Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222974
Hossam O. Ahmed
The importance of the Unmanned Aircraft Systems (UAS) has been increased significantly nowadays due to the increasing demands on affording novel urban transportation system solutions that could leverage the transportation utilization ratio specially in congested urban cities. However, the viability of deploying Urban Air Mobility (UAM) solutions in our daily life depends on many critical safety factors. One of the most pivotal key players in the UAM safety aspect is their capability for accurately landing on narrow and unplanned urban lading spots. Subsequently, processing the elevation sensory data by depending on a single array-based sensor unit has many drawbacks in case of sudden electronically failure or spontaneous obstacle shadowing effects. In this paper, we proposed a multicore systolic real-time processing unit that is capable to increase the automation requirement levels for future UAMs through adopting parallel and complex sensory fusion computer architectures for increasing the accuracy of UAM during the landing process. The novel Fuzzy Logic System (FLS) processing unit is interactively dealing with Multiple Sensor Nodes (MSN) that are both frequency spectrum and spatially separated on the bottom side of an UAM. The proposed idea is surpassing the conventional single sensor-array based-solutions for UAM landing process in terms of improving the accuracy and safety concerns. The proposed systolic FLS architecture in this paper has been designed and tested using MATLAB and VHDL to be interfaced with five Lidar Sensors and five ultrasonic sensors using the Intel Altera OpenVINO FPGA board. The proposed systolic FLS processing unit achieved a processing computational speed of about 25.3 Giga Operations per Seconds (GOPS) and only 178.12 mW as core dynamic thermal power dissipation.
由于对提供新颖的城市交通系统解决方案的需求不断增加，特别是在拥挤的城市中，可以利用交通利用率，无人机系统(UAS)的重要性已经显著增加。然而，在我们的日常生活中部署城市空中交通(UAM)解决方案的可行性取决于许多关键的安全因素。UAM安全方面最关键的关键因素之一是它们在狭窄和计划外的城市提货点上准确着陆的能力。因此，在突发电子故障或自发障碍物阴影效应的情况下，依靠单个阵列传感器单元处理高程传感器数据存在许多缺点。在本文中，我们提出了一种多核收缩实时处理单元，该单元能够通过采用并行和复杂的感觉融合计算机架构来提高未来UAM的自动化要求水平，以提高UAM在着陆过程中的精度。新型模糊逻辑系统(FLS)处理单元交互式地处理位于UAM底部的多个传感器节点(MSN)，这些节点在频谱和空间上都是分离的。在提高精度和安全性方面，所提出的想法超越了传统的基于单传感器阵列的UAM着陆过程解决方案。利用MATLAB和VHDL对本文提出的收缩FLS架构进行了设计和测试，并利用Intel Altera OpenVINO FPGA板与五个激光雷达传感器和五个超声波传感器进行了接口。所提出的收缩FLS处理单元的处理计算速度约为25.3 Giga Operations per Seconds (GOPS)，核心动态热功耗仅为178.12 mW。
{"title":"25.3 GOPS Autonomous Landing Guidance Assistant System Using Systolic Fuzzy Logic System for Urban Air Mobility (UAM) Vehicles Using FPGA","authors":"Hossam O. Ahmed","doi":"10.1109/ICNS50378.2020.9222974","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222974","url":null,"abstract":"The importance of the Unmanned Aircraft Systems (UAS) has been increased significantly nowadays due to the increasing demands on affording novel urban transportation system solutions that could leverage the transportation utilization ratio specially in congested urban cities. However, the viability of deploying Urban Air Mobility (UAM) solutions in our daily life depends on many critical safety factors. One of the most pivotal key players in the UAM safety aspect is their capability for accurately landing on narrow and unplanned urban lading spots. Subsequently, processing the elevation sensory data by depending on a single array-based sensor unit has many drawbacks in case of sudden electronically failure or spontaneous obstacle shadowing effects. In this paper, we proposed a multicore systolic real-time processing unit that is capable to increase the automation requirement levels for future UAMs through adopting parallel and complex sensory fusion computer architectures for increasing the accuracy of UAM during the landing process. The novel Fuzzy Logic System (FLS) processing unit is interactively dealing with Multiple Sensor Nodes (MSN) that are both frequency spectrum and spatially separated on the bottom side of an UAM. The proposed idea is surpassing the conventional single sensor-array based-solutions for UAM landing process in terms of improving the accuracy and safety concerns. The proposed systolic FLS architecture in this paper has been designed and tested using MATLAB and VHDL to be interfaced with five Lidar Sensors and five ultrasonic sensors using the Intel Altera OpenVINO FPGA board. The proposed systolic FLS processing unit achieved a processing computational speed of about 25.3 Giga Operations per Seconds (GOPS) and only 178.12 mW as core dynamic thermal power dissipation.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122242541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222980
