Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility

TL;DR

This paper investigates the application of Deep Reinforcement Learning for contingency management in autonomous air mobility, comparing its effectiveness and challenges to classical methods in complex, hazard-prone environments.

Contribution

It extends a prior MDP formulation of contingency management and demonstrates how DRL can be trained to mitigate hazards in advanced air mobility scenarios.

Findings

DRL agents outperform classical techniques in hazard mitigation.

DRL offers adaptable decision-making in dynamic environments.

Verification of DRL systems remains challenging.

Abstract

Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) and with it comes novel challenges and opportunities for transforming aviation. As AAM operations introduce increasing heterogeneity in vehicle capabilities and density, increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper focuses on one example where increased automation has been suggested. Autonomous operations will need contingency management systems that can monitor evolving risk across a span of interrelated (or interdependent) hazards and, if necessary, execute appropriate control interventions via supervised or automated decision making. Accommodating this complex environment may require automated functions (autonomy) that apply artificial intelligence (AI) techniques that can adapt and respond to a quickly changing environment. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments where the objective can be constructed as a sequential decision-making problem. An extension of a prior formulation of the contingency management problem as a Markov Decision Process (MDP) is presented and uses a DRL framework to train agents that mitigate hazards present in the simulation environment. A comparison of these learning-based agents and classical techniques is presented in terms of their performance, verification difficulties, and development process.