This paper outlines a multi-dimensional user-oriented performance metrics approach in evaluating the operation of the terminal airspace system to aid in the airport and airspace planning and decision making. Safety, d...This paper outlines a multi-dimensional user-oriented performance metrics approach in evaluating the operation of the terminal airspace system to aid in the airport and airspace planning and decision making. Safety, delay and predictability metrics contribute to the analytical framework. From the findings, the occurrence of air incidence has a high severity level at departure, and arrival phases of flight, higher likelihood at the radar room and much of the incidences were as a result of faulty equipment and inherent absence of modern airspace infrastructure. Also, in Lagos terminal airspace, the number of incidences has no close correlation with the level of traffic complexity. Total schedule arrival delay ranges from 1 - 392 minutes representing an average of 7.8 - 17.9 minutes per aircraft that arrived Lagos airport at that period. Be</span><span style="font-family:Verdana;">sides, the total approach contact time ranges from 1 - 57 minutes, translating to 4.6 - 7.1 minutes per aircraft. However, variability in arrival time of 1 - 5 minutes is common from published airline arrival scheduled time. In the same vein, the variability of 1 - 5 minutes is common from approach contact times of aircraft. These figures indicate sound arrival predictability signature for Lagos airport. Also, departure time variability above 30 mi</span><span style="font-family:Verdana;">nutes is familiar from the ATC clearance time for the various routes under study. However, there is about or more 25% variability of more than 15</span> <span style="font-family:Verdana;">minutes, and this indicates possible inconsistency of predicting departure times from the times Air Traffic Control</span><b> </b><span style="font-family:Verdana;">(ATC) clearance was acquired. Above all, the predictability of departure times in Lagos airport is weak compared to those of the arrival. Taken by it, this may be a sign of airspace congestion or ATC deficiencies at the Lagos airport. This is an indication of the lack of users’ confidence in Nigeria’s air transport industry to deliver just-in-time service.展开更多
空中交通管制员在指挥飞机时存在频繁嘴部开合活动。为从管制员的嘴部陆空通话行为中准确区分哈欠行为,降低管制员疲劳工作产生的安全风险,提出了一种基于视频的结合卷积神经网络(Convolutional Neural Network,CNN)与长短期记忆网络(Lo...空中交通管制员在指挥飞机时存在频繁嘴部开合活动。为从管制员的嘴部陆空通话行为中准确区分哈欠行为,降低管制员疲劳工作产生的安全风险,提出了一种基于视频的结合卷积神经网络(Convolutional Neural Network,CNN)与长短期记忆网络(Long and Short Term Memory Networks,LSTM)的管制员嘴部行为识别方法。首先,搭建面部定位模型提取人脸68特征点,建立嘴部几何区域提取模型划分嘴部区域;其次,建立管制员哈欠检测模型分别提取嘴部视频序列帧的空间特征与时间特征;最后,采集数据集管制员嘴部活动数据集(Civil Aviation University of China-Controller,CAUC CON)用于模型训练,通过哈欠分类模型得出序列帧内管制员嘴部哈欠识别结果。结果表明:基于视频的加入时间信息的哈欠检测方法更适合管制员的工作条件,较传统哈欠识别方法的平均识别准确率最高提升了14.4%。展开更多
Advanced Air Mobility(AAM)has emerged as a pioneering concept designed to optimize the efficacy and ecological sustainability of air transportation.Its core objective is to provide highly automated air transportation ...Advanced Air Mobility(AAM)has emerged as a pioneering concept designed to optimize the efficacy and ecological sustainability of air transportation.Its core objective is to provide highly automated air transportation services for passengers or cargo,operating at low altitudes within urban,suburban,and rural regions.AAM seeks to enhance the efficiency and environmental viability of the aviation sector by revolutionizing the way air travel is conducted.In a complex aviation environment,traffic management and control are essential technologies for safe and effective AAM operations.One of the most difficult obstacles in the envisioned AAM systems is vehicle coordination at merging points and intersections.The escalating demand for air mobility services,particularly within urban areas,poses significant complexities to the execution of such missions.In this study,we propose a novel multi-agent reinforcement learning(MARL)approach to efficiently manage high-density AAM operations in structured airspace.Our approach provides effective guidance to AAM vehicles,ensuring conflict avoidance,mitigating traffic congestion,reducing travel time,and maintaining safe separation.Specifically,intelligent learning-based algorithms are developed to provide speed guidance for each AAM vehicle,ensuring secure merging into air corridors and safe passage through intersections.To validate the effectiveness of our proposed model,we conduct training and evaluation using BlueSky,an open-source air traffic control simulation environment.Through 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 operations.The simulation results validate the efficacy of our approach and its ability to achieve the desired outcomes.展开更多
