Loss of control (LOC) is a prevalent cause of drone crashes. Onboard prevention systems should be designed requiring low computing power, for which data-driven techniques provide a promising solution. This study proposes the use of recurrent neural networks (RNNs) for LOC prediction. Four architectures were trained in order to identify which RNN configuration is most suitable and if this model can predict LOC for changing aerodynamic characteristics, wind conditions, quadcopter types, and LOC events. One-hundred and seventy-two real-world LOC events were conducted using a 53 g Tiny Whoop, a 73 g URUAV UZ85, and a 265 g GEPRC CineGO quadcopter. For these flights, LOC was initiated by demanding an excessive yaw rate (2000 deg/s), which provokes an unrecoverable upset and subsequent crash. All RNNs were trained using only onboard sensor measurements. It was found that the commanded rotor values provided the clearest early warning signals for LOC because these values showed saturation before LOC. Moreover, all four architectures could correctly and reliably predict the impending LOC event 2 s before it actually occurred. Furthermore, to investigate generality of the methodology, the predictors were successfully applied to flight data in which the quadcopter mass, blade diameter, and blade count were varied.
{"title":"Loss-of-Control Prediction of a Quadcopter Using Recurrent Neural Networks","authors":"A. V. Altena, J.J.B.C. Van Beers, C. de Visser","doi":"10.2514/1.i011231","DOIUrl":"https://doi.org/10.2514/1.i011231","url":null,"abstract":"Loss of control (LOC) is a prevalent cause of drone crashes. Onboard prevention systems should be designed requiring low computing power, for which data-driven techniques provide a promising solution. This study proposes the use of recurrent neural networks (RNNs) for LOC prediction. Four architectures were trained in order to identify which RNN configuration is most suitable and if this model can predict LOC for changing aerodynamic characteristics, wind conditions, quadcopter types, and LOC events. One-hundred and seventy-two real-world LOC events were conducted using a 53 g Tiny Whoop, a 73 g URUAV UZ85, and a 265 g GEPRC CineGO quadcopter. For these flights, LOC was initiated by demanding an excessive yaw rate (2000 deg/s), which provokes an unrecoverable upset and subsequent crash. All RNNs were trained using only onboard sensor measurements. It was found that the commanded rotor values provided the clearest early warning signals for LOC because these values showed saturation before LOC. Moreover, all four architectures could correctly and reliably predict the impending LOC event 2 s before it actually occurred. Furthermore, to investigate generality of the methodology, the predictors were successfully applied to flight data in which the quadcopter mass, blade diameter, and blade count were varied.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"70 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84459264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Super-Resolution of Remote Sensing Images from Flagship Lunar-Orbiting Missions","authors":"Aneesh M. Heintz, Ian Mackey, M. Peck","doi":"10.2514/1.i011165","DOIUrl":"https://doi.org/10.2514/1.i011165","url":null,"abstract":"","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"28 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84209764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many onboard vision tasks for spacecraft navigation require high-quality remote-sensing images with clearly decipherable features. However, design constraints and the operational and environmental conditions limit their quality. Enhancing images through postprocessing is a cost-efficient solution. Current deep learning methods that enhance low-resolution images through super-resolution do not quantify network uncertainty of predictions and are trained at a single scale, which hinders practical integration in image-acquisition pipelines. This work proposes performing multiscale super-resolution using a deep normalizing flow network for uncertainty-quantified and Monte Carlo estimates so that image enhancement for spacecraft vision tasks may be more robust and predictable. The proposed network architecture outperforms state-of-the-art super-resolution models on in-orbit lunar imagery data. Simulations demonstrate its viability on task-based evaluations for landmark identification.
