160,000-square-foot interior screen.

Read more to discover their pivotal role and how generative AI is used to "reconceptualize" the film for the August 28 premiere of The Wizard of Oz at Sphere.

A Georgia Tech alum’s dissertation introduced ways to make artificial intelligence (AI) more accessible, interpretable, and accountable. Although it’s been a year since his doctoral defense, Zijie (Jay) Wang’s (Ph.D. ML-CSE 2024) work continues to resonate with researchers.

Wang is a recipient of the 2025 Outstanding Dissertation Award from the Association for Computing Machinery Special Interest Group on Computer-Human Interaction (ACM SIGCHI). The award recognizes Wang for his lifelong work on democratizing human-centered AI.

“Throughout my Ph.D. and industry internships, I observed a gap in existing research: there is a strong need for practical tools for applying human-centered approaches when designing AI systems,” said Wang, now a safety researcher at OpenAI.

“My work not only helps people understand AI and guide its behavior but also provides user-friendly tools that fit into existing workflows.”

[Related: Georgia Tech College of Computing Swarms to Yokohama, Japan, for CHI 2025]

Wang’s dissertation presented techniques in visual explanation and interactive guidance to align AI models with user knowledge and values. The work culminated from years of research, fellowship support, and internships.

Wang’s most influential projects formed the core of his dissertation. These included:

• CNN Explainer: an open-source tool developed for deep-learning beginners. Since its release in July 2020, more than 436,000 global visitors have used the tool.
• DiffusionDB: a first-of-its-kind large-scale dataset that lays a foundation to help people better understand generative AI. This work could lead to new research in detecting deepfakes and designing human-AI interaction tools to help people more easily use these models.
• GAM Changer: an interface that empowers users in healthcare, finance, or other domains to edit ML models to include knowledge and values specific to their domain, which improves reliability.
• GAM Coach: an interactive ML tool that could help people who have been rejected for a loan by automatically letting an applicant know what is needed for them to receive loan approval.
• Farsight: a tool that alerts developers when they write prompts in large language models that could be harmful and misused.  

“I feel extremely honored and lucky to receive this award, and I am deeply grateful to many who have supported me along the way, including Polo, mentors, collaborators, and friends,” said Wang, who was advised by School of Computational Science and Engineering (CSE) Professor Polo Chau.

“This recognition also inspired me to continue striving to design and develop easy-to-use tools that help everyone to easily interact with AI systems.”

Like Wang, Chau advised Georgia Tech alumnus Fred Hohman (Ph.D. CSE 2020). Hohman won the ACM SIGCHI Outstanding Dissertation Award in 2022.

Chau’s group synthesizes machine learning (ML) and visualization techniques into scalable, interactive, and trustworthy tools. These tools increase understanding and interaction with large-scale data and ML models. 

Chau is the associate director of corporate relations for the Machine Learning Center at Georgia Tech. Wang called the School of CSE his home unit while a student in the ML program under Chau.

Wang is one of five recipients of this year’s award to be presented at the 2025 Conference on Human Factors in Computing Systems (CHI 2025). The conference occurs April 25-May 1 in Yokohama, Japan. 

SIGCHI is the world’s largest association of human-computer interaction professionals and practitioners. The group sponsors or co-sponsors 26 conferences, including CHI.

Wang’s outstanding dissertation award is the latest recognition of a career decorated with achievement.

Months after graduating from Georgia Tech, Forbes named Wang to its 30 Under 30 in Science for 2025 for his dissertation. Wang was one of 15 Yellow Jackets included in nine different 30 Under 30 lists and the only Georgia Tech-affiliated individual on the 30 Under 30 in Science list.

While a Georgia Tech student, Wang earned recognition from big names in business and technology. He received the Apple Scholars in AI/ML Ph.D. Fellowship in 2023 and was in the 2022 cohort of the J.P. Morgan AI Ph.D. Fellowships Program.

Along with the CHI award, Wang’s dissertation earned him awards this year at banquets across campus. The Georgia Tech chapter of Sigma Xi presented Wang with the Best Ph.D. Thesis Award. He also received the College of Computing’s Outstanding Dissertation Award.

“Georgia Tech attracts many great minds, and I’m glad that some, like Jay, chose to join our group,” Chau said. “It has been a joy to work alongside them and witness the many wonderful things they have accomplished, and with many more to come in their careers.”

Cranes are common features in urban skylines. Because construction projects are constantly beginning and ending, the exact number of cranes in use globally is unknown. What is known, however, is that cranes have caused hundreds of deaths and catastrophic injuries. In the U.S. alone, dozens of deaths occur annually, and the construction industry loses billions of dollars. 

“Crane usage is not well regulated or well measured. A lot of accidents are not reported or cataloged — and for those that are, there’s often not a proper investigation,” noted William Singhose, professor in Georgia Tech’s George W. Woodruff School of Mechanical Engineering and director of the Crane Safety Research Center.  

The center includes researchers from Georgia Tech, the University of Washington, Utah State University, construction equipment suppliers, and industrial automation specialists. Together, they hope to bridge the gap between engineering curricula, practical applications, and legislation.  