文摘This paper outlines a multi-dimensional user-oriented performance metrics approach in evaluating the operation of the terminal airspace system to aid in the airport and airspace planning and decision making. Safety, delay and predictability metrics contribute to the analytical framework. From the findings, the occurrence of air incidence has a high severity level at departure, and arrival phases of flight, higher likelihood at the radar room and much of the incidences were as a result of faulty equipment and inherent absence of modern airspace infrastructure. Also, in Lagos terminal airspace, the number of incidences has no close correlation with the level of traffic complexity. Total schedule arrival delay ranges from 1 - 392 minutes representing an average of 7.8 - 17.9 minutes per aircraft that arrived Lagos airport at that period. Be</span><span style="font-family:Verdana;">sides, the total approach contact time ranges from 1 - 57 minutes, translating to 4.6 - 7.1 minutes per aircraft. However, variability in arrival time of 1 - 5 minutes is common from published airline arrival scheduled time. In the same vein, the variability of 1 - 5 minutes is common from approach contact times of aircraft. These figures indicate sound arrival predictability signature for Lagos airport. Also, departure time variability above 30 mi</span><span style="font-family:Verdana;">nutes is familiar from the ATC clearance time for the various routes under study. However, there is about or more 25% variability of more than 15</span> <span style="font-family:Verdana;">minutes, and this indicates possible inconsistency of predicting departure times from the times Air Traffic Control</span><b> </b><span style="font-family:Verdana;">(ATC) clearance was acquired. Above all, the predictability of departure times in Lagos airport is weak compared to those of the arrival. Taken by it, this may be a sign of airspace congestion or ATC deficiencies at the Lagos airport. This is an indication of the lack of users’ confidence in Nigeria’s air transport industry to deliver just-in-time service.
文摘空中交通管制员在指挥飞机时存在频繁嘴部开合活动。为从管制员的嘴部陆空通话行为中准确区分哈欠行为,降低管制员疲劳工作产生的安全风险,提出了一种基于视频的结合卷积神经网络(Convolutional Neural Network,CNN)与长短期记忆网络(Long and Short Term Memory Networks,LSTM)的管制员嘴部行为识别方法。首先,搭建面部定位模型提取人脸68特征点,建立嘴部几何区域提取模型划分嘴部区域;其次,建立管制员哈欠检测模型分别提取嘴部视频序列帧的空间特征与时间特征;最后,采集数据集管制员嘴部活动数据集(Civil Aviation University of China-Controller,CAUC CON)用于模型训练,通过哈欠分类模型得出序列帧内管制员嘴部哈欠识别结果。结果表明:基于视频的加入时间信息的哈欠检测方法更适合管制员的工作条件,较传统哈欠识别方法的平均识别准确率最高提升了14.4%。
基金This work was funded in part by the National Science Foundation(NSF)CAREER Award CMMI-2237215.
文摘Advanced Air Mobility(AAM)has emerged as a pioneering concept designed to optimize the efficacy and ecological sustainability of air transportation.Its core objective is to provide highly automated air transportation services for passengers or cargo,operating at low altitudes within urban,suburban,and rural regions.AAM seeks to enhance the efficiency and environmental viability of the aviation sector by revolutionizing the way air travel is conducted.In a complex aviation environment,traffic management and control are essential technologies for safe and effective AAM operations.One of the most difficult obstacles in the envisioned AAM systems is vehicle coordination at merging points and intersections.The escalating demand for air mobility services,particularly within urban areas,poses significant complexities to the execution of such missions.In this study,we propose a novel multi-agent reinforcement learning(MARL)approach to efficiently manage high-density AAM operations in structured airspace.Our approach provides effective guidance to AAM vehicles,ensuring conflict avoidance,mitigating traffic congestion,reducing travel time,and maintaining safe separation.Specifically,intelligent learning-based algorithms are developed to provide speed guidance for each AAM vehicle,ensuring secure merging into air corridors and safe passage through intersections.To validate the effectiveness of our proposed model,we conduct training and evaluation using BlueSky,an open-source air traffic control simulation environment.Through 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 operations.The simulation results validate the efficacy of our approach and its ability to achieve the desired outcomes.
