Investigating the Assessment of Artificial Intelligence as a Method to Improve Aviation Pilot Training with Simulator

The aviation industry was set to see unprecedented growth over the two decades. Key occupationspredicted to be in shortage included not only pilots, but also flight instructors. Undoubtedly, Covid-۱۹is currently having a huge impact on the industry. Nevertheless, the current environment furtherstrengthens the need for pilots to maintain their training. Consequently, there is pressure to deliver highqualitytraining outcomes for an increasing number of pilots and trainees with limited resourcesavailable. Current simulator-based training schemes are limited by placing a significant reliance on thepersonal experience of flight instructors to assess pilot performance. Finding ways to increase the qualityand efficiency of simulator-based training is therefore of high importance. With recent advances inartificial intelligence, it is possible to use Machine Learning(ML) techniques to extract latent patternsfrom massive datasets, to analyze pilot trainees’ activities, and to provide feedback on their performanceby processing hundreds of different parameters available on flight simulators. An ML-aided pilottraining and education framework is needed that exploits the power of the ML techniques for moreobjective performance evaluation. In this paper to address these concerns, an artificial intelligence-basedtechnology was evaluated that provided a simulator pre-training program for student pilots (n = ۳۷) priorto beginning their Private Pilot training. The two-one-sided test (TOST) procedure was used to evaluatethe equivalence of the training and control groups. Then, Roscoe’s Transfer Effectiveness Ratio wasused to assess the effect of a simulator pre-training program on the pre-solo training outcomes of studentpilots. The results showed that a guided simulator pre-training program reduces flight training hours,ground training hours, and the number of calendar days required to complete their pre-solo block oftraining. These results will help inform flight training organizations that are considering new ways tohelp support their training pipeline and increase the training efficiency of their organization.

کلیدواژه ها:

artificial intelligence ، flight instructor shortage ، flight training ، pilot shortage ، simulatorpre-training ، student pilots