{"title":"Multiscale Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows","authors":"Aneesh M. Heintz, Mason Peck, Ian Mackey","doi":"10.2514/1.i011089","DOIUrl":"https://doi.org/10.2514/1.i011089","url":null,"abstract":"Many onboard vision tasks for spacecraft navigation require high-quality remote-sensing images with clearly decipherable features. However, design constraints and the operational and environmental conditions limit their quality. Enhancing images through postprocessing is a cost-efficient solution. Current deep learning methods that enhance low-resolution images through super-resolution do not quantify network uncertainty of predictions and are trained at a single scale, which hinders practical integration in image-acquisition pipelines. This work proposes performing multiscale super-resolution using a deep normalizing flow network for uncertainty-quantified and Monte Carlo estimates so that image enhancement for spacecraft vision tasks may be more robust and predictable. The proposed network architecture outperforms state-of-the-art super-resolution models on in-orbit lunar imagery data. Simulations demonstrate its viability on task-based evaluations for landmark identification.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135516901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Aerodynamic Parameter Estimation for a Morphing Unmanned Aerial Vehicle from Flight Tests","authors":"Zhe Hui, Gang Chen","doi":"10.2514/1.i011183","DOIUrl":"https://doi.org/10.2514/1.i011183","url":null,"abstract":"","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"197 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75040699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zachary C. Goddard, K. Wardlaw, Kyle Williams, A. Mazumdar
Motion primitives allow for application of discrete search algorithms to rapidly produce trajectories in complex continuous space. The maneuver automaton (MA) provides an elegant formulation for creating a primitive library based on trims and maneuvers. However, performance is fundamentally limited by the contents of the primitive library. If the library is too sparse, performance can be poor in terms of path cost, whereas a library that is too large can increase run time. This work outlines new methods for using genetic algorithms to prune a primitive library. The proposed methods balance the path cost and planning time while maintaining the reachability of the MA. The genetic algorithm in this paper evaluates and mutates populations of motion primitive libraries to optimize both objectives. We illustrate the performance of these methods with a simulated study using a nonlinear medium-fidelity F-16 model. We optimize a library with the presented algorithm for obstacle-free navigation and a nap-of-the-Earth navigation task. In the obstacle-free navigation task, we show a tradeoff of a 10.16% higher planning cost for a 96.63% improvement in run time. In the nap-of-the-Earth task, we show a tradeoff of a 9.712% higher planning cost for a 92.06% improvement in run time.
{"title":"Selecting Minimal Motion Primitive Libraries with Genetic Algorithms","authors":"Zachary C. Goddard, K. Wardlaw, Kyle Williams, A. Mazumdar","doi":"10.2514/1.i011188","DOIUrl":"https://doi.org/10.2514/1.i011188","url":null,"abstract":"Motion primitives allow for application of discrete search algorithms to rapidly produce trajectories in complex continuous space. The maneuver automaton (MA) provides an elegant formulation for creating a primitive library based on trims and maneuvers. However, performance is fundamentally limited by the contents of the primitive library. If the library is too sparse, performance can be poor in terms of path cost, whereas a library that is too large can increase run time. This work outlines new methods for using genetic algorithms to prune a primitive library. The proposed methods balance the path cost and planning time while maintaining the reachability of the MA. The genetic algorithm in this paper evaluates and mutates populations of motion primitive libraries to optimize both objectives. We illustrate the performance of these methods with a simulated study using a nonlinear medium-fidelity F-16 model. We optimize a library with the presented algorithm for obstacle-free navigation and a nap-of-the-Earth navigation task. In the obstacle-free navigation task, we show a tradeoff of a 10.16% higher planning cost for a 96.63% improvement in run time. In the nap-of-the-Earth task, we show a tradeoff of a 9.712% higher planning cost for a 92.06% improvement in run time.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"14 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91133286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiao Chu, W. Zeng, Xianghua Tan, Yadong Zhou, Dan Zhu
Due to the variety of flight patterns in airport terminal airspace, as well as the high global similarity of different flight patterns entering and leaving from the same runway or corridor, it is difficult for current mainstream methods to achieve good clustering. To this end, this paper first constructs a truncated dynamic time warping (TDTW) trajectory similarity measurement to characterize different trajectory patterns with high global similarity and large local differences. Furthermore, a hierarchical flight pattern mining method is proposed, which is divided into four layers according to different characteristics. The first three layers of the method classify trajectories according to takeoff and landing types, runways, and corridors; whereas the fourth layer uses a [Formula: see text]-medoid clustering method based on TDTW, thereby making the mining process more controllable and in line with actual operation. Compared to dynamic time warping, the experimental results show that the intraclass compactness and interclass separation of the cluster obtained by the proposed method have decreased and increased by 44.6 and 20.1%, respectively, and the overall performance has improved by 54.1%. More refined and reasonable flight patterns have been obtained.
