首页 > 最新文献

Journal of Aerospace Information Systems最新文献

英文 中文
Optimal Service Migration for Data and Reasoning Fabric 数据与推理结构的最优业务迁移
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011120
Vahram Stepanyan, Stefan Schuet, Kalmanje Krishnakumar
In this paper we consider migration problem for Data and Reasoning Fabric (DRF)-enabled airspace operations assuming a fixed cloud/edge infrastructure with allocated computing, storage, and power resources, where cloud/edge servers and communication stations are in a wired connected network, while vehicles use a wireless network for communication. The objective is to automatically select the best location for the requested service execution, which achieves minimum cost while satisfying the user quality of service (QoS) and available resources constraints. To this end, estimates of the response time, consumed energy, and total cost are defined for each potential compute location. A mixed-integer linear program is then formulated and solved to identify optimal compute locations given QoS constraints and network infrastructure limitations, with worst-case vehicle positioning. The approach is applied to trajectory replanning use case to avoid a collision with an emergency vehicle in real time.
在本文中,我们考虑了支持数据和推理结构(DRF)的空域操作的迁移问题,假设具有分配的计算、存储和电源资源的固定云/边缘基础设施,其中云/边缘服务器和通信站位于有线连接网络中,而车辆使用无线网络进行通信。目标是为请求的服务执行自动选择最佳位置,在满足用户服务质量(QoS)和可用资源约束的同时实现最低成本。为此,为每个可能的计算位置定义响应时间、消耗的能量和总成本的估计。然后制定并求解了一个混合整数线性规划,以确定给定QoS约束和网络基础设施限制下最坏情况下车辆定位的最优计算位置。将该方法应用于轨迹重新规划用例,以实时避免与应急车辆的碰撞。
{"title":"Optimal Service Migration for Data and Reasoning Fabric","authors":"Vahram Stepanyan, Stefan Schuet, Kalmanje Krishnakumar","doi":"10.2514/1.i011120","DOIUrl":"https://doi.org/10.2514/1.i011120","url":null,"abstract":"In this paper we consider migration problem for Data and Reasoning Fabric (DRF)-enabled airspace operations assuming a fixed cloud/edge infrastructure with allocated computing, storage, and power resources, where cloud/edge servers and communication stations are in a wired connected network, while vehicles use a wireless network for communication. The objective is to automatically select the best location for the requested service execution, which achieves minimum cost while satisfying the user quality of service (QoS) and available resources constraints. To this end, estimates of the response time, consumed energy, and total cost are defined for each potential compute location. A mixed-integer linear program is then formulated and solved to identify optimal compute locations given QoS constraints and network infrastructure limitations, with worst-case vehicle positioning. The approach is applied to trajectory replanning use case to avoid a collision with an emergency vehicle in real time.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"35 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134956794","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}
引用次数: 0
Data-Driven Diagnosis of Multicopter Thrust Fault Using Supervised Learning with Inertial Sensors 基于惯性传感器监督学习的多旋翼推力故障数据驱动诊断
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011256
Taegyun Kim, Seungkeun Kim, Hyo-Sang Shin
This study proposes a data-driven fault diagnosis for multicopter unmanned aerial vehicles that uses the principal direction vector of inertial measurement unit (IMU) sensor signals calculated by principal component analysis. The main idea comes from the fact that a normal sphere-shaped distribution of the sensor data changes to a specific elliptical shape under a certain thrust fault situation. The fault diagnosis is based on classification and regression using supervised learning with the gyroscope and accelerometer datasets of an IMU. We analyze the performance of the proposed approach by depending on different learning algorithms. To verify the diagnostic performance, ground experiments with a hexacopter on the gimbaled jig are performed for various cases of damaged propellers. Then, the applicability of the proposed data-driven fault diagnosis is confirmed by analyzing the accuracy of the fault’s location and degree.
