Augmenting flight training with artificial intelligence to efficiently train pilots

利用人工智能增强飞行训练，有效培训飞行员

• 批准号: 576737-2022
• 负责人: Taylor, MatthewME
• 金额: $ 8.74万
• 依托单位: University of Alberta
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=750479
• 关键词: Augmenting; flight; training; artificial; intelligence

There is a critical shortage of commercial pilots in Canada. 55,000 additional pilots will be needed by 2025, in large part because pilots qualified to conduct such training are in very high demand and short supply. With this partnership, pioneers in human-in-the-loop research and intelligent tutoring systems from the University of Alberta and the University of Manitoba join forces with Delphi Technology Corp (DTC), an innovative Winnipeg-based flight training solution provider. We will collaborate to provide novel methods to improve trainee student outcomes without requiring additional instructors to facilitate them. The primary outcome of this project is to improve DTC's ability to quickly train more pilots with high success rates without increasing instructor workload. The solutions proposed in this research will help to 1) train more student pilots efficiently, 2) increase retention of students, 3) scale student training to better satisfy this scarcity of pilots, and 4) provide a versatile and effective training platform. This applied research will use machine learning and intelligent tutoring system techniques to enable a new, simulation-based training pipeline that aims to dramatically increase the success of DTC's training program. Fundamental research, conducted concurrently, will also help advance the state of the art human-AI collaboration and tutoring.

加拿大的商业飞行员严重短缺。到2025年，还需要5.5万名飞行员，这在很大程度上是因为有资格进行此类培训的飞行员供不应求。通过这一合作伙伴关系，来自艾伯塔大学和马尼托巴大学的人在回路研究和智能教学系统方面的先驱与总部位于温尼伯的创新飞行培训解决方案提供商德尔福技术公司(DTC)联手。我们将合作提供新的方法来改善实习生的结果，而不需要额外的讲师来帮助他们。该项目的主要成果是提高DTC在不增加教员工作量的情况下，以高成功率快速培训更多飞行员的能力。本研究提出的解决方案将有助于1)有效地培训更多的学员飞行员，2)增加学员的留存率，3)扩大学员培训规模，以更好地满足飞行员短缺的需求，4)提供一个通用而有效的培训平台。这项应用研究将使用机器学习和智能教学系统技术来实现一种新的、基于模拟的培训渠道，旨在显著提高DTC培训计划的成功率。同时进行的基础研究也将有助于推进人类-人工智能合作和辅导的最先进水平。