Amanda Matthews, Marcus Smith, A. Staley, S. Stalnaker
When National Airspace System (NAS) flight demand (e.g., Flight Operator operations) exceeds capacity (e.g., airport-, weather-, airspace-related) at a NAS resource the result is delay. To ensure an efficient NAS, the Federal Aviation Administration (FAA) uses various Time-Based Management (TBM) capabilities to balance capacity and demand across NAS resources. These capabilities assign the resulting delay across the resource flight demand. For example, the FAA uses the Time-Based Flow Management (TBFM) system to manage the balance between demand and capacity at arrival airports and departure fixes/flows by assigning delays across airborne and ground-based flights. TBFM is not creating delay, rather assigning delay that exists within the NAS to balance traffic demand with available capacity. TBFM uses controlled departure times to assign this delay on an as-requested approach. There is a desire among flight operators to provide priority inputs that can be accounted for by TBFM in order to minimize delay assigned to those flights that are most important to them in meeting their business objectives. Fleet Prioritization concepts, which intend to address this desire to better accommodate flight operator preferences as part of TBM, is considered consistent with achieving increased Operational Flexibility, one of four stated objectives in the FAA’s Vision for Trajectory-Based Operations (TBO).The MITRE Corporation in collaboration with the Federal Aviation Administration (FAA) is analyzing and exploring how a TBM Fleet Prioritization Service can be incorporated as part of future TBFM system capabilities. The Flight Operators’ needs for Fleet Prioritization and a concept for this was investigated, including concept elements that would be needed. Process-, procedural-, and automation-based methods were identified to achieve Fleet Prioritization goals. The scope of shortfalls related to TBFM and broader TBM operations were explored and data analysis performed to determine to what extent operational and/or business considerations necessitate the prioritization of flights to reallocate assigned delay in TBM operations. TBM assigned departure delays can vary widely for a flight; however, current operational TBM practices provide only a limited planning horizon for potential prioritization activities. The prioritization of flights requires sufficient planning time to ensure that the flight operators can meet business needs. Further data analysis highlighted that the advantages of applying increased scheduling lead-time as a means to minimize delay are location-dependent and not consistent NAS-wide. Therefore, any envisioned Fleet Prioritization service will require location-specific considerations. This paper will describe how the FAA should make both near-term and longer-term improvements to exchange data with flight operators, mature the concept, and utilize existing capabilities to improve flight operator preference accommodation.
{"title":"Exploring A Time-Based Management Fleet Prioritization Service","authors":"Amanda Matthews, Marcus Smith, A. Staley, S. Stalnaker","doi":"10.1109/ICNS50378.2020.9222980","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222980","url":null,"abstract":"When National Airspace System (NAS) flight demand (e.g., Flight Operator operations) exceeds capacity (e.g., airport-, weather-, airspace-related) at a NAS resource the result is delay. To ensure an efficient NAS, the Federal Aviation Administration (FAA) uses various Time-Based Management (TBM) capabilities to balance capacity and demand across NAS resources. These capabilities assign the resulting delay across the resource flight demand. For example, the FAA uses the Time-Based Flow Management (TBFM) system to manage the balance between demand and capacity at arrival airports and departure fixes/flows by assigning delays across airborne and ground-based flights. TBFM is not creating delay, rather assigning delay that exists within the NAS to balance traffic demand with available capacity. TBFM uses controlled departure times to assign this delay on an as-requested approach. There is a desire among flight operators to provide priority inputs that can be accounted for by TBFM in order to minimize delay assigned to those flights that are most important to them in meeting their business objectives. Fleet