{"title":"Hierarchical Method for Mining a Prevailing Flight Pattern in Airport Terminal Airspace","authors":"Xiao Chu, W. Zeng, Xianghua Tan, Yadong Zhou, Dan Zhu","doi":"10.2514/1.i011263","DOIUrl":"https://doi.org/10.2514/1.i011263","url":null,"abstract":"Due to the variety of flight patterns in airport terminal airspace, as well as the high global similarity of different flight patterns entering and leaving from the same runway or corridor, it is difficult for current mainstream methods to achieve good clustering. To this end, this paper first constructs a truncated dynamic time warping (TDTW) trajectory similarity measurement to characterize different trajectory patterns with high global similarity and large local differences. Furthermore, a hierarchical flight pattern mining method is proposed, which is divided into four layers according to different characteristics. The first three layers of the method classify trajectories according to takeoff and landing types, runways, and corridors; whereas the fourth layer uses a [Formula: see text]-medoid clustering method based on TDTW, thereby making the mining process more controllable and in line with actual operation. Compared to dynamic time warping, the experimental results show that the intraclass compactness and interclass separation of the cluster obtained by the proposed method have decreased and increased by 44.6 and 20.1%, respectively, and the overall performance has improved by 54.1%. More refined and reasonable flight patterns have been obtained.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"08 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85830737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Space launch vehicles are highly complex multidisciplinary systems with multiple subsystems. These subsystems vary significantly, complicating the selection of an objective function. Exergy efficiency has been suggested by some as a suitable objective function with relevance across a diverse set of subsystems; however, some characteristics of exergy efficiency may make it poorly suited for the task. At its core, exergy is the amount of work available from a system for a certain environment. In this paper, the use of exergy efficiency in the optimization of a space launch vehicle is explored. Exergy efficiency objective functions are constructed, including and excluding mass decreases from staging. These objective functions are used for the optimization of a physics-based rocket trajectory model. The results are compared to historical Saturn V data and analyzed to investigate the suitability of the metric. Due to the importance of mass in mechanical energy calculations, exergy efficiency can favor designs with more massive final stages, particularly when calculations include the staging-related mass decreases.
