To follow the development trend of unmanned platform, diversified users and personalized services in the future aviation field, hierarchical governance is being adopted in airspace operation. With the continuous improvement and accumulation of computing power, algorithms and data, the data driven artificial intelligence method will continue to empower hierarchical airspace system. Firstly, this paper combs the development trend of China's airspace system in terms of five hierarchical scenarios: ultra-low altitude transportation, urban transportation, regional transportation, hub transportation and suborbital transportation. The core difficulties and key issues of airspace operation are summarized. Secondly, the research framework, research contents and key technologies of data-driven artificial intelligence method to solve the scientific problems of airspace operation are proposed. Specific cases of application of artificial intelligence for hierarchical scenarios of airspace are briefly analyzed. Finally, new thoughts on the role of human in airspace operation are presented.
CHEN Zhijie
,
TANG Jinhui
,
WANG Chong
,
CHENG Jizeng
,
CAO Shan
,
SHAO Xin
. Using artificial intelligence in airspace system to improve airspace hierarchical governance capability[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021
, 42(4)
: 525018
-525018
.
DOI: 10.7527/S1000-6893.2020.25018
[1] SAMET A, PABLO C, HANAN S. Predicting estimated time of arrival for commercial flights[C]//Proceedings of the 24th ACM SIGKDD international Conference on Knowledge Discovery & Data Mining. London:ACM, 2018:19-23.
[2] 林友芳,康友隐,万怀宇,等.基于深度时空卷积网络的民航需求预测[J].北京交通大学学报,2018,42(2):1-8. LIN Y F,KANG Y Y,WAN H Y, et a1. Deep sptio-temporal convolutional networks for flight requirements prediction[J]. Journal of Beijing Jiaotong University,2018, 42(2):1-8(in Chinese).
[3] MUKHERJEE A, HANSEN M.A. Dynamic rerouting model for air traffic flow management[J]. Transportation Research Part B(Methodological), 2009,43(1):159-171.
[4] 杜文博.面向航空交通系统的复杂网络与网络动力学研究[D].合肥:中国科学技术大学,2010. DU W B. Research on complex network and network dynamics for air transportation systems[D]. Hefei:University of Science and Technology of China, 2010(in Chinese).
[5] 袁立罡.终端区动态交通特征与运行态势研究[D].南京:南京航空航天大学,2016. YUAN L G. Research on dynamic traffic characteristics and operation situation of terminal area[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2016(in Chinese).
[6] MAYARA C R M, HANSMAN R J, LI L S, et al. 2018. Flight trajectory data analytics for characterization of air traffic flows:A comparative analysis of terminal area operations between New York, Hong Kong and Sao Paulo[J]. Transportation Research Part C:Emerging Technologies,2018,97:324-347.
[7] 叶博嘉.基于多Agent的空中交通协同流量管理研究[D].南京:南京航空航天大学,2013. YE J B. Research on collaborative air traffic flow management based upon multi-agent modeling and simulation[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2013(in Chinese).
[8] JARVIS P A,WOLFE S R, MAARTEN S, et al. Agent-based modeling and simulation of collaborative air traffic flow management using brahms[J]. SAE International Journal of Aerospace, 2010, 3(1):39-45.
[9] XU X H, YAO Y. Application of genetic algorithm to aircraft sequencing in terminal area[J]. Journal of Traffic and Transportation Engineering, 2004,4(3):121-126.
[10] ROBOLLO J, BRINTON C. BROWNIAN. Motion delay model for the integration of multiple traffic management initiatives[C]//Proceedings of the 11th USA/Europe Air Traffic Management Research and Development Seminar. Lisbon:Eurocontrol,2015:5-15.
[11] CRUCIOL L L B V, LI W G. Air holding problem solving by reinforcement learning to reduce the congestion in airspace sectors[C]//Proceedings of the 2012 International Conference on Artificial Intelligence. Toronto:AAAI, 2012:272-278.
[12] 李国杰. 大数据研究的科学价值[J]. 计算机学会通讯, 2012, 8(9):8-15. LI G J. Scientific value of big data research[J]. Communications of the CCF, 2012, 8(9):8-15(in Chinese).
[13] 李诚龙,屈文秋,李彦冬,等.面向eVTOL航空器的城市空中运输交通管理综述[J].交通运输工程学报,2020,20(4):35-54. LI C L, QU W Q, LI D Y, et a1. Overview of traffic management of urban air mobility (UAM) with eVOTL aircraft[J]. Journal of traffic and transportation engineering, 2020,20(4):35-54(in Chinese).
[14] ZHANG J, ZHENG Y, QI D, et al. Predicting citywide crowd flows using deep spatio-temporal residual networks[J]. Artificial Intelligence, 2018, 259:147-166.
[15] 张洪海,廖志华,张启钱,等.终端区空域结构调整对进场交通流的影响[J].交通运输工程学报,2016,16(2):100-108. ZHANG H H, LIAO Z H, ZHANG Q Q, et al. Impact of adjusting airspace structure on arrival traffic flow in terminal area[J].Journal of Traffic and Transportation Engineering,2016,16(2):100-108(in Chinese).
[16] 韦伟. 基于实测数据的道路交通状态特征及拥堵传播规律分析方法[D]. 北京:北京交通大学, 2017. WEI W. Analytical method of traffic condition characteristics and congestion propagation rules based on practical measured data[D]. Beijing:Beijing Jiaotong University, 2017(in Chinese).
[17] 全权, 李刚, 柏艺琴, 等.低空无人机交通管理概览与建议[J].航空学报, 2020, 41(1):023238. QUAN Q, LI G, BAI Y Q, et a1. Low altitude UAV traffic management:An introductory overview and proposal[J]. Acta Aeronautica et Astronautica Sinica,2020, 41(1):023238(in Chinese).
[18] 汤锦辉,王冲,程晓航, 等.基于多智能体的空中交通管理智能技术[J].指挥信息系统与技术,2016,7(6):17-23. TANG J H, WANG C, CHENG X H, et a1. Intelligent technology for air traffic management based on multi-agent systems[J]. Command Information System and Technology, 2016, 7(6):17-23(in Chinese).
[19] BRITTAIN M, WEI P. Autonomous air traffic controller:A deep multi-agent reinforcement learning approach[DB/OL]. arXiv preprint arXiv:1905.01303, 2019.
[20] 孙长银, 穆朝絮.多智能体深度强化学习的若干关键科学问题[J].自动化学报, 2020, 46(7):1301-1312. SUN C Y, MU C X. Important scientific problems of multi-agent deep reinforcement learning[J]. Acta Automatica Sinica, 2020, 46(7):1301-1312(in Chinese).
[21] 杜威,丁世飞.多智能体强化学习综述[J].计算机科学,2019,46(8):1-8. DU W, DING S F. Overview on multi-agent reinforcement learning[J]. Computer Science, 2019, 46(8):1-8(in Chinese).
CJA