Prioritization concepts, which intend to address this desire to better accommodate flight operator preferences as part of TBM, is considered consistent with achieving increased Operational Flexibility, one of four stated objectives in the FAA’s Vision for Trajectory-Based Operations (TBO).The MITRE Corporation in collaboration with the Federal Aviation Administration (FAA) is analyzing and exploring how a TBM Fleet Prioritization Service can be incorporated as part of future TBFM system capabilities. The Flight Operators’ needs for Fleet Prioritization and a concept for this was investigated, including concept elements that would be needed. Process-, procedural-, and automation-based methods were identified to achieve Fleet Prioritization goals. The scope of shortfalls related to TBFM and broader TBM operations were explored and data analysis performed to determine to what extent operational and/or business considerations necessitate the prioritization of flights to reallocate assigned delay in TBM operations. TBM assigned departure delays can vary widely for a flight; however, current operational TBM practices provide only a limited planning horizon for potential prioritization activities. The prioritization of flights requires sufficient planning time to ensure that the flight operators can meet business needs. Further data analysis highlighted that the advantages of applying increased scheduling lead-time as a means to minimize delay are location-dependent and not consistent NAS-wide. Therefore, any envisioned Fleet Prioritization service will require location-specific considerations. This paper will describe how the FAA should make both near-term and longer-term improvements to exchange data with flight operators, mature the concept, and utilize existing capabilities to improve flight operator preference accommodation.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131548449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222874
Lechen Wang, Xuechun Li, Jianfeng Mao
Traffic states prediction in air transportation systems is a challenging problem and has not been fully explored because it is subject to many more highly correlated factors and a more complicated traffic management scheme compared to urban transportation systems. It becomes a more formidable task when facing a multi-airport system (MAS), in which several major airports are closely located and tightly coupled with each other through limited terminal airspace. In this work, we propose a novel method using a time series model and recurrent neural network to make the estimated time of arrival (ETA) for a flight to an MAS, which can be potentially utilized for flight delay prediction and congestion analysis. The experiment utilizes two months of 4D trajectories data from Beijing Capital International Airport (PEK) to Shenzhen Bao’an International airport (ZGSZ). The entire prediction work is decomposed into two sub-problems, en-route travel time prediction which is from flight origin to the entering gate of MAS, defined as the location is 300km from the airport in MAS, and terminal maneuvering area (TMA) travel time prediction which is from the entrance to flight’s destination. The auto-regressive integrated moving average (ARIMA), a time series prediction model, is used to predict travel time in en-route under given the flight departure time. Bidirectional long short term memory (LSTM), a recurrent neural network, is developed to forecast travel time in the arrival approach by utilizing spatio-temporal features. To design the input features, we use density-based spatial clustering (DBSCAN) with the help of the Voronoi diagram to extract spatial information from every historical flight trajectory of aircraft operated in an MAS, then select the observation time window to capture the temporal information for each flight. The Multivariate Stacked Fully connected-Bidirectional LSTM (MSFCB-LSTM) model is constructed to make shortterm forecasting using spatio-temporal features we designed when the flight’s entering MAS time is given. For TMA travel time prediction, a case study of Guangdong-Hong Kong-Macao Greater Bay Area (GHM-GBA), a typical MAS which contains five major airports closely located within 120km, is carried out using actual historical 4D trajectory data. Finally, Using two months 4D trajectories data, PEK to ZGSZ, the result exhibits the best accuracy, a measurement we define for prediction, of the longterm prediction of ETA given departure time is 92%, and mean absolute error (MAE) is 6.09 minutes.
