A reinforcement learning approach to vehicle coordination for structured advanced air mobility

作     者：Sabrullah Deniz Yufei Wu Yang Shi Zhenbo Wang 

作者机构：Department of MechanicalAerospaceand Biomedical EngineeringThe University of TennesseeKnoxvilleTN37996USA 

出 版 物：《Green Energy and Intelligent Transportation》 (新能源与智能载运（英文）)

年 卷 期：2024年第3卷第2期

页      面：20-37页

核心收录：

学科分类：08[工学] 0825[工学-航空宇航科学与技术] 

基　　金：This work was funded in part by the National Science Foundation(NSF)CAREER Award CMMI-2237215 

主　　题：Advanced Air Mobility(AAM) Urban Air Mobility(UAM) Air Traffic Control(ATC) Multi-Agent Reinforcement Learning(MARL) 

摘      要：Advanced Air Mobility(AAM)has emerged as a pioneering concept designed to optimize the efficacy and ecological sustainability of air *** core objective is to provide highly automated air transportation services for passengers or cargo,operating at low altitudes within urban,suburban,and rural *** seeks to enhance the efficiency and environmental viability of the aviation sector by revolutionizing the way air travel is *** a complex aviation environment,traffic management and control are essential technologies for safe and effective AAM *** of the most difficult obstacles in the envisioned AAM systems is vehicle coordination at merging points and *** escalating demand for air mobility services,particularly within urban areas,poses significant complexities to the execution of such *** this study,we propose a novel multi-agent reinforcement learning(MARL)approach to efficiently manage high-density AAM operations in structured *** approach provides effective guidance to AAM vehicles,ensuring conflict avoidance,mitigating traffic congestion,reducing travel time,and maintaining safe ***,intelligent learning-based algorithms are developed to provide speed guidance for each AAM vehicle,ensuring secure merging into air corridors and safe passage through *** validate the effectiveness of our proposed model,we conduct training and evaluation using BlueSky,an open-source air traffic control simulation *** the simulation of thousands of aircraft and the integration of real-world data,our study demonstrates the promising potential of MARL in enabling safe and efficient AAM *** simulation results validate the efficacy of our approach and its ability to achieve the desired outcomes.