Distributed Computational Guidance for High-Density Urban Air Mobility with Cooperative and Non-Cooperative Collision Avoidance

Urban Air Mobility (UAM) will result in numerous aircraft which will need to respond to a dynamically changing airspace to safely reach their destinations. We use a highly efficient Markov Decision Process (MDP) based trajectory planner to demonstrate multi-agent distributed trajectory planning that can safely avoid cooperative and non-cooperative actors in the high-density free flight airspace. We demonstrate the algorithm in an urban setting where multiple aircraft all navigate to their designated landing site while avoiding cooperative and non-cooperative aircraft. We study the algorithm performance as the aircraft density increases to demonstrate scalability and the effect of cooperative versus non-cooperative actors in the environment.