{"title":"Integrating ARIMA and Bidirectional LSTM to Predict ETA in Multi-Airport Systems","authors":"Lechen Wang, Xuechun Li, Jianfeng Mao","doi":"10.1109/ICNS50378.2020.9222874","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222874","url":null,"abstract":"Traffic states prediction in air transportation systems is a challenging problem and has not been fully explored because it is subject to many more highly correlated factors and a more complicated traffic management scheme compared to urban transportation systems. It becomes a more formidable task when facing a multi-airport system (MAS), in which several major airports are closely located and tightly coupled with each other through limited terminal airspace. In this work, we propose a novel method using a time series model and recurrent neural network to make the estimated time of arrival (ETA) for a flight to an MAS, which can be potentially utilized for flight delay prediction and congestion analysis. The experiment utilizes two months of 4D trajectories data from Beijing Capital International Airport (PEK) to Shenzhen Bao’an International airport (ZGSZ). The entire prediction work is decomposed into two sub-problems, en-route travel time prediction which is from flight origin to the entering gate of MAS, defined as the location is 300km from the airport in MAS, and terminal maneuvering area (TMA) travel time prediction which is from the entrance to flight’s destination. The auto-regressive integrated moving average (ARIMA), a time series prediction model, is used to predict travel time in en-route under given the flight departure time. Bidirectional long short term memory (LSTM), a recurrent neural network, is developed to forecast travel time in the arrival approach by utilizing spatio-temporal features. To design the input features, we use density-based spatial clustering (DBSCAN) with the help of the Voronoi diagram to extract spatial information from every historical flight trajectory of aircraft operated in an MAS, then select the observation time window to capture the temporal information for each flight. The Multivariate Stacked Fully connected-Bidirectional LSTM (MSFCB-LSTM) model is constructed to make shortterm forecasting using spatio-temporal features we designed when the flight’s entering MAS time is given. For TMA travel time prediction, a case study of Guangdong-Hong Kong-Macao Greater Bay Area (GHM-GBA), a typical MAS which contains five major airports closely located within 120km, is carried out using actual historical 4D trajectory data. Finally, Using two months 4D trajectories data, PEK to ZGSZ, the result exhibits the best accuracy, a measurement we define for prediction, of the longterm prediction of ETA given departure time is 92%, and mean absolute error (MAE) is 6.09 minutes.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131560519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222889
Z. Chaudhry, K. Fox
Air Traffic Management (ATM) is under great pressure and facing major challenges in the coming years. The industry is driven by safety, capacity, cost of service, efficiency and the environment. "Continuous traffic growth, structural airspace and airport capacity issues, and extreme weather events call for new approaches to reshape today’s operations and business models" [1]. If the aviation industry is to handle the levels of traffic predicted, as well as to cope with new flight modalities on the horizon, including Unmanned Aerial Systems (UAS) and space, "It will be essential to take a step forward in the capabilities of our systems to cope with the flood of data and to make intelligent decisions" [2].
{"title":"Artificial Intelligence Applicability to Air Traffic Management Network Operations","authors":"Z. Chaudhry, K. Fox","doi":"10.1109/ICNS50378.2020.9222889","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222889","url":null,"abstract":"Air Traffic Management (ATM) is under great pressure and facing major challenges in the coming years. The industry is driven by safety, capacity, cost of service, efficiency and the environment. \"Continuous traffic growth, structural airspace and airport capacity issues, and extreme weather events call for new approaches to reshape today’s operations and business models\" [1]. If the aviation industry is to handle the levels of traffic predicted, as well as to cope with new flight modalities on the horizon, including Unmanned Aerial Systems (UAS) and space, \"It will be essential to take a step forward in the capabilities of our systems to cope with the flood of data and to make intelligent decisions\" [2].","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127021426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222890
Jonathan West, L. Sherry
Researchers have proposed a portfolio of autonomous transportation systems for metropolitan areas including Urban Air Mobility (UAM) systems. Urban Air Mobility systems consist of low occupant battery operated helicopters, similar to drones. In a future state, when Urban Air Mobility is a ubiquitous transportation option, urban planners will need to understand the potential role of the Urban Air Mobility system for an efficient evacuation of a metropolitan area. An agent-based model is used to assess the evacuation efficiency as throughput and time to complete. The agent-based model includes autonomous Urban Air Mobility systems operating in an urban environment on routes defined by existing city streets and originating at a central location that may be on the ground or on the top of a building. In the event of an evacuation, the routing of each Urban Air Mobility unit is determined by a central air traffic flow management system to maximize the evacuation throughput. Standard deviation of time-to-complete is computing to understand where the model shows convergence. The implications of the results and limitations of the model are discussed.
