Optimal Novel Taxiing Navigation of a BOEING-747 Aircraft Using Artificial Intelligence

Aircraft ground movement coordination plays a key role in improving airport efficiency, as it acts as a link to all other ground operations. Finding novel approaches to coordinate the movements of a fleet of aircraft at an airport in order to improve system resilience to disruptions with increasing autonomy is at the centre of many key studies for airport airside operations. Moreover, autonomous taxiing is envisioned as a key component in future digitalized airports. However, state-of-the-art routing and scheduling algorithms for airport ground movements do not consider high-fidelity aircraft models at both the proactive and reactive planning phases.
The majority of such algorithms do not actively seek to optimize fuel efficiency and reduce harmful greenhouse gas emissions. This thesis proposes new approaches using Artificial Intelligence (AI) for optimal taxiing navigation of a high-fidelity aircraft model, working in conjunction with a routing and scheduling algorithm that determines the taxi route, waypoints, and time deadlines. The proposed approaches used in this thesis are: PID controller, artificial neural networks controller, Fuzzy Inference System (FIS) model and an online controller using reinforcement learning.
The proposed approaches integrate a MATLAB-Simulink model of the BOEING-747 aircraft with artificial intelligence based control that successfully generate fuel-efficient four- dimensional trajectories 4DTs in real time, while taking constraints on operations into account. The proposed methodologies are realistic and simple to implement. Moreover, simulation studies show that the proposed approaches are capable of providing a reduction in the fuel consumed during the taxiing of a large Boeing 747-100 jumbo jet.