Automating the resolution of flight conflicts: Deep reinforcement learning in service of air traffic controllers

TL;DR

This paper introduces a graph convolutional multiagent reinforcement learning approach to automate flight conflict resolution, aiming to improve safety, transparency, and operational efficiency in air traffic control.

Contribution

It presents a novel multiagent deep reinforcement learning method using graph convolutional networks for conflict detection and resolution in air traffic management.

Findings

High-quality conflict resolution solutions achieved

Addresses transparency concerns in AI decision-making

Suitable for complex, dense air traffic scenarios

Abstract

Dense and complex air traffic scenarios require higher levels of automation than those exhibited by tactical conflict detection and resolution (CD\&R) tools that air traffic controllers (ATCO) use today. However, the air traffic control (ATC) domain, being safety critical, requires AI systems to which operators are comfortable to relinquishing control, guaranteeing operational integrity and automation adoption. Two major factors towards this goal are quality of solutions, and transparency in decision making. This paper proposes using a graph convolutional reinforcement learning method operating in a multiagent setting where each agent (flight) performs a CD\&R task, jointly with other agents. We show that this method can provide high-quality solutions with respect to stakeholders interests (air traffic controllers and airspace users), addressing operational transparency issues.