{"title":"Agent-Based Simulation of Metropolitan Area Evacuation by Unmanned Air Mobility","authors":"Jonathan West, L. Sherry","doi":"10.1109/ICNS50378.2020.9222890","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222890","url":null,"abstract":"Researchers have proposed a portfolio of autonomous transportation systems for metropolitan areas including Urban Air Mobility (UAM) systems. Urban Air Mobility systems consist of low occupant battery operated helicopters, similar to drones. In a future state, when Urban Air Mobility is a ubiquitous transportation option, urban planners will need to understand the potential role of the Urban Air Mobility system for an efficient evacuation of a metropolitan area. An agent-based model is used to assess the evacuation efficiency as throughput and time to complete. The agent-based model includes autonomous Urban Air Mobility systems operating in an urban environment on routes defined by existing city streets and originating at a central location that may be on the ground or on the top of a building. In the event of an evacuation, the routing of each Urban Air Mobility unit is determined by a central air traffic flow management system to maximize the evacuation throughput. Standard deviation of time-to-complete is computing to understand where the model shows convergence. The implications of the results and limitations of the model are discussed.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134114859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222923
C. Brinton, Alicia Borgman Fernandes, Curt Kaler
As the National Airspace System (NAS) evolves into a more automated system, it will be essential that human operators can effectively team with their automated Decision Support Systems (DSSs) to manage the performance of the system. When automated systems recommend courses of action, the human operator must understand the operational recommendations with sufficient depth and clarity to evaluate their appropriateness and monitor the performance of the system. Significant shortcomings exist in the current state-of-the-art in Air Traffic Management (ATM) DSSs that cause human specialists to distrust the automation’s recommendations and information provided by the system.The focus of the research effort described herein is to identify methods, algorithms, and an overall framework in which ATM DSSs can reason about the appropriate contingency plans to consider in different operational scenarios and communicate the contingency plan to the human specialists to fulfill their information needs. This effort also studied approaches to automatically predict the effectiveness of contingency plans, so that the ATM DSS can determine when a given contingency is no longer the best option and a new ‘plan B’ should be considered.
{"title":"Explicit Contingency Planning For Improved Human-Autonomy Teaming In Decision Support","authors":"C. Brinton, Alicia Borgman Fernandes, Curt Kaler","doi":"10.1109/ICNS50378.2020.9222923","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222923","url":null,"abstract":"As the National Airspace System (NAS) evolves into a more automated system, it will be essential that human operators can effectively team with their automated Decision Support Systems (DSSs) to manage the performance of the system. When automated systems recommend courses of action, the human operator must understand the operational recommendations with sufficient depth and clarity to evaluate their appropriateness and monitor the performance of the system. Significant shortcomings exist in the current state-of-the-art in Air Traffic Management (ATM) DSSs that cause human specialists to distrust the automation’s recommendations and information provided by the system.The focus of the research effort described herein is to identify methods, algorithms, and an overall framework in which ATM DSSs can reason about the appropriate contingency plans to consider in different operational scenarios and communicate the contingency plan to the human specialists to fulfill their information needs. This effort also studied approaches to automatically predict the effectiveness of contingency plans, so that the ATM DSS can determine when a given contingency is no longer the best option and a new ‘plan B’ should be considered.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116399062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222986
Kai Zhang, Yongxin Liu, Jian Wang, Houbing Song, Dahai Liu
Accurate estimation of airspace capacity is essential to a safe, efficient and predictable air transportation system. Conventional approaches focus on controller workload using airspace complexity measurements that only consider operational conditions of controllers. However, such model-driven methods don’t completely demonstrate airspace capacity in the real world because of lack of consideration for other critical factors such as weather. To address this challenge, we propose a new airspace capacity estimation model based on decision tree ensembles. Our model combines multi-source data to quantify the maximum transportation capacity of en route sector under different circumstances.This paper makes the following contributions: (a) we present an interpretable data-driven model that estimates the capacities of the National Airspace System (NAS), and highlight factor importance for airspace capacities; (b) the airspace capacity estimated by our proposed model is dynamically adjusted based on the real-time environment that has the potential to be a guide for temporary flight path changes or air traffic selections for an emergency landing; and (c) we promote the role of machine learning-based methods in future ATM and airspace optimization.
