Development of intelligent avionics systems to optimize and automate aircraft trajectories, while reducing the environmental impact of aviation

尽管受到COVID-19大流行的影响，但航空利益攸关方表示，未来的空中交通将非常密集。虽然这种扩张对全球经济发展是必要的，但也会带来一些运营、安全、社会和环境方面的挑战。面对这种情况，航空业必须开发新的实践和技术，以更有效和环境可持续的方式运营飞机。该研究计划的主要目标是探索智能航空电子系统发展的新解决方案，以改善空中交通管理，减少飞机排放，同时提高飞行安全。在这种情况下，“智能”一词指的是学习飞机性能的能力，以及使用基于人工智能的技术来控制飞机的运动。在短期内，该研究项目将侧重于开发优化和自动化地面飞机轨迹管理的解决方案。但是，从长期来看，目标是将这一概念从地面推广到空气空间。实现主要目标的战略包括三个阶段。首先，将设计新的自建模算法来监测和学习飞机的性能。这里的目标是开发智能航空电子系统，随着时间的推移保持准确。所有预测飞行器轨迹、排放和噪声的数学模型也将在第一步开发。第二阶段将重点研究飞机在滑行和起飞过程中的轨迹优化。图神经网络结合ADS-B数据将考虑建模和计算地面交通。将测试确定性和进化优化算法，并比较它们的结果。最优解决方案将被定义为最小化时间、燃料消耗和排放，同时确保安全性和可行性的轨迹。最后，第三阶段将致力于利用人工智能和计算机视觉技术开发新的控制算法，使飞机能够在地面上自动移动。所有方法将使用两个专业和高质量的飞行模拟器和真实的飞行数据进行验证。该研究计划旨在提出新的解决方案，使当前的航空运输系统现代化，并朝着更优化和自主的飞机轨迹管理方向发展。此外，自主技术的使用将使飞行程序更高效、更安全，最重要的是，有助于减少排放。这项研究计划还旨在探索人工智能给航空航天领域带来的潜力，从而鼓励工业界和研究人员朝这个方向发展。最后，将对高素质人员进行创新研究课题的培训，使他们为加拿大航空航天工业做出重大贡献。

Despite the impact of the COVID-19 pandemic, aviation stakeholders suggest that tomorrow's air traffic will be extremely dense. While necessary for global economic development, this expansion will pose several operational, safety, social and environmental challenges. Faced with this situation, it is crucial for the aviation industry to develop new practices and technologies to operate aircraft in a more efficient and environmentally sustainable way. The main objective of this research program is to explore new solutions for the development of intelligent avionics systems to improve air traffic management and reduce aircraft emissions, while enhancing flight safety. The word "intelligent" in this context refers to the ability to learn the performance of an aircraft, as well as the use of artificial intelligence-based techniques to control the motion of an aircraft. In the short term, this research program will focus on the development of solutions to optimize and automate the management of aircraft trajectories on the ground. However, in the longer term, the objective will be to generalize this concept from the ground to the airspace. The strategy for achieving the main objective includes three phases. First, new self-modeling algorithms will be designed to monitor and learn the performance of an aircraft. The objective here is to develop intelligent avionics systems that remain accurate over time. All mathematical model to predict air-craft trajectory, emissions and noise will be also developed during this first step. The second phase will focus on optimizing aircraft trajectories during taxiing and takeoff. Graph neural networks combined with ADS-B data will be considered to model and account ground traffic. Deterministic and evolutionary optimization algorithms will be tested, and their results compared. The optimal solution will be defined as the trajectory that minimizes time, fuel consumption, and emissions, while ensuring safety and feasibility. Finally, the third phase will be devoted to the development of new control algorithms using artificial intelligence and computer vision techniques to enable aircraft to move automatically on the ground. All methodologies will be validated using two professional and highly qualified flight simulators and real flight data. This research program aims to propose new solutions to modernize the current air transport system and move towards a more optimal and autonomous management of aircraft trajectories. In addition, the use of autonomous technologies will make flight procedures more efficient, safer and, most importantly, help reduce emissions. This research program also aims to explore the potential that artificial intelligence can bring to the aerospace field, and thus encourage industry and researchers to pursue this direction. Finally, highly qualified personnel will be trained on innovative research topics, preparing them to make a significant contribution to the Canadian aerospace industry.