2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)最新文献

{"title":"Trajectory Flight-Time Prediction based on Machine Learning for Unmanned Traffic Management","authors":"C. Conte, D. Accardo, G. Rufino","doi":"10.1109/DASC50938.2020.9256513","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256513","url":null,"abstract":"This paper describes the study conducted to predict the trajectory flight-time of a drone adopting a machine learning approach. The proposed method has been carried out developing a feedforward neural network to estimate the flight-time needed by the drone to perform a selected corner of a designed path. To acquire a consistent database for the neural network training several reference corner paths have been flown by a test drone. The reference corners have fixed side length and different turning angle. Neural network input parameters are the corner angle, relative orientation and intensity of wind. From the telemetry analysis the flight-time to fly the corner path has been computed and employed to train the neural network. The Levenberg-Marquardt algorithm and the Bayesian Regularization backpropagation algorithm have been exploited as training functions, analyzing several neural network architectures with a different number of hidden layers and neurons. At the end, the neural networks that are characterized by the best training and test performance have been selected for each training function. Stating the trained network, a generic path has been planned to test the proposed method. The error between the estimated flight-time and the real flight-time from the drone telemetry has been evaluated.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123563911","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}

{"title":"Learning-to-Fly RL: Reinforcement Learning-based Collision Avoidance for Scalable Urban Air Mobility","authors":"Kuk Jin Jang, Y. Pant, Alena Rodionova, R. Mangharam","doi":"10.1109/DASC50938.2020.9256710","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256710","url":null,"abstract":"As hundreds of Unmanned Aircraft System (UAS) operate within urban airspaces, automated and decentralized UAS traffic management (UTM) will be critical to maintain safe and efficient operations. In this work, we present Learning-to-Fly with Reinforcement Learning (L2F-RL), a decentralized, on-demand Collision Avoidance (CA) framework that systematically combines machine learning with cooperative model predictive control for UAS collision avoidance while retaining satisfaction of higher-level mission objectives. L2F-RL consists of: 1) RL-based policy for conflict resolution (CR) with discrete-decision making, 2) decentralized, cooperative model predictive control for CA. To accelerate training with RL, we utilize reward shaping and curriculum learning. Our approach outperforms baseline approaches with a 99.10% separation rate (ratio of success to total test cases) in the worst case, improving to 100% in the best case with a 1000X improvement in computation time compared to centralized methods. Our results demonstrate the potential of combining learning approaches with optimization-based control, making it a significant contribution towards scalable, decentralized UTM.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123106330","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}

{"title":"OpenSky Report 2020: Analysing in-flight emergencies using big data","authors":"X. Olive, A. Tanner, Martin Strohmeier, Matthias Schäfer, M. Feridun, Allan Tart, I. Martinovic, Vincent Lenders","doi":"10.1109/DASC50938.2020.9256787","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256787","url":null,"abstract":"Transponder codes are four octal digit numbers transmitted by an aircraft transponder in response to a secondary surveillance radar interrogation. These discrete transponder codes (also known as squawk codes) help with the clear labelling of an affected aircraft on radar screens. Three particular squawk codes are associated with specific situations: 7500 for hijacking, 7600 for radio failure and 7700 for general emergencies, often related to medical or technical issues. In this paper, we analyse more than 800 trajectories received by the OpenSky Network over a two-year period as they were broadcasting the 7700 emergency code. Background information about the reason of these emergencies is taken from social networks and other crowdsourced information sources on the Internet. We provide an overview of various reasons for in-flight emergencies, typical trajectory patterns and communication strategies by airlines. Based on our semi-labelled dataset of trajectories, we also train models able to suggest possible explanations for trajectories when no information is available.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129956572","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}

{"title":"Software Solution for Visualization and Evaluation of Flight Data in Terms of Competency-Based Training","authors":"Tomáš Malich, V. Socha, R. Matyáš, L. Hanakova, Stanislav Kusmirek, Vojtěch Kráčmar","doi":"10.1109/DASC50938.2020.9256590","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256590","url":null,"abstract":"In this paper, we present a complex solution for flight data gathering, analyzation, and visualization. This solution can be used for the Competency-Based Training of pilots in general aviation. For the data gathering, we are introducing a concept of an embedded device. For data analyzation, we are introducing the approach for algorithmic detection of flight maneuvers based on the recorded flight data. There is a multiplatform software application for data visualization. We are also describing the reasons for creating such solutions and potential future uses of our hardware and software products. This paper is mostly describing the important requirements and their implementation regarding the future usage for Competency-Based Training of pilots in general aviation. We are not describing a lot of technical details to keep this paper straightforward and we are mostly focusing on passing the whole idea and benefits of our products.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114627071","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}

{"title":"Multiclass Geospatial Object Detection using Machine Learning-Aviation Case Study","authors":"D. Dhulipudi, Rajan Ks","doi":"10.1109/DASC50938.2020.9256771","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256771","url":null,"abstract":"There is growing interest to explore the autonomous taxiing that can sense its environment and maneuver safely with little or no human input. This technology is like the one developed for driver less cars that synthesize information from multiple sensors, which sense surrounding environment to detect road surface, lanes, obstacles and signage. This paper presents application of computer vision and machine learning to autonomous method for the surface movement of an air vehicle. We present a system and method that uses pattern recognition which aids unmanned aircraft system (UAS) and enhance the manned air vehicle landing and taxiing. Encouraged with our previous results [1], we extend upon our research to include multiple object relevant to taxiing. The objective of the current project is to build training dataset of annotated objects acquired from overhead perspective. It is useful for training a deep neural network to learn to detect, count specific airport objects in a video or image. This paper details the procedure and parameters used to create training dataset for running convolutional neural networks (CNNs) on a set of aerial images for efficient and automated object recognition. In this method, multiple airport surface signage dataset from satellite images are subjected to training for pattern recognition. This trained system learns and then identifies and locates important visual references from imaging sensors and could help in decision making during taxiing phase.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132865184","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}

{"title":"Building Transparent and Personalized AI Support in Air Traffic Control","authors":"C. Westin, B. Hilburn, C. Borst, E. van Kampen, M. Bång","doi":"10.1109/DASC50938.2020.9256708","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256708","url":null,"abstract":"Artificial intelligence is considered a key enabler for realizing a more efficient future air traffic management system. As the automation designed to support us grows more sophisticated and complex, our understanding of it tends to suffer. Recent research has addressed this issue in two ways: either through increased automation transparency or increased personalization. This paper overviews recent work in these two areas of strategic conformance (i.e., personalization) and automation transparency (e.g., explainable artificial intelligence and machine learning interpretability). We discuss how to achieve and how to balance conformance and transparency in the context of a machine learning system for conflict detection and resolution in air traffic control. In the MAHALO project, we aim to build, and empirically evaluate, a personalized and transparent decision support system by combining supervised and reinforcement learning approaches. We believe that such a system could strive for optimal performance while accommodating individual differences. By knowing the individual's preferences, the system would be able to afford transparency by explaining both why it suggests another solution (that deviates from the individual's), and why this solution is considered to be better.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133603903","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}

{"title":"Verification of an Airport Taxiway Path-Finding Algorithm","authors":"Siyuan He, Ke Du, Joshua Wilhelm, Jean-Baptiste Jeannin","doi":"10.1109/DASC50938.2020.9256698","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256698","url":null,"abstract":"At controlled airports, aircraft taxi on the ground following precise instructions from Air Traffic Control. Those instructions can get quite intricate and complicated and lead to errors from Air Traffic Control or confusion from pilots, especially at larger airports. In order to reduce the pilots' workload and lower the risk of accidents from pilot error or Air Traffic Control mistakes, it is desirable to automate taxiing of aircraft. One aspect of automated taxiing is to automatically find the correct taxiway path from Air Traffic Control instructions. In this paper, we implement and formally verify a taxiway path-finding algorithm in the Coq proof assistant, and test it on three different airports of various sizes (Ann Arbor, Willow Run and Detroit Wayne). We first build an undirected airport taxiway graph topology, extend it to a directed expanded graph, disallowing some unrealistic paths such as U-turns, and formally encode the two graphs into Coq types. We then implement the path-finding algorithm on the directed expanded graph, and map downward the result back to the undirected graph. We formally verify the correctness of our algorithm in the Coq theorem prover.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"518 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133761118","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}