{"title":"Tree-Based Airspace Capacity Estimation","authors":"Kai Zhang, Yongxin Liu, Jian Wang, Houbing Song, Dahai Liu","doi":"10.1109/ICNS50378.2020.9222986","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222986","url":null,"abstract":"Accurate estimation of airspace capacity is essential to a safe, efficient and predictable air transportation system. Conventional approaches focus on controller workload using airspace complexity measurements that only consider operational conditions of controllers. However, such model-driven methods don’t completely demonstrate airspace capacity in the real world because of lack of consideration for other critical factors such as weather. To address this challenge, we propose a new airspace capacity estimation model based on decision tree ensembles. Our model combines multi-source data to quantify the maximum transportation capacity of en route sector under different circumstances.This paper makes the following contributions: (a) we present an interpretable data-driven model that estimates the capacities of the National Airspace System (NAS), and highlight factor importance for airspace capacities; (b) the airspace capacity estimated by our proposed model is dynamically adjusted based on the real-time environment that has the potential to be a guide for temporary flight path changes or air traffic selections for an emergency landing; and (c) we promote the role of machine learning-based methods in future ATM and airspace optimization.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114611619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222996
Nouri Ghazavi, Scott Masarky, Joe Monahan, Mike Copp, Shawn Sanchez, Denise David, Tritana Supamusdisukul
Currently, the airport surface is one of the most difficult areas for a flight crew to navigate, especially at large complex airports. Taxi instructions are communicated through Ultra High Frequency / Very High Frequency (UHF/VHF) radio communications from the air traffic controller to the flight deck [1]. Frequency congestion at major airports increases difficulty conveying taxi instructions. The challenges of effective communication for ground controllers and pilots due to a single method of communication to many aircraft are clearly present in the current state. Flight crews may experience limitations to visibility and signage, or have a lack of reference to surface destinations, further complicating surface navigation. The combination of lengthy detailed taxi instructions, issuing instructions multiple times, radio frequency congestion, and unfamiliarity with the airport can result in a complex environment for the flight crew.The Federal Aviation Administration (FAA) is interested in improving clarity and delivery of taxi instructions through automation in the tower and the flight deck, focusing on Part 121 aircraft at larger airports. Current research interests will focus on developing capabilities and procedures to digitize taxi instructions on a Ground Control (GC) application and deliver the taxi instructions to the flight deck’s Electronic Flight Bag (EFB). Development of digital taxi instruction concepts and infrastructure should leverage existing National Airspace System (NAS) systems and procedures and identify gaps for further exploration. Digital taxi instructions may improve instruction clarity with minimal voice exchanges and clarifications from the GC before a common understanding is reached. Also, the flight deck will have less "head down" time processing taxi instructions, increasing surface situational awareness.This paper will provide initial research on the use of connected aircraft to support digital taxi instructions. The initial scope and future potential capabilities will be discussed. Identification of the functional hierarchy to realize digital taxi instruction capabilities will be reviewed. The concept has identified data elements and message sets that could be integrated into the digital taxi applications via System Wide Information Management (SWIM). Current exchange models like Flight Information Exchange Model (FIXM) should be considered for handling the message sets. Lastly, initial benefits of digital taxi instruction have been identified.