提出了一种利用主成分分析计算惯性测量单元(IMU)传感器信号主方向矢量的多旋翼无人机数据驱动故障诊断方法。其主要思想来自于在一定的逆冲断层情况下,传感器数据的正态球形分布转变为特定的椭圆形状。对IMU的陀螺仪和加速度计数据集进行分类和回归,利用监督学习方法进行故障诊断。我们通过不同的学习算法来分析所提出的方法的性能。为了验证该诊断方法的性能,在六轴飞行器上进行了各种螺旋桨损坏情况的地面实验。然后,通过分析故障位置和程度的准确性,验证了数据驱动故障诊断方法的适用性。
{"title":"Data-Driven Diagnosis of Multicopter Thrust Fault Using Supervised Learning with Inertial Sensors","authors":"Taegyun Kim, Seungkeun Kim, Hyo-Sang Shin","doi":"10.2514/1.i011256","DOIUrl":"https://doi.org/10.2514/1.i011256","url":null,"abstract":"This study proposes a data-driven fault diagnosis for multicopter unmanned aerial vehicles that uses the principal direction vector of inertial measurement unit (IMU) sensor signals calculated by principal component analysis. The main idea comes from the fact that a normal sphere-shaped distribution of the sensor data changes to a specific elliptical shape under a certain thrust fault situation. The fault diagnosis is based on classification and regression using supervised learning with the gyroscope and accelerometer datasets of an IMU. We analyze the performance of the proposed approach by depending on different learning algorithms. To verify the diagnostic performance, ground experiments with a hexacopter on the gimbaled jig are performed for various cases of damaged propellers. Then, the applicability of the proposed data-driven fault diagnosis is confirmed by analyzing the accuracy of the fault’s location and degree.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"47 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136371337","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}
引用次数: 0
Dynamic Targeting to Improve Earth Science Missions 动态瞄准改进地球科学任务
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011233
Alberto Candela, Jason Swope, Steve A. Chien
Dynamic targeting (DT) is an emerging concept in which data from a lookahead instrument are used to intelligently reconfigure and point a primary instrument to enhance science return. For example, in the smart ice hunting radar (Smart Ice Cloud Sensing project), a forward-looking radiometer is used to detect deep convective ice storms, which are then targeted using a radar. In other concepts, forward-looking sensors are used to detect clouds so that a primary sensor can avoid them. To this end, we have developed several algorithms from operations research and an artificial intelligence/heuristic search to point/reconfigure the dynamic instrument. We present simulation studies of DT for these concepts and benchmark these algorithms to show that DT is a powerful tool with the potential to significantly improve instrument science yield.
动态定位(DT)是一个新兴的概念,它使用前瞻性仪器的数据来智能地重新配置和指向主要仪器,以提高科学回报。例如,在智能寻冰雷达(智能冰云传感项目)中,使用前视辐射计探测深层对流冰暴,然后使用雷达定位。在其他概念中,前视传感器用于探测云,以便主传感器可以避开它们。为此,我们从运筹学和人工智能/启发式搜索中开发了几种算法来指向/重新配置动态仪器。我们对这些概念进行了DT的模拟研究,并对这些算法进行了基准测试,以表明DT是一个强大的工具,具有显着提高仪器科学产量的潜力。
{"title":"Dynamic Targeting to Improve Earth Science Missions","authors":"Alberto Candela, Jason Swope, Steve A. Chien","doi":"10.2514/1.i011233","DOIUrl":"https://doi.org/10.2514/1.i011233","url":null,"abstract":"Dynamic targeting (DT) is an emerging concept in which data from a lookahead instrument are used to intelligently reconfigure and point a primary instrument to enhance science return. For example, in the smart ice hunting radar (Smart Ice Cloud Sensing project), a forward-looking radiometer is used to detect deep convective ice storms, which are then targeted using a radar. In other concepts, forward-looking sensors are used to detect clouds so that a primary sensor can avoid them. To this end, we have developed several algorithms from operations research and an artificial intelligence/heuristic search to point/reconfigure the dynamic instrument. We present simulation studies of DT for these concepts and benchmark these algorithms to show that DT is a powerful tool with the potential to significantly improve instrument science yield.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"69 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134995916","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}
引用次数: 0
Attitude Takeover Control of Failed Spacecraft via Leader–Followers Adaptive Cooperative Game 基于领导-追随者自适应合作博弈的失效航天器姿态接管控制
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011242
Huai-Ning Wu, Mi Wang
