A Survey on Reinforcement Learning in Aviation Applications

TL;DR

This survey reviews how reinforcement learning is increasingly applied to aviation for sequential decision-making, highlighting recent advances, challenges, and future research directions in this data-driven approach.

Contribution

It provides a comprehensive overview of RL applications in aviation, detailing standard formulations, existing implementations, and identifying technical gaps for future exploration.

Findings

RL is promising for aviation decision-making tasks.

Many applications are formulated as sequential decision problems.

The survey highlights technical gaps and future research directions.

Abstract

Compared with model-based control and optimization methods, reinforcement learning (RL) provides a data-driven, learning-based framework to formulate and solve sequential decision-making problems. The RL framework has become promising due to largely improved data availability and computing power in the aviation industry. Many aviation-based applications can be formulated or treated as sequential decision-making problems. Some of them are offline planning problems, while others need to be solved online and are safety-critical. In this survey paper, we first describe standard RL formulations and solutions. Then we survey the landscape of existing RL-based applications in aviation. Finally, we summarize the paper, identify the technical gaps, and suggest future directions of RL research in aviation.