Read the full story on the George W. Woodruff School of Mechanical Engineering website.

In early February, Pascal Van Hentenryck, professor and chair of the School of Industrial and Systems Engineering at Georgia Tech, as well as director of the NSF AI4OPT Institute and Tech AI, visited the Georgia Tech Panama Logistics Innovation and Research Center, with the aim of fostering collaboration between Georgia Tech and Panama’s academic and tech communities. His visit was part of Georgia Tech Panama’s Breakfast & Learn series and served as a strategic introduction between Georgia Tech’s leading minds in artificial intelligence (AI) and key players in Panama’s innovation ecosystem.

Bridging Academia and Industry

Van Hentenryck’s agenda included two sessions tailored to different audiences. The first, held in collaboration with Ciudad del Saber Foundation and the Panamanian Chamber of Technology, brought together entrepreneurs, tech sector leaders, and innovation advocates to discuss global trends in artificial intelligence. He highlighted the critical role AI will play in shaping future industries, underscoring how Georgia Tech can be a vital partner in accelerating Panama’s adoption of emerging technologies.

The second session, hosted at the Georgia Tech Panama Center, was an invitation-only gathering for professors and researchers specializing in AI and engineering disciplines. Van Hentenryck shared research insights, real-world applications of AI across various fields, and ideas for strengthening academic-industry collaboration.

Cultivating Strategic Relationships

While the visit was not part of a formal initiative, it marked a significant step toward deeper engagement. Van Hentenryck forged connections with technology entrepreneurs, university faculty, and representatives from the Secretaría Nacional de Ciencia, Tecnología e Innovación, Panama’s national science and innovation authority. These conversations opened the door to potential future partnerships and collaborative projects.

“This visit gave us the opportunity to connect Panama’s academic and private sectors,” said Van Hentenryck. “We see great potential for long-term collaboration that supports the country’s innovation goals.”

Looking Ahead

The Georgia Tech Panama Center anticipates that this exchange will lead to joint research, capacity-building, and the co-development of initiatives to strengthen AI and emerging technologies in Panama. The visit reflects Georgia Tech’s ongoing commitment to supporting global innovation through knowledge sharing and strategic partnerships.

What’s the hottest thing in electronics and high-performance computing? In a word, it’s “cool.”

To be more precise, it’s a liquid cooling system developed at Georgia Tech for electronics aimed at solving a long-standing problem: overheating.

Developed by Daniel Lorenzini, a 2019 Tech graduate who earned his Ph.D. in mechanical engineering, the cooling system uses microfluidic channels — tiny, intricate pathways for liquids — that are embedded within the chip packaging.

He worked with VentureLab, a Tech program in the Office of Commercialization, to spin his research into a startup company, EMCOOL, headquartered in Norcross.

“Our solution directly addresses the heat at the source of the silicon chip and therefore makes it faster,” Lorenzini said. “Our design has our system sitting directly on the silicon chips that generate the most heat. Using the fluids in the micro-pin fins, it carries the heat that’s produced away from the chip.”

That cooling solution is directly integrated into the electronic components, making it significantly more efficient than conventional cooling methods, because it enhances the heat dissipation process.

The result is a much lower risk of overheating and reduced power consumption, he said.

Lorenzini, who researched and refined the technology in the lab of Yogendra Joshi at the George W. Woodruff School of Mechanical Engineering, was awarded a patent for the technology in September 2024.

Now, EMCOOL, which has five empoloyees, is actively pursuing venture capital funding to scale its technology and address the escalating thermal management challenges posed by AI processors in modern data centers.

The system uses a cooling block with tiny, pin-like fins on one side and a special thermal interface material on the other. There's also a junction attached to the block, with ports for the fluid to flow in and out. The cooling fluid moves through the micro-pin fins and helps to carry away the heat.

Since the ports are designed to match the shape of the fins, it ensures that the fluid flows efficiently and the heat is dissipated as effectively as possible at chip-scale. 

As electronic devices — from high-performance personal computers to data centers used for artificial intelligence processing — become more powerful, they generate more heat. This excess heat can damage components or cause the device to underperform.

Traditional cooling methods, which include fans or heat sinks, often struggle to keep pace with the increasing demands of the newer model electronics. Lorenzini’s microfluidic system addresses the challenge of overheating with his patented, more effective, compact, and integrated cooling solution.

With the guidance of Jonathan Goldman, director of Quadrant-i in Tech’s Office of Commercialization, Lorenzini secured grant funding through the National Science Foundation and the Georgia Research Alliance to further the research and build design prototypes.

“We immediately had the sense there was commercial potential here,” Goldman said. “Thermal management, or getting rid of heat, is a ubiquitous problem in the computer industry, so when we saw what Daniel was doing, we immediately began to engage with him to understand what the commercial potential was.”

Indeed, the initial focus for the technology was the $159 billion global electronic gaming market. Gamers need a lot of computing power, which generates a lot of heat, causing lag.

But beyond gaming systems, the company, which manufactures custom cooling blocks and kits at its Norcross facility, is eyeing more sectors, which also suffer from overheating, Goldman said.

The technology addresses similar overheating electronics challenges in high-performance computing, telecommunications, and energy systems.

