Canada needs pilots to fly its planes, and researchers at the University of Waterloo are using artificial intelligence (AI) to help get more pilots into the air.
With support from the Government of Canada through the Federal Economic Development Agency of Southern Ontario (FedDev Ontario), experts at the Waterloo Sustainable Aviation Institute (WISA) are creating more licensed pilots in less time and at less cost. We utilize a number of new technologies to train. With money and in a more environmentally friendly way.
At its core, WISA is leveraging AI to train machine learning algorithms to instruct more pilots.
“The central idea of our research is to see how accurately AI can help evaluate pilot performance and support instructors in pilot training,” explains Shi Cao, PhD, professor of systems design engineering who is leading the project. “The goal is not to replace humans with AI, but to have AI assist and support humans.”
Canada is facing a severe pilot shortage and needs 7,300 more pilots by 2025, according to the Canadian Aerospace Council. Mr. Cao, an ergonomics expert, believes that solving this problem requires collaboration between industry, government, and academia.
Today, pilot training programs blend traditional methods such as lectures, documentation and flight hours with new technology.
“Flight simulators have become more popular in recent years, creating opportunities to experiment with new training methods. However, there is still much to explore when it comes to technologies such as data analytics, wearable sensors, virtual reality, and augmented reality. There are a lot of things,” said Cao.
Cao and WISA colleagues Dr. Ewa Niechwiej-Szwedo, Dr. Elizabeth Irving and Dr. John Muñoz are working together to show how new technologies can enhance pilot training, reduce environmental impacts and improve understanding of pilot skill development.
To achieve their goals, the team will lay the foundation for the project by first focusing on data collection, building an integrated data platform, and developing a data management strategy. They are developing image recognition algorithms to accurately capture pilots' real-time actions, a feat that was previously impossible. At the same time, we are collecting extensive sample data from flight simulators and aircraft to enhance data analysis. This data is used to train machine learning algorithms. Leveraging the vast and reliable pilot data, we plan to use AI to evaluate and predict pilot performance. The goal is to incorporate these AI tools into pilot training programs and measure their effectiveness.
“Our findings could help develop tools that automatically assess pilot performance and provide feedback for improvement,” Cao said. “This could complement the role of the flight instructor and allow trainees to self-assess in flight simulators or solo flights, where it is currently difficult to assess and provide feedback.”
Cao and his colleagues at WISA have benefited from the support in more ways than one. Brad Montsion, a 2013 graduate of Waterloo's scientific aviation program and now a pilot for a major Canadian airline, is earning his PhD as part of WISA's collaborative aviation program. He is enrolled in the Systems Design Engineering aeronautics option with Cao as his supervisor.
As one of the few Waterloo doctoral students with flying experience in the aviation industry, Montsion has been frequently consulted by Cao and other researchers about their research. He also designed the evaluation tools the research group uses.
“I am confident that Dr. Cao's research will be useful for future pilot training,” Montsion said. cited the lack of access to such training. “We will conduct evidence-based training using technology such as video recording, flight data parameters, and eye-tracking devices to support this assessment, and further training using simulators and virtual and augmented reality. This can help address these barriers.”
One of our key corporate partners is AdHawk Microsystems. Founded by University of Waterloo alumni and faculty, the company has invented a new type of low-power, research-grade eye tracking device. The WISA team uses this technology to record eye movement data. At the same time, researchers are renting aircraft from the Brantford Flight Center and using the services of flight instructors to collect data from both students and licensed pilots. This information is added to the computational model to further improve its quality.
WISA researchers have made great progress, but much work remains. Cao said the pilot will continue to collect his data, refine the model and test its accuracy. The research results will be published in an academic journal for peer review, and we plan to train graduate students in this area of research to support the aviation sector in the future.
“We have all these new technological tools,” Kao said, “so why wouldn't we use them? Preliminary evidence supports this approach to pilot training, and we intend to push further.”
This research project was funded by a $296,500 Research-for-Impact gift provided through WISA. The funding is part of a $9.17 million investment made as part of FedDev Ontario's Aerospace Regional Recovery Initiative. WISA supported a total of 38 Research-for-Impact projects.
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or stance, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