In this paper, the problem of microsatellites-based adaptive cooperative game attitude takeover control for a failed spacecraft is investigated. Specifically, a manned microsatellite (leader) and a team of autonomous microsatellites (followers) are ordered to cooperate to complete the attitude control task in an optimal way, in which the control strategy and the cost function (or intent) of the leader are unknown to the followers. Based on the differential game (DG) theory, the microsatellites-based attitude takeover control problem is formulated as a cooperative DG, in which each microsatellite has the individual cost function. A key problem is that the followers must infer the leader’s intent first, that is, retrieve the weighting matrix of the cost function of the leader. To achieve this, a composite adaptive law is introduced for each follower to estimate the feedback gain matrix of the leader by using system state data and the cost functions of other followers; based on this, the leader’s intent is inferred online by minimizing a residual error. Then, the cooperative game control law of each follower is designed by itself, and the Pareto equilibrium of the DG system is achieved. Finally, the effectiveness of the proposed leader–followers adaptive cooperative game control method is verified by a simulation study.
研究了失效航天器下基于微卫星的自适应协同博弈姿态接管控制问题。具体来说,一个载人微卫星(领导者)和一个自主微卫星(追随者)团队被命令以最优方式合作完成姿态控制任务,其中领导者的控制策略和成本函数(或意图)是被追随者不知道的。基于微分对策(DG)理论,将基于微卫星的姿态接管控制问题表述为一个合作DG,其中每个微卫星都有各自的代价函数。一个关键的问题是,追随者必须首先推断领导者的意图,即检索领导者成本函数的权重矩阵。为此,对每个follower引入复合自适应律,利用系统状态数据和其他follower的代价函数估计leader的反馈增益矩阵;在此基础上,通过最小化残差在线推断领导者的意图。然后,自行设计各follower的合作博弈控制律,实现DG系统的Pareto均衡。最后,通过仿真研究验证了所提出的领导-追随者自适应合作博弈控制方法的有效性。
{"title":"Attitude Takeover Control of Failed Spacecraft via Leader–Followers Adaptive Cooperative Game","authors":"Huai-Ning Wu, Mi Wang","doi":"10.2514/1.i011242","DOIUrl":"https://doi.org/10.2514/1.i011242","url":null,"abstract":"In this paper, the problem of microsatellites-based adaptive cooperative game attitude takeover control for a failed spacecraft is investigated. Specifically, a manned microsatellite (leader) and a team of autonomous microsatellites (followers) are ordered to cooperate to complete the attitude control task in an optimal way, in which the control strategy and the cost function (or intent) of the leader are unknown to the followers. Based on the differential game (DG) theory, the microsatellites-based attitude takeover control problem is formulated as a cooperative DG, in which each microsatellite has the individual cost function. A key problem is that the followers must infer the leader’s intent first, that is, retrieve the weighting matrix of the cost function of the leader. To achieve this, a composite adaptive law is introduced for each follower to estimate the feedback gain matrix of the leader by using system state data and the cost functions of other followers; based on this, the leader’s intent is inferred online by minimizing a residual error. Then, the cooperative game control law of each follower is designed by itself, and the Pareto equilibrium of the DG system is achieved. Finally, the effectiveness of the proposed leader–followers adaptive cooperative game control method is verified by a simulation study.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"180 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136371512","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}
引用次数: 0
Coordinating Team Tactics for Swarm-Versus-Swarm Adversarial Games 群对群对抗性游戏的协调团队策略
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011226
Laura G. Strickland, Matthew C. Gombolay
Although swarms of unmanned aerial vehicles have received much attention in the last few years, adversarial swarms (that is, competitive swarm-versus-swarm games) have been less well studied. In this paper, we demonstrate a deep reinforcement learning method to train a policy of fixed-wing aircraft agents to leverage hand-scripted tactics to exploit force concentration advantage and within-team coordination opportunities to destroy, or destroy, as many opponent team members as possible while preventing teammates from being attrited. The efficacy of agents using the policy network trained using the proposed method outperform teams utilizing only one of the handcrafted baseline tactics in [Formula: see text]-vs-[Formula: see text] engagements for [Formula: see text] as small as two and as large as 64 as well as learner teams trained to vary their yaw rate actions, even when the trained team’s agents’ sensor range and teammate partnership possibility is constrained.
尽管在过去几年中,无人驾驶飞行器群受到了广泛关注,但对抗性蜂群(即竞争性蜂群对抗蜂群游戏)的研究却很少。在本文中,我们展示了一种深度强化学习方法来训练固定翼飞机代理策略,以利用手写脚本战术来利用力量集中优势和团队内协调机会来摧毁或摧毁尽可能多的对手团队成员,同时防止队友被消耗。使用该方法训练的策略网络的代理的效率优于只使用[公式:见文]中手工制作的基线策略中的一种的团队-vs-[公式:见文]约定(小至2个,大至64个)以及训练以改变其偏航率行动的学习者团队,即使训练团队的代理的传感器范围和队友合作可能性受到限制。
{"title":"Coordinating Team Tactics for Swarm-Versus-Swarm Adversarial Games","authors":"Laura G. Strickland, Matthew C. Gombolay","doi":"10.2514/1.i011226","DOIUrl":"https://doi.org/10.2514/1.i011226","url":null,"abstract":"Although swarms of unmanned aerial vehicles have received much attention in the last few years, adversarial swarms (that is, competitive swarm-versus-swarm games) have been less well studied. In this paper, we demonstrate a deep reinforcement learning method to train a policy of fixed-wing aircraft agents to leverage hand-scripted tactics to exploit force concentration advantage and within-team coordination opportunities to destroy, or destroy, as many opponent team members as possible while preventing teammates from being attrited. The efficacy of agents using the policy network trained using the proposed method outperform teams utilizing only one of the handcrafted baseline tactics in [Formula: see text]-vs-[Formula: see text] engagements for [Formula: see text] as small as two and as large as 64 as well as learner teams trained to vary their yaw rate actions, even when the trained team’s agents’ sensor range and teammate partnership possibility is constrained.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"112 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135373357","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}
引用次数: 0
Simultaneous Motion Replanning and Gravity Model Refinement near Small Solar System Bodies 太阳系小天体同步运动重规划和重力模型改进
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-11-01 DOI: 10.2514/1.i011200
Aditya Savio Paul, Michael Otte
Strategic missions to orbit celestial bodies have primarily considered spacecraft trajectories as a two-step process: capture of the spacecraft within the gravitational influence of the body, followed by in-orbit maneuvers. Moreover, a priori maneuver planning approaches using Earth-based measurements tend to generate motion plans that have little scope of replanning, especially when the spacecraft is in the body’s vicinity. Fine-grained motion plans that respond to mission conditions require a detailed understanding of the gravitational forces around the body, which can provide essential information about the body. Our research focuses on a problem variant where the orbital maneuvers are designed to continually refine the onboard gravitational model of the body while simultaneously using the model to perform increasingly smoother orbital maneuvers. We develop a receding horizon approach. Starting with a (low-fidelity) gravity model created from Earth-based observations, the gravity model is continually updated as the spacecraft experiences varying gravitational forces. The updated model is simultaneously and continually used to replan the craft’s trajectory, ensuring that successive maneuvers respect the most up-to-date gravity model. The motion plan eventually attains a near-stable orbital motion. Such an approach has the potential to expand to autonomous missions to improve the mapping and exploration of smaller bodies.
绕天体轨道运行的战略任务主要将航天器轨迹视为一个两步过程:在天体引力影响下捕获航天器,然后进行在轨机动。此外,使用地面测量的先验机动规划方法倾向于生成很少有重新规划范围的运动计划,特别是当航天器在物体附近时。对任务条件做出反应的细粒度运动计划需要对物体周围的引力有详细的了解,这可以提供关于物体的基本信息。我们的研究重点是一个问题变体,其中轨道机动的设计是为了不断完善机载重力模型,同时使用该模型来执行越来越平滑的轨道机动。我们发展后退视界方法。从基于地球的观测创建的(低保真)重力模型开始,重力模型随着航天器经历不同的引力而不断更新。更新后的模型被同时不断地用于重新规划飞船的轨道,确保连续的机动符合最新的重力模型。运动计划最终达到接近稳定的轨道运动。这种方法有可能扩展到自主任务,以改善对较小天体的测绘和探索。
{"title":"Simultaneous Motion Replanning and Gravity Model Refinement near Small Solar System Bodies","authors":"Aditya Savio Paul, Michael Otte","doi":"10.2514/1.i011200","DOIUrl":"https://doi.org/10.2514/1.i011200","url":null,"abstract":"Strategic missions to orbit celestial bodies have primarily considered spacecraft trajectories as a two-step process: capture of the spacecraft within the gravitational influence of the body, followed by in-orbit maneuvers. Moreover, a priori maneuver planning approaches using Earth-based measurements tend to generate motion plans that have little scope of replanning, especially when the spacecraft is in the body’s vicinity. Fine-grained motion plans that respond to mission conditions require a detailed understanding of the gravitational forces around the body, which can provide essential information about the body. Our research focuses on a problem variant where the orbital maneuvers are designed to continually refine the onboard gravitational model of the body while simultaneously using the model to perform increasingly smoother orbital maneuvers. We develop a receding horizon approach. Starting with a (low-fidelity) gravity model created from Earth-based observations, the gravity model is continually updated as the spacecraft experiences varying gravitational forces. The updated model is simultaneously and continually used to replan the craft’s trajectory, ensuring that successive maneuvers respect the most up-to-date gravity model. The motion plan eventually attains a near-stable orbital motion. Such an approach has the potential to expand to autonomous missions to improve the mapping and exploration of smaller bodies.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"70 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134995915","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}
引用次数: 0
Identification of Uncertain Parameter in Flight Vehicle Using Physics-Informed Deep Learning 基于物理信息深度学习的飞行器不确定参数识别
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-10-26 DOI: 10.2514/1.i011269
Kyung-Mi Na, Chang-Hun Lee
This paper presents the estimation method for uncertain parameters in flight vehicles, especially missile systems, based on physics-informed neural networks (PINNs) augmented with a novel integration-based loss. The proposed method identifies four types of structured uncertainty: burnout time, rocket motor tilt angle, location of the center of pressure, and control fin bias, which significantly affect the missile performance. In the estimation framework, as neural networks (NNs) are updated, these uncertainties are also identified simultaneously because they are also included in the structure of NNs. After testing 100 simulation data, the average estimation errors are within 1% of the mean value for each type of uncertainty. The methodology is able to identify the parameters despite noise corruption in the time-series data. Compared with the conventional PINNs, adding the new loss based on the integration of differential equations yields a more reliable estimation performance for all types of uncertainty. This approach can be effective for complex systems and ill-posed inverse problems, which makes it applicable to other aerospace systems.
