Closed-Loop Brain Imaging May Improve Pilot Training

Roughly half of airline pilots in the United States will be required to retire during the next 15 years, exacerbating what is already a shortage of professionals, the Regional Airline Association reports. But what if there is a way to improve pilot training to get qualified pilots on the job sooner, at less cost, and ensure all receive the necessary, foundational training efficiently before their careers take flight?

Training of complex cognitive skills, such as aircraft piloting, requires long practice sessions. The skill-acquisition process is most effective when the learner is ready and engaged with the task that matches the learner’s current abilities. If the current task is too difficult or too easy, it may lead to unnecessary over-training or insufficient under-training, discouraging the learner and potentially resulting in a lack of skills learned.

“Brain function measures of a learner during training can be combined with behavioral performance metrics to provide a more comprehensive assessment of the learner’s progress and these can be used throughout the training to personalize and optimize the process,” said Hasan Ayaz, PhD, an associate professor in the School of Biomedical Engineering, Science and Health Systems. “However, measuring brain function continuously in practical learning settings at scale wasn’t feasible until recently. The latest generation of wearable and mobile neuroimaging modality, functional near infrared spectroscopy sensors provide new opportunities for both cognitive workload and training assessment of operators, in natural environments continuously.”

So, Ayaz’s team developed a closed-loop training protocol that inputs a learner’s brain activity to adapt the training for an individual based on their brain activity and performance, in a process known as neuroadaptive training. In this preliminary study of young adults, in collaboration with Lockheed Martin Advanced Technology Laboratory program manager Matthias Ziegler, the team tested the neuroadaptive training in a four-session, two-week long series of tests with realistic flight simulator scenarios.

The results, recently published in the journal Frontiers in Neuroergonomics, suggest that fNIRS-informed training can improve the way we evaluate individual performance for mission-critical essential workers.

In the study, two groups of young adults aged 20-28, participated in a four-session, two-week- long series of tests to practice realistic scenarios on flight simulator software that included flying, landing, situational awareness and other aspects of piloting. As the participants performed these tasks, their brain activity was captured continuously with fNIRS headband sensors positioned over prefrontal cortex and informed the training progress. The neuroadaptive group’s training protocol was adapted at each session, based on their brain activity-derived mental workload and performance in the previous session. Those who went through the neuroadaptive training showed higher levels of performance, reached more difficult levels earlier and performed better than those in a control group that underwent traditional behavioral training in which participants get a more difficult task once they complete the previous one.

“We’re proposing to monitor participants throughout training, continuously assess their cognitive workload and change the difficulty of tasks to maximize learning most efficiently,” said Ayaz. “This is a new way to use brain sciences and neuroimaging to improve the learning process. We’re adapting the scenarios based on individuals’ brain activity in a closed loop, consistent with neuroergonomics.”

Such tests, Ayaz argues, are particularly important in mission-critical tasks, like surgery, aviation and other professions where every second counts and lives are on the line. It can also be used in lower-stakes moments or typical everyday tasks.

“Advancement and complexity of technology has made training a time consuming and difficult task,” said Ziegler. “Dr. Ayaz’s work to personalize training based on brain activity, therefore reducing training time and increasing success rate, is an exciting advancement in neuroscience- assisted training that has the potential to reshape how our workforce develops its skills.”

The burgeoning field of neuroergonomics research utilizes wearable neurotechnologies and incorporates both theory and applications to advance our understanding of brain with practical implications in diverse sectors such as healthcare, education, transportation, manufacturing, entertainment, communication and many other aspects of everyday life. 

Ayaz, together with Frederic Dehais, PhD, a professor at ISAE-SUPAERO, in Toulouse, France, and colleagues have been organizing the international neuroergonomics conference series in 2016, to discuss this emerging field, with the next conference on July 28 to August 1, 2022 in New York City.

Editor’s note: The authors note that fNIR Devices, LLC manufactures the optical brain imaging instrument and licensed IP and know-how from Drexel University. Ayaz helped develop the technology and holds a minor share in the firm. The study was supported by Lockheed Martin Advanced Technology Laboratories.

Tagged with: