Autonomous Separation Assurance with Deep Multi-Agent Reinforcement Learning
- 1 December 2021
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 18 (12), 890-905
- https://doi.org/10.2514/1.i010973
Abstract
A novel deep multi-agent reinforcement learning framework is proposed to identify and resolve conflicts among a variable number of aircraft in a high-density, stochastic, and dynamic en route sector. The concept of using distributed vehicle autonomy to ensure separation is proposed, instead of a centralized sector air traffic controller. Our proposed framework uses proximal policy optimization that is customized to incorporate an attention network. This allows the agents to have access to variable aircraft information in the sector in a scalable, efficient approach to achieve high traffic throughput under uncertainty. Agents are trained using a centralized learning, decentralized execution scheme where one neural network is learned and shared by all agents. The proposed framework is validated on three case studies in the BlueSky air traffic simulator. Several baselines are introduced, and the numerical results show that the proposed framework significantly reduces offline training time, increases safe separation performance, and results in a more efficient policy.Keywords
Funding Information
- National Science Foundation (1718420)
- Iowa Space Grant Consortium (NNX16AL88H)
This publication has 23 references indexed in Scilit:
- Decomposition Methods for Optimized Collision Avoidance with Multiple ThreatsJournal of Guidance, Control, and Dynamics, 2012
- Hazard Alerting Based on Probabilistic ModelsJournal of Guidance, Control, and Dynamics, 2012
- Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problemsThe Knowledge Engineering Review, 2012
- Accounting for State Uncertainty in Collision AvoidanceJournal of Guidance, Control, and Dynamics, 2011
- Particle Swarm Optimization Applied to Space TrajectoriesJournal of Guidance, Control, and Dynamics, 2010
- Dynamic Optimization Strategies for Three-Dimensional Conflict Resolution of Multiple AircraftJournal of Guidance, Control, and Dynamics, 2004
- Resolution of Conflicts Involving Many Aircraft via Semidefinite ProgrammingJournal of Guidance, Control, and Dynamics, 2001
- Optimal Strategies for Free-Flight Air Traffic Conflict ResolutionJournal of Guidance, Control, and Dynamics, 1999
- Long Short-Term MemoryNeural Computation, 1997
- Discrete approximations to optimal trajectories using direct transcription and nonlinear programmingJournal of Guidance, Control, and Dynamics, 1992