本文提出了一种基于物理信息神经网络(pinn)和一种新的基于积分的损失的飞行器,特别是导弹系统中不确定参数的估计方法。该方法识别了四种结构不确定性:燃尽时间、火箭发动机倾斜角、压力中心位置和控制翼偏差,这四种结构不确定性对导弹性能有显著影响。在估计框架中,随着神经网络的更新,这些不确定性也被同时识别,因为它们也包含在神经网络的结构中。在测试了100个模拟数据后,每种不确定度的平均估计误差都在平均值的1%以内。该方法能够在时间序列数据噪声损坏的情况下识别参数。与传统的pinn相比,加入基于微分方程积分的新损失对所有类型的不确定性具有更可靠的估计性能。该方法对复杂系统和不适定逆问题具有较好的求解效果,适用于其他航空航天系统。
{"title":"Identification of Uncertain Parameter in Flight Vehicle Using Physics-Informed Deep Learning","authors":"Kyung-Mi Na, Chang-Hun Lee","doi":"10.2514/1.i011269","DOIUrl":"https://doi.org/10.2514/1.i011269","url":null,"abstract":"This paper presents the estimation method for uncertain parameters in flight vehicles, especially missile systems, based on physics-informed neural networks (PINNs) augmented with a novel integration-based loss. The proposed method identifies four types of structured uncertainty: burnout time, rocket motor tilt angle, location of the center of pressure, and control fin bias, which significantly affect the missile performance. In the estimation framework, as neural networks (NNs) are updated, these uncertainties are also identified simultaneously because they are also included in the structure of NNs. After testing 100 simulation data, the average estimation errors are within 1% of the mean value for each type of uncertainty. The methodology is able to identify the parameters despite noise corruption in the time-series data. Compared with the conventional PINNs, adding the new loss based on the integration of differential equations yields a more reliable estimation performance for all types of uncertainty. This approach can be effective for complex systems and ill-posed inverse problems, which makes it applicable to other aerospace systems.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134907266","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}
引用次数: 0
Leveraging Machine Learning for Generating and Utilizing Motion Primitives in Adversarial Environments 利用机器学习在对抗环境中生成和利用运动原语
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-10-26 DOI: 10.2514/1.i011283
Zachary C. Goddard, Rithesh Rajasekar, Madhumita Mocharla, Garrett Manaster, Kyle Williams, Anirban Mazumdar
Motion primitives enable fast planning for complex and dynamic environments. Adversarial environments pose a particularly challenging and unpredictable scenario. Motion-primitive-based planners have the potential to provide benefit in these types of environments. The key challenge is to design a library of maneuvers that effectively capture the necessary capabilities of the vehicle. This work presents a primitive-based game tree search to solve adversarial games in continuous state and action spaces and applies a reinforcement learning framework to autonomously generate effective primitives for the given task. The results demonstrate the ability of the learning framework to produce maneuvers necessary for competing against adversaries. Furthermore, we propose a method for learning a model to estimate the state-dependent value of each motion primitives and demonstrate how to incorporate this model to increase planning performance under time constraints. Additionally, we compare our primitive-based algorithm against forward simulated methods from existing literature and highlight the benefits of motion primitives.
运动原语支持对复杂和动态环境进行快速规划。对抗性环境构成了一个特别具有挑战性和不可预测的场景。基于运动原始的规划器有可能在这些类型的环境中提供好处。关键的挑战是设计一个机动库,有效地捕捉车辆的必要能力。这项工作提出了一个基于原语的游戏树搜索来解决连续状态和动作空间中的对抗游戏,并应用强化学习框架为给定任务自主生成有效的原语。结果表明,学习框架能够产生与对手竞争所需的机动。此外,我们提出了一种学习模型的方法来估计每个运动原语的状态依赖值,并演示了如何结合该模型来提高时间约束下的规划性能。此外,我们将基于原语的算法与现有文献中的正向模拟方法进行了比较,并强调了运动原语的优点。
{"title":"Leveraging Machine Learning for Generating and Utilizing Motion Primitives in Adversarial Environments","authors":"Zachary C. Goddard, Rithesh Rajasekar, Madhumita Mocharla, Garrett Manaster, Kyle Williams, Anirban Mazumdar","doi":"10.2514/1.i011283","DOIUrl":"https://doi.org/10.2514/1.i011283","url":null,"abstract":"Motion primitives enable fast planning for complex and dynamic environments. Adversarial environments pose a particularly challenging and unpredictable scenario. Motion-primitive-based planners have the potential to provide benefit in these types of environments. The key challenge is to design a library of maneuvers that effectively capture the necessary capabilities of the vehicle. This work presents a primitive-based game tree search to solve adversarial games in continuous state and action spaces and applies a reinforcement learning framework to autonomously generate effective primitives for the given task. The results demonstrate the ability of the learning framework to produce maneuvers necessary for competing against adversaries. Furthermore, we propose a method for learning a model to estimate the state-dependent value of each motion primitives and demonstrate how to incorporate this model to increase planning performance under time constraints. Additionally, we compare our primitive-based algorithm against forward simulated methods from existing literature and highlight the benefits of motion primitives.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"47 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135016607","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}
引用次数: 0
Prefetch and Push Method of Flight Information Based on Migration Workflow 基于迁移工作流的航班信息预取与推送方法
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-10-24 DOI: 10.2514/1.i011197
Tao Xu, Youchao Sun
As the architecture of aircraft cockpit panels becomes more complicated and more flight data are placed onto the panels, trainee pilots require more time during flight training to learn and comprehend flight information. This problem lengthens flight training time and raises costs. This paper proposes a mechanism for prefetching and pushing flight information to facilitate flight training for trainee pilots. This paper addresses the challenges of a high quantity of data and the chaotic time-series relationship between distinct data in flight sequence data by building a migration workflow model in the aircraft cockpit environment and getting flight data with shorter time intervals. Then the flight data are input into the Multilayer Perceptron Long Short-Term Memory (MLP-LSTM) prediction algorithm, which generates the prompt operation information and prediction information by analyzing the current flight data and predicting flight data of next stage. A case study of the takeoff stage is given. The experimental results of the prediction algorithm are given, which prove that the time-series flight data refined by the migration workflow model and MLP-LSTM algorithm have a better prediction effect compared with the LSTM algorithm.
随着飞机座舱仪表板结构的复杂化,大量的飞行数据被放置在仪表板上,受训飞行员在飞行训练中需要更多的时间来学习和理解飞行信息。这个问题延长了飞行训练时间,增加了成本。本文提出了一种预获取和推送飞行信息的机制,以方便见习飞行员的飞行训练。本文通过建立飞机座舱环境下的迁移工作流模型,以较短的时间间隔获取飞行数据,解决了飞行序列数据量大、不同数据间时间序列关系混乱等问题。然后将飞行数据输入多层感知机长短期记忆(Multilayer Perceptron Long - short - Memory, MLP-LSTM)预测算法,该算法通过分析当前飞行数据并预测下一阶段的飞行数据,生成提示操作信息和预测信息。给出了起飞阶段的实例分析。给出了预测算法的实验结果,证明了迁移工作流模型和MLP-LSTM算法对时间序列飞行数据的预测效果优于LSTM算法。
{"title":"Prefetch and Push Method of Flight Information Based on Migration Workflow","authors":"Tao Xu, Youchao Sun","doi":"10.2514/1.i011197","DOIUrl":"https://doi.org/10.2514/1.i011197","url":null,"abstract":"As the architecture of aircraft cockpit panels becomes more complicated and more flight data are placed onto the panels, trainee pilots require more time during flight training to learn and comprehend flight information. This problem lengthens flight training time and raises costs. This paper proposes a mechanism for prefetching and pushing flight information to facilitate flight training for trainee pilots. This paper addresses the challenges of a high quantity of data and the chaotic time-series relationship between distinct data in flight sequence data by building a migration workflow model in the aircraft cockpit environment and getting flight data with shorter time intervals. Then the flight data are input into the Multilayer Perceptron Long Short-Term Memory (MLP-LSTM) prediction algorithm, which generates the prompt operation information and prediction information by analyzing the current flight data and predicting flight data of next stage. A case study of the takeoff stage is given. The experimental results of the prediction algorithm are given, which prove that the time-series flight data refined by the migration workflow model and MLP-LSTM algorithm have a better prediction effect compared with the LSTM algorithm.