Multi-Agent Planning for Autonomous Airport Surface Movement Operations

Both EASA and SESAR JU define a vision and roadmap towards an autonomous air traffic management system. Furthermore, past and ongoing SESAR JU projects investigate how to increase the efficiency and predictability of current operations by means of automation. In this paper, we explore the operational implications that may result from fully-automated airport surface movement operations. In our model, a hierarchical multi-agent system coordinates and controls all movements on the airport surface. It comprises the Airport Operations Agent to handle the flight schedule and runway configuration, the Routing Agent to compute conflict-free trajectories, and the Guidance Agents to instruct and monitor the Aircraft Agents while these execute the planned routes. To compute conflict-free trajectories for all agents, we tailored state-of-the-art multi-agent motion planning algorithms to the requirements of taxiing operations: the two-level routing algorithm combines Priority-Based Search (PBS) with Safe Interval Path Planning (SIPP). It accounts for the different taxiing processes such as pushback, engine-start, or wake turbulence separation for takeoffs by defining an activity sequence for each agent. Furthermore, we include the kinematics and different sizes of the aircraft as well as a minimal safety distance between them. Using the real-world flight schedules of two of the busiest days at Amsterdam Airport Schiphol, including different runway configurations, we examine the performance of the autonomous taxiing system with respect to the historic operations. For the considered simulation conditions, we show that the MAS yields 15% lower taxi times for both arriving and departing flights, discuss how reliable these results are, and point out directions for future work.