目前，机场地面是机组人员最难导航的区域之一，特别是在大型复杂机场。滑行指令通过超高频/甚高频(UHF/VHF)无线电通信从空中交通管制员传递到飞行甲板[1]。主要机场的频繁拥堵增加了传达出租车指令的难度。由于与许多飞机的通信方法单一，地面管制员和飞行员有效通信的挑战显然存在于当前状态。机组人员可能会遇到能见度和标识的限制，或者缺乏对地面目的地的参考，这进一步使地面导航复杂化。冗长详细的滑行指令、多次发出指令、无线电频率拥堵以及对机场的不熟悉，这些因素加在一起，会给机组人员带来复杂的环境。美国联邦航空管理局(FAA)有兴趣通过塔台和飞行甲板的自动化来提高出租车指令的清晰度和传递，重点关注大型机场的121部分飞机。目前的研究兴趣将集中在开发地面控制(GC)应用程序中数字化滑行指令的能力和程序，并将滑行指令传递给驾驶舱的电子飞行包(EFB)。数字出租车指令概念和基础设施的发展应利用现有的国家空域系统(NAS)系统和程序，并确定进一步探索的差距。在达成共识之前，数字出租车指令可以通过最少的语音交换和GC的澄清来提高指令的清晰度。此外，飞行甲板将有更少的“低头”时间处理滑行指令，增加水面态势感知。本文将提供关于使用互联飞机来支持数字滑行指令的初步研究。将讨论初始范围和未来的潜在能力。识别功能层次，以实现数字出租车指令能力将进行审查。该概念确定了可以通过系统范围信息管理(System Wide Information Management, SWIM)集成到数字出租车应用程序中的数据元素和消息集。应该考虑当前的交换模型，如航班信息交换模型(FIXM)来处理消息集。最后，已经确定了数字出租车指导的初步好处。
{"title":"Operational Evaluation of Digital Taxi Instruction","authors":"Nouri Ghazavi, Scott Masarky, Joe Monahan, Mike Copp, Shawn Sanchez, Denise David, Tritana Supamusdisukul","doi":"10.1109/ICNS50378.2020.9222996","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222996","url":null,"abstract":"Currently, the airport surface is one of the most difficult areas for a flight crew to navigate, especially at large complex airports. Taxi instructions are communicated through Ultra High Frequency / Very High Frequency (UHF/VHF) radio communications from the air traffic controller to the flight deck [1]. Frequency congestion at major airports increases difficulty conveying taxi instructions. The challenges of effective communication for ground controllers and pilots due to a single method of communication to many aircraft are clearly present in the current state. Flight crews may experience limitations to visibility and signage, or have a lack of reference to surface destinations, further complicating surface navigation. The combination of lengthy detailed taxi instructions, issuing instructions multiple times, radio frequency congestion, and unfamiliarity with the airport can result in a complex environment for the flight crew.The Federal Aviation Administration (FAA) is interested in improving clarity and delivery of taxi instructions through automation in the tower and the flight deck, focusing on Part 121 aircraft at larger airports. Current research interests will focus on developing capabilities and procedures to digitize taxi instructions on a Ground Control (GC) application and deliver the taxi instructions to the flight deck’s Electronic Flight Bag (EFB). Development of digital taxi instruction concepts and infrastructure should leverage existing National Airspace System (NAS) systems and procedures and identify gaps for further exploration. Digital taxi instructions may improve instruction clarity with minimal voice exchanges and clarifications from the GC before a common understanding is reached. Also, the flight deck will have less \"head down\" time processing taxi instructions, increasing surface situational awareness.This paper will provide initial research on the use of connected aircraft to support digital taxi instructions. The initial scope and future potential capabilities will be discussed. Identification of the functional hierarchy to realize digital taxi instruction capabilities will be reviewed. The concept has identified data elements and message sets that could be integrated into the digital taxi applications via System Wide Information Management (SWIM). Current exchange models like Flight Information Exchange Model (FIXM) should be considered for handling the message sets. Lastly, initial benefits of digital taxi instruction have been identified.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124469572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9222883
Hang Zhou, Xiao-Bing Hu
In order to overcome the demerits of traditional city air terminals, a new service mode based on urban mobile stations for providing the urban luggage check-in service is proposed in this study. The station locations are dynamically allocated based on the real-time passenger distribution. Three aspects including the average distance from passengers to urban mobile stations, the maximum tolerable distance, and the maximum service capacity are considered. An effective hybrid algorithm is developed, in which the ripple-spreading algorithm is applied for solving many-to-many path optimization problems and an adaptive genetic algorithm is developed for locating stations. In a case study of Tianjin, China, the proposed method is applied to allocate the urban mobile stations. The service performance of the new mode is compared with that of the traditional city air terminals mode to show the advantages.