{"title":"Evaluation of Exergy Efficiency Optimization of Space Launch Vehicles","authors":"C. White, Jeffrey E. Dyas, Bryan L. Mesmer","doi":"10.2514/1.i011241","DOIUrl":"https://doi.org/10.2514/1.i011241","url":null,"abstract":"Space launch vehicles are highly complex multidisciplinary systems with multiple subsystems. These subsystems vary significantly, complicating the selection of an objective function. Exergy efficiency has been suggested by some as a suitable objective function with relevance across a diverse set of subsystems; however, some characteristics of exergy efficiency may make it poorly suited for the task. At its core, exergy is the amount of work available from a system for a certain environment. In this paper, the use of exergy efficiency in the optimization of a space launch vehicle is explored. Exergy efficiency objective functions are constructed, including and excluding mass decreases from staging. These objective functions are used for the optimization of a physics-based rocket trajectory model. The results are compared to historical Saturn V data and analyzed to investigate the suitability of the metric. Due to the importance of mass in mechanical energy calculations, exergy efficiency can favor designs with more massive final stages, particularly when calculations include the staging-related mass decreases.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"5 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78404260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jeffrey M. Newcamp, Michael Z. Miller, A. Golkar, W. Gu, A. Salado
{"title":"Introduction to the Systems Engineering’s Top Space Challenges Virtual Collection","authors":"Jeffrey M. Newcamp, Michael Z. Miller, A. Golkar, W. Gu, A. Salado","doi":"10.2514/1.i011266","DOIUrl":"https://doi.org/10.2514/1.i011266","url":null,"abstract":"","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"12 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80806965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ye Liu, K. K. Ng, Nan Chu, Kai Kwong Hon, Xiaoge Zhang
Recent studies in four-dimensional flight trajectories attempted to identify the impacts of various flight trajectories and maneuver parameters on air traffic management efficiency and aviation safety. The previous studies attempted to cluster trajectories based on spatial scales. However, these might require converting the flight trajectories to equal lengths for sequence-based clustering. This paper proposes a novel trajectory three-channel image representation and Gaussian mixture model clustering based on several image-processing methodologies. The aircraft’s latitude, longitude, flight level, and ground speed are represented as corresponding pixel information of the image followed by image-based flight trajectory representation and clustering methods (including deep convolutional autoencoder (DCAE), principal component analysis (PCA) image dimensionality reduction, and image feature points extraction) using a half-year of automatic dependent surveillance-broadcast flight trajectory data in the Hong Kong flight information region. The computational results indicate that the image-based trajectory representation produces more insights for trajectory processing, such as the application of convolutional neural networks and image-processing algorithms. In addition, the DCAE model has better performance and robustness for trajectory feature extraction and similarity analysis than PCA, which will provide ideas for multiparameter trajectory similarity analysis and prediction.
{"title":"Spatiotemporal Image-Based Flight Trajectory Clustering Model with Deep Convolutional Autoencoder Network","authors":"Ye Liu, K. K. Ng, Nan Chu, Kai Kwong Hon, Xiaoge Zhang","doi":"10.2514/1.i011194","DOIUrl":"https://doi.org/10.2514/1.i011194","url":null,"abstract":"Recent studies in four-dimensional flight trajectories attempted to identify the impacts of various flight trajectories and maneuver parameters on air traffic management efficiency and aviation safety. The previous studies attempted to cluster trajectories based on spatial scales. However, these might require converting the flight trajectories to equal lengths for sequence-based clustering. This paper proposes a novel trajectory three-channel image representation and Gaussian mixture model clustering based on several image-processing methodologies. The aircraft’s latitude, longitude, flight level, and ground speed are represented as corresponding pixel information of the image followed by image-based flight trajectory representation and clustering methods (including deep convolutional autoencoder (DCAE), principal component analysis (PCA) image dimensionality reduction, and image feature points extraction) using a half-year of automatic dependent surveillance-broadcast flight trajectory data in the Hong Kong flight information region. The computational results indicate that the image-based trajectory representation produces more insights for trajectory processing, such as the application of convolutional neural networks and image-processing algorithms. In addition, the DCAE model has better performance and robustness for trajectory feature extraction and similarity analysis than PCA, which will provide ideas for multiparameter trajectory similarity analysis and prediction.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"64 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85671278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Patrick M. Dillon, Michael D. Zollars, Isaac E. Weintraub, Alexander Von Moll
{"title":"Optimal Trajectories for Aircraft Avoidance of Multiple Weapon Engagement Zones","authors":"Patrick M. Dillon, Michael D. Zollars, Isaac E. Weintraub, Alexander Von Moll","doi":"10.2514/1.i011224","DOIUrl":"https://doi.org/10.2514/1.i011224","url":null,"abstract":"","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"80 1","pages":""},"PeriodicalIF":1.5,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80927305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","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：