Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning framework”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRS2020

Building a standardized Observing System Simulation Experiment (OSSE) framework for Mars

We advocate that the Decadal Survey recommends the NASA Science Mission Directorate to develop a rigorous Observing System Simulation Experiment (OSSE) framework for Mars, to optimize future atmospheric observations. Atmospheric conditions on Mars are a potential hazard source for landing missions. Errors in the estimates of atmospheric density profiles, inadequate knowledge of wind vertical structure and dust concentration as a function of height are likely causes of uncertainty at the landing site on the order of kilometers. An operational real-time weather forecasting capability for Mars would reduce such uncertainties, carrying enormous benefits to future robotic missions, and would be an invaluable prerequisite for human missions.A real-time forecasting capability relies upon three fundamental components: a critical mass of observing systems, a data assimilation system (DAS), and a global forecast model. The DAS allows the model to ingest the data effectively, optimizing the observational information content,and transforming them into a gridded representation of the atmosphere at a given time, called an ‘analysis’. The analysis is the best estimate of the atmospheric state for that time, and also represents a set of ‘initial conditions’ from which a global model can be initialized, to predict a future state of the atmosphere. The connection between analysis and forecast represents the foundation of modern weather forecasting. However, from the point of view of a forecast system,not all observations are equally impactful, partially because of the problem of “observational error correlation”, one important research topic in data assimilation development. For the Earth, partly due to the spontaneous and deregulated development of observations and forecast capabilities worldwide for more than half a century,the use of observations in contemporary operational forecast systems is suboptimal, with many potentially useful data being underutilized. On the contrary, Mars atmospheric scientists are in the unique situation of designing the next-generation observing systems by learning from the experience gathered on the Earth, so as to assure that the future instruments are specifically optimized to give the maximum benefit to a future weather forecast capability.An immensely powerful tool that has been firmly established by atmospheric scientists on the Earth is represented by a properly designed OSSE framework. A realistic OSSE framework cannot only quantify the benefit of future data types, be them surface based or space borne, but can also help design and optimize an entire observational network. Furthermore, OSSEs can provide deep insights into an atmosphere’s behavior, by addressing conceptual problems of its intrinsic predictability and delineating the regions or features of the atmosphere which are more sensitive to additional data and would benefit from a denser sampling. The difficulties posed by OSSEs are fundamentally different for Earth and Mars. For Earth, the enormous data volume imposes a tremendous constraint on any innovation in the observing systems: it is very hard for a single sensor to impact the skill. For Mars, the problem is the opposite: almost any additional instrument will exert some impact. However, OSSEs can help to evaluate the cost/benefit for every sensor and suggest optimal data configuration and density.The purpose of this white paper is to provide an introduction to a rigorously designed OSSE framework, explain the underlying problems and challenges, and engage the Mars community to collaborate with Earth Atmospheric scientists in order to develop a joint-OSSE framework for Mars with the largest consensual basis possible. An OSSE infrastructure would increase the understanding of the Martian atmosphere, would help NASA to optimize instrument specifications and orbit choice, providing the maximium benefit for a given expenditure of resources, and could even help establishing a roadmap for a future real-time weather forecasting capability.

Oreste Reale↗
NASA NTRS1992

Self-organization via active exploration in robotic applications

We describe a neural network based robotic system. Unlike traditional robotic systems, our approach focussed on non-stationary problems. We indicate that self-organization capability is necessary for any system to operate successfully in a non-stationary environment. We suggest that self-organization should be based on an active exploration process. We investigated neural architectures having novelty sensitivity, selective attention, reinforcement learning, habit formation, flexible criteria categorization properties and analyzed the resulting behavior (consisting of an intelligent initiation of exploration) by computer simulations. While various computer vision researchers acknowledged recently the importance of active processes (Swain and Stricker, 1991), the proposed approaches within the new framework still suffer from a lack of self-organization (Aloimonos and Bandyopadhyay, 1987; Bajcsy, 1988). A self-organizing, neural network based robot (MAVIN) has been recently proposed (Baloch and Waxman, 1991). This robot has the capability of position, size rotation invariant pattern categorization, recognition and pavlovian conditioning. Our robot does not have initially invariant processing properties. The reason for this is the emphasis we put on active exploration. We maintain the point of view that such invariant properties emerge from an internalization of exploratory sensory-motor activity. Rather than coding the equilibria of such mental capabilities, we are seeking to capture its dynamics to understand on the one hand how the emergence of such invariances is possible and on the other hand the dynamics that lead to these invariances. The second point is crucial for an adaptive robot to acquire new invariances in non-stationary environments, as demonstrated by the inverting glass experiments of Helmholtz. We will introduce Pavlovian conditioning circuits in our future work for the precise objective of achieving the generation, coordination, and internalization of sequence of actions.

Ogmen, H.↗
NASA NTRS2017

A Machine Learning Concept for DTN Routing

This paper discusses the concept and architecture of a machine learning based router for delay tolerant space networks. The techniques of reinforcement learning and Bayesian learning are used to supplement the routing decisions of the popular Contact Graph Routing algorithm. An introduction to the concepts of Contact Graph Routing, Q-routing and Naive Bayes classification are given. The development of an architecture for a cross-layer feedback framework for DTN (Delay-Tolerant Networking) protocols is discussed. Finally, initial simulation setup and results are given.