{"title":"UAV-Based Measuring System for Terrestrial Navigation and Landing Aid Signals","authors":"Daniel Sommer, Ashok Sarath Chandra Reddy Irigireddy, Justin Parkhurst, Kevin Pepin, Eduardo-Rojas Nastrucci","doi":"10.1109/DASC50938.2020.9256447","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256447","url":null,"abstract":"Terrestrial navigation and landing aid stations help a pilot to safely navigate and land an aircraft by using signals originating from ground-based stations. These systems need to be tested periodically toconfirm that their performance is within International Civil Aviation Organization (ICA0) limits. Currently, this test is performed by using a manned aircraft making several passes around the ground stations or along the runways. In this paper, an unmanned aerial system (UAS), called the positional information via GPS and encoded overlayed navigation signals (PIGEONS), is presented. The system employs a light-weight hexacopter, with a wingspan of 55 cm, that performs autonomous flight and uses an onboard software-defined radio (SDR) that measures the instrument landing system (ILS) and VHF omnidirectional range (VOR) systems. The UAS test system is designed so that flight coordinates can be preprogrammed, making it adaptable to different test locations. The system data is stored onboard while telemetry information is sent to the pilot during flight to inform them of the system's status. The ILS, VOR, and GPS measurements are analyzed once the UAS has completed the flight to determine the compliance of these guidance and landing aid systems with the performance requirements from the ICAO. Positioning measurement inaccuracies are reduced by using a Real-Time Kinematic (RTK) GPS. The ILS system was tested at DAB Airport in Daytona Beach, FL and the VOR was tested at OMN Airport in Ormond Beach, FL. The azimuth measurements for the VOR tower were taken between 292° and 328°. Two drive-bys were performed, and two moving averages were applied in post-processing to both passes using 50,000 and 100,000 samples. This resulted in average magnitudes of error between the measured data and reference GPS for the four passes of 4.18°, 5.34°, 2.24°, and 2.05°. Due to measuring limitations, the measured modulation indexes were limited, being bounded before hitting the 0.0 and 0.4 modulation indexes.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114065899","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}

{"title":"Coupling Consensus Based Tasks with Subsumption Architecture for UAS Swarm Based Intelligence Surveillance and Reconnaissance Operations","authors":"Prasanna Kolar","doi":"10.1109/DASC50938.2020.9256816","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256816","url":null,"abstract":"This paper investigates the controls problem of coupling consensus based tasks with a behavioral based algorithm like subsumption architecture and used in tracking of multiple unmanned aerial vehicles working in dynamic and distributed environments. Distributed autonomous systems continue to grow in complexity and remain a challenging and interesting research topic. The system is designed such that each vehicle requires only a local information exchange, with out the need to communicate with a global central system. A general class of state and input transformation is utilized to convert a tracking problem into a consensus like time-varying problem. We have successfully implemented a swarm of autonomous aerial vehicles, by integrating a consensus based task allocation system with a behavior based system that works by concepts of subsumption architecture. This work focuses on integrating a decentralized task planning algorithm called Consensus Based Bundled Algorithm with a true behavior based exploratory architecture called Subsumption Architecture in order to exploit the best features of both these architectures. An improvement in the framework was observed in the task allocation when a relationship coupling logic was implemented. It is proposed that if the parent task is considered by an agent and executes the entire bundle, planning the reassignment of tasks are not necessary during the consensus based tasking. This planned task set can be re-assigned dynamically during run-time by the Subsumption Architecture, when implemented on a system that has an on-board autonomy and computing system. We implement this combined framework for the task of Intelligence Surveillance and Reconnaissance.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114206534","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}

{"title":"In-Flight Entertainment Datalink Analysis and Simulation","authors":"Shahid Ayub, I. Petrunin, A. Tsourdos, Saba Al-Rubaye, Gareth Stapylton, Gary Dent","doi":"10.1109/DASC50938.2020.9256432","DOIUrl":"https://doi.org/10.1109/DASC50938.2020.9256432","url":null,"abstract":"In-Flight Entertainment (IFE) datalink is one of the airport connectivity areas, where efforts are being made by different stakeholders to improve and update the entertainment services offered to the passengers. An important objective of IFE datalink is to increase the flight operation efficiency by managing IFE data transfer within turnaround time which is about 45 minutes. With the rapid advancements and innovation in multimedia applications and services, the IFE data size in the future will turn into terabytes, therefore, this transfer requires a multi-Gbps datalink in order to be completed within expected turnaround time. This paper focuses on simulation of IFE datalink communication scenario at an airport surface using Wi-Fi (802.11ac) technology, provides rules and guidelines on suitability of wireless datalinks for IFE update at the airports, studies QoS requirements, and performs optimization. Several aspects of the IFE datalink selection and deployment have been considered, such as airport operational areas, airport layouts, radio frequency, and data congestion before conducting a capacity and coverage analysis.","PeriodicalId":112045,"journal":{"name":"2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115139667","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}