{"title":"An Effective Hybrid Algorithm for Real-Time Optimizing Locations of Urban Mobile Stations for Luggage Check-in Service","authors":"Hang Zhou, Xiao-Bing Hu","doi":"10.1109/ICNS50378.2020.9222883","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9222883","url":null,"abstract":"In order to overcome the demerits of traditional city air terminals, a new service mode based on urban mobile stations for providing the urban luggage check-in service is proposed in this study. The station locations are dynamically allocated based on the real-time passenger distribution. Three aspects including the average distance from passengers to urban mobile stations, the maximum tolerable distance, and the maximum service capacity are considered. An effective hybrid algorithm is developed, in which the ripple-spreading algorithm is applied for solving many-to-many path optimization problems and an adaptive genetic algorithm is developed for locating stations. In a case study of Tianjin, China, the proposed method is applied to allocate the urban mobile stations. The service performance of the new mode is compared with that of the traditional city air terminals mode to show the advantages.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"11 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116816281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ICNS50378.2020.9223015
Mihir Rimjha, Sayantan Tarafdar, N. Hinze, A. Trani, H. Swingle, Jerry C. Smith, T. Marien, S. Dollyhigh
The objective of this paper is to study the potential market for electric Vertical-Takeoff-and-Landing (eVTOL) aircraft in the cargo delivery role in an urban network. Specifically, we study the potential small-package cargo operations network in the Northern California region. Recent developments in the cargo shipping industry have opened opportunities for faster modes of small-package delivery in intra-city markets. With increasing congestion of ground transportation modes and limited catchment areas, there is a potential for small-package, high-value cargo delivery using proposed eVTOL aircraft.The On-Demand Mobility (ODM) concept for cargo transportation could improve the speed and efficiency of the delivery of small packages to communities. The concept could expand the delivery services offered by traditional ground transportation modes. The concept, however, needs to offer compelling speed advantages at a reasonable cost. The objective of this study is to estimate the potential demand for ODM cargo operations in the Northern California area encompassing 17 counties. Annual cargo flows in the study area are estimated using the Transearch, Freight Analysis Framework 4, and Bureau of Transportation Statistics T-100 International datasets. A parametric analysis of market share presents the results of this study.The study presents a first-order impact analysis of ODM cargo operations on passenger ODM operations. A significant challenge in this study is the lack of specific level of detail of the shipment cost of the various databases used. Generally, private cargo companies do disclose detailed records of shipments to the public.
本文的目的是研究电动垂直起降(eVTOL)飞机在城市网络中的货运角色的潜在市场。具体来说，我们研究潜在的小包裹货物运营网络在北加州地区。货运业最近的发展为在城市内市场上更快的小包裹递送模式提供了机会。由于地面运输方式日益拥挤，集水区有限，建议使用eVTOL飞机运送小包裹、高价值的货物。货物运输的按需移动(ODM)概念可以提高向社区运送小包裹的速度和效率。这一概念可以扩展传统地面运输模式提供的交付服务。然而，这个概念需要以合理的成本提供令人信服的速度优势。本研究的目的是估计包括17个县在内的北加州地区对ODM货运业务的潜在需求。使用Transearch、Freight Analysis Framework 4和Bureau of Transportation Statistics T-100 International数据集估算研究区域的年货运量。本研究的结果为市场占有率的参数化分析。本研究提出货运ODM营运对客运ODM营运的一阶影响分析。本研究的一个重大挑战是缺乏对所使用的各种数据库的运输成本的具体详细程度。一般来说，私人货运公司确实会向公众披露货运的详细记录。
{"title":"On-Demand Mobility Cargo Demand Estimation in Northern California Region","authors":"Mihir Rimjha, Sayantan Tarafdar, N. Hinze, A. Trani, H. Swingle, Jerry C. Smith, T. Marien, S. Dollyhigh","doi":"10.1109/ICNS50378.2020.9223015","DOIUrl":"https://doi.org/10.1109/ICNS50378.2020.9223015","url":null,"abstract":"The objective of this paper is to study the potential market for electric Vertical-Takeoff-and-Landing (eVTOL) aircraft in the cargo delivery role in an urban network. Specifically, we study the potential small-package cargo operations network in the Northern California region. Recent developments in the cargo shipping industry have opened opportunities for faster modes of small-package delivery in intra-city markets. With increasing congestion of ground transportation modes and limited catchment areas, there is a potential for small-package, high-value cargo delivery using proposed eVTOL aircraft.The On-Demand Mobility (ODM) concept for cargo transportation could improve the speed and efficiency of the delivery of small packages to communities. The concept could expand the delivery services offered by traditional ground transportation modes. The concept, however, needs to offer compelling speed advantages at a reasonable cost. The objective of this study is to estimate the potential demand for ODM cargo operations in the Northern California area encompassing 17 counties. Annual cargo flows in the study area are estimated using the Transearch, Freight Analysis Framework 4, and Bureau of Transportation Statistics T-100 International datasets. A parametric analysis of market share presents the results of this study.The study presents a first-order impact analysis of ODM cargo operations on passenger ODM operations. A significant challenge in this study is the lack of specific level of detail of the shipment cost of the various databases used. Generally, private cargo companies do disclose detailed records of shipments to the public.","PeriodicalId":424869,"journal":{"name":"2020 Integrated Communications Navigation and Surveillance Conference (ICNS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123127261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：