Delay Tolerant Networks↗
NASA NTRSDate not supplied

Biological Research and Space Health Enabled by Machine Learning to Support Deep Space Missions

A key science goal of the NASA “Moon to Mars” campaign is to understand how biology responds to the Lunar, Martian, and deep space environments in order to advance fundamental knowledge, reduce risk, and support safe, productive human space missions. Through the powerful emerging approaches of artificial intelligence (AI) and machine learning (ML), a paradigm shift has begun in biomedical science and engineered astronaut health systems, to enable Earth independence and autonomy of mission operations. Here we present an overview of AI/ML architecture to support deep space mission goals, developed with leaders in the field. First, we focus on the fundamental biological research that supports our understanding of physiological responses to spaceflight, and we describe current efforts to support AI/ML research including data standardization and data engineering through maximally open and FAIR (findable, accessible, interoperable, reusable) databases and the generation of AI-ready datasets for reuse and analysis. We also discuss remote data management frameworks for research data as well as environmental and health data that are generated during deep space missions. We highlight several research projects that leverage data standardization and management for fundamental biological discovery to uncover the complex effects of space travel on living systems. Next, we provide an overview of cutting-edge AI/ML approaches that can be integrated to support remote monitoring and analysis during deep space missions, including generative models and large language models to learn the underlying biomedical patterns and predict outcomes or answer questions during off world medical scenarios. We also describe current AI/ML methods to support this research and monitoring through automated cloud-based labs which enable limited human intervention and closed-loop experimentation in remote settings. These labs could support mission autonomy by analyzing environmental data streams, and would be facilitated through in situ analytics capabilities to avoid sending large raw data files through low bandwidth communications. Finally, in the context of deep space missions with limited communications or access to medical advice from Earth, we describe a solution for integrated, real-time mission biomonitoring across hierarchical levels from continuous environmental monitoring, to wearables and point-of-care devices, to molecular and physiological monitoring. We introduce a precision space health system that will ensure that the future of space health is predictive, preventative, participatory and personalized.

artificial intelligence↗
NASA NTRS2014

Activate/Inhibit KGCS Gateway via Master Console EIC Pad-B Display

My internship consisted of two major projects for the Launch Control System.The purpose of the first project was to implement the Application Control Language (ACL) to Activate Data Acquisition (ADA) and to Inhibit Data Acquisition (IDA) the Kennedy Ground Control Sub-Systems (KGCS) Gateway, to update existing Pad-B End Item Control (EIC) Display to program the ADA and IDA buttons with new ACL, and to test and release the ACL Display.The second project consisted of unit testing all of the Application Services Framework (ASF) by March 21st. The XmlFileReader was unit tested and reached 100 coverage. The XmlFileReader class is used to grab information from XML files and use them to initialize elements in the other framework elements by using the Xerces C++ XML Parser; which is open source commercial off the shelf software. The ScriptThread was also tested. ScriptThread manages the creation and activation of script threads. A large amount of the time was used in initializing the environment and learning how to set up unit tests and getting familiar with the specific segments of the project that were assigned to us.

Computer Programming↗
NASA NTRS2014

MAVEN Information Security Governance, Risk Management, and Compliance (GRC): Lessons Learned

As the first interplanetary mission managed by the NASA Goddard Space Flight Center, the Mars Atmosphere and Volatile EvolutioN (MAVEN) had three IT security goals for its ground system: COMPLIANCE, (IT) RISK REDUCTION, and COST REDUCTION. In a multiorganizational environment in which government, industry and academia work together in support of the ground system and mission operations, information security governance, risk management, and compliance (GRC) becomes a challenge as each component of the ground system has and follows its own set of IT security requirements. These requirements are not necessarily the same or even similar to each other's, making the auditing of the ground system security a challenging feat. A combination of standards-based information security management based on the National Institute of Standards and Technology (NIST) Risk Management Framework (RMF), due diligence by the Mission's leadership, and effective collaboration among all elements of the ground system enabled MAVEN to successfully meet NASA's requirements for IT security, and therefore meet Federal Information Security Management Act (FISMA) mandate on the Agency. Throughout the implementation of GRC on MAVEN during the early stages of the mission development, the Project faced many challenges some of which have been identified in this paper. The purpose of this paper is to document these challenges, and provide a brief analysis of the lessons MAVEN learned. The historical information documented herein, derived from an internal pre-launch lessons learned analysis, can be used by current and future missions and organizations implementing and auditing GRC.

FISMA↗
NASA NTRS2022

Classifying Unidentified X-Ray Sources in the Chandra Source Catalog Using A Multiwavelength Machine-Learning Approach

The rapid increase in serendipitous X-ray source detections requires the development of novel approaches to efficiently explore the nature of X-ray sources. If even a fraction of these sources could be reliably classified, it would enable population studies for various astrophysical source types on a much larger scale than currently possible. Classification of large numbers of sources from multiple classes characterized by multiple properties (features) must be done automatically and supervised machine learning (ML) seems to provide the only feasible approach. We perform classification of Chandra Source Catalog version