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"26 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135266574","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}
引用次数: 0
Improved Nonlinear Statistical Photocalibration of Photodetectors Without Calibrated Light Sources 无标定光源光电探测器的改进非线性统计光定标
4区 工程技术 Q2 ENGINEERING, AEROSPACE Pub Date : 2023-10-18 DOI: 10.2514/1.i011211
Stephen C. Cain
The calibration of charge coupled device arrays is commonly conducted using dark frames. Nonabsolute calibration techniques only measure the relative response of the detectors. A recent attempt at creating a procedure for calibrating a photodetector using the underlying Poisson nature of the photodetection statistics that relied on a nonlinear model was shown to be successful but was highly susceptible to the readout noise present in the measurement. This effort produced the nonlinear statistical nonuniformity calibration (NLSNUC) algorithm, which demonstrated an ability to better model the output of photodetector array elements than similar techniques that relied on a linear model. In this paper, a modified three-point NLSNUC photocalibration procedure is defined that requires only first and second moments of the measurements and allows the response to be modeled using a nonlinear function over the dynamic range of the detector. The modified NLSNUC technique is applied to image data containing a light source with a known output power. Estimates of the number of photoelectrons measured by the detector are shown to be superior to those obtained by the original NLSNUC algorithm as well as other statistical calibration techniques that do not utilize a calibrated light source.
电荷耦合器件阵列的校准通常使用暗帧进行。非绝对校准技术只测量探测器的相对响应。最近的一项尝试是,利用光电探测统计的潜在泊松特性(依赖于非线性模型)创建一种校准光电探测器的程序,该程序被证明是成功的,但极易受到测量中存在的读出噪声的影响。这项工作产生了非线性统计非均匀性校准(NLSNUC)算法,该算法证明了比依赖线性模型的类似技术更好地模拟光电探测器阵列元素输出的能力。在本文中,定义了一种改进的三点NLSNUC光校准程序,该程序只需要测量的第一和第二时刻,并允许使用检测器动态范围内的非线性函数对响应进行建模。将改进的NLSNUC技术应用于含有已知输出功率光源的图像数据。探测器测量的光电子数的估计值优于原始NLSNUC算法以及其他不使用校准光源的统计校准技术。
{"title":"Improved Nonlinear Statistical Photocalibration of Photodetectors Without Calibrated Light Sources","authors":"Stephen C. Cain","doi":"10.2514/1.i011211","DOIUrl":"https://doi.org/10.2514/1.i011211","url":null,"abstract":"The calibration of charge coupled device arrays is commonly conducted using dark frames. Nonabsolute calibration techniques only measure the relative response of the detectors. A recent attempt at creating a procedure for calibrating a photodetector using the underlying Poisson nature of the photodetection statistics that relied on a nonlinear model was shown to be successful but was highly susceptible to the readout noise present in the measurement. This effort produced the nonlinear statistical nonuniformity calibration (NLSNUC) algorithm, which demonstrated an ability to better model the output of photodetector array elements than similar techniques that relied on a linear model. In this paper, a modified three-point NLSNUC photocalibration procedure is defined that requires only first and second moments of the measurements and allows the response to be modeled using a nonlinear function over the dynamic range of the detector. The modified NLSNUC technique is applied to image data containing a light source with a known output power. Estimates of the number of photoelectrons measured by the detector are shown to be superior to those obtained by the original NLSNUC algorithm as well as other statistical calibration techniques that do not utilize a calibrated light source.","PeriodicalId":50260,"journal":{"name":"Journal of Aerospace Information Systems","volume":"875 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135884630","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}
引用次数: 0
期刊
Journal of Aerospace Information Systems
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1