“This work propels us forward in pushing the boundaries of what traditional cooling technologies can achieve because by harnessing the power of microfluidics, EMCOOL's systems offer a compact and energy-efficient way to manage heat,” Goldman said. “This has the potential to revolutionize industries reliant on high-performance computing, where heat management is a constant challenge.”

ATLANTA and SAN FRANCISCO — When University of California San Francisco (UCSF) officials were contracted by the U.S. Department of Agriculture (USDA) to conduct research on line speeds at pork and poultry processing facilities, they knew exactly who to ask for additional support: researchers from the Safety, Health, and Environmental Services (SHES) division at Georgia Tech.

A program housed in Tech’s Enterprise Innovation Institute, SHES offers occupational safety, health, and environmental (OSHA) consulting and training services to manufacturers across the country and has worked extensively examining food-processing workers’ exposure to chemicals.

UCSF needed a partner with specific scientific expertise regarding employee exposure to a chemical used to limit bacterial growth during pork processing. SHES’ prior working relationship with UCSF also proved beneficial. In 2021, SHES industrial hygienist Brandon Philpot was the primary investigator (PI) for a collaborative project with a group from the UC system to develop safety training for workers fabricating engineered stone countertops.

“UC San Francisco’s School of Medicine was so impressed with our team's work, they came back to us for this much larger project,” said Jenny Houlroyd, Ph.D., manager of occupational health services at SHES. “We're trying to build meaningful relationships and leverage expertise across institutions.”

Study Parameters

The study was initiated when the USDA’s Food Safety and Inspection Service division contracted with third-party experts to investigate whether increases in poultry and swine evisceration line speeds affected worker safety.

A secondary aspect of the study looked at the potential for an increase in worker exposure to peracetic acid (a food-safe chemical applied to surfaces in certain food-processing applications) when processing line speeds are increased.

“The study’s designers believed that ergonomics was the driving factor in worker safety, but they were unsure if by slaughtering and processing more animals per day, workers were also applying more peracetic acid,” said Houlroyd. “This is what the SHES team was asked to measure.”

In addition to tapping Georgia Tech’s expertise in industrial hygiene, UCSF brought in several other schools in the University of California system, primarily UC Berkeley, to assist with research.

Scope of SHES’ Role

“Our work with UC started in July 2024 and was completed in January 2025,” said Houlroyd, who served as the project’s PI and UC liaison.

Conducting the field research were SHES industrial hygienists Philpot, Sean Castillo, and Bob Hendry, as well as SHES OSHA Training Institute Education Center manager Hilarie Warren. The group traveled to six pork processing plants across the U.S. over 11 weeks.

Although the preferred method for industrial hygiene and worker exposure is to chart direct exposure to the workers themselves, the study did not allow employees to wear chemical monitors on the processing line for safety reasons.

“Our on-site sampling included putting on a variety of wearable monitors on ourselves,” Hendry said. “We’d then go to the various work areas in the plant where peracetic acid was used, stand next to the workers, and take readings.”

Each SHES team member upheld consistent sampling standards, but they were stationed at different sites. As a result, Castillo said, “It was up to us to use professional judgment to evaluate where the areas of concern were. We had to make sure we were very organized so that if I was at one site one week and Bob came out the next week, we could replicate our data almost one-to-one.”

Importance of Worker Interviews

The USDA study received Institutional Review Board (IRB) approval, which is needed if researchers interact with human subjects. Houlroyd noted that because the USDA study was considered formal research, IRB approval was necessary.

Although conducting worker interviews was not a requirement of their participation, the SHES team set up a special room where they interviewed employees on ergonomic issues and musculoskeletal disorders.

“We were able to take the load off from our collaborators and, in doing so, speed up their process so that they could finish their research earlier,” said Castillo.

Philpot stressed the importance of worker interviews to the study. “The process was good for collecting background information on what the employees were going through, day in and day out, to see if there’s anything that we could do to help their situation.”

By putting workers at ease, he and his teammates were able to gain their trust and listen to their concerns. “They could actually see that we cared about what's going on,” Philpot said.

According to Houlroyd, “One of the reasons the UC group loved Brandon and Sean and Bob so much is that we've had so much experience doing interviews, we were quick to jump into that role and help them. Our team knows that there is dignity in all labor, so we approach workers with respect. We meet the workers where they are, and we speak to them not as an academic, but human to human.”

Study Results

Acting Secretary of Labor Julie Su reported that the USDA study found that faster line speeds did result in an increased risk of injuries, but that this risk “could be mitigated with other controls, specifically having more workers on the line and having effective ergonomic plans.”

The results of the peracetic acid research conducted by SHES, however, were inconclusive. “Was there more exposure at the faster line speed?” asked Houlroyd. “We found one plant where it was true, but it wasn't consistently true at all the plants, so it was determined that there should be more research.”

Regardless, she welcomed the chance to strengthen collaborative ties with the UC system and celebrated the meticulous and compassionate work conducted by SHES.

“I am so grateful for this team for traveling to remote locations in our country and spending 11 weeks in slaughterhouses,” said Houlroyd. “I had no doubt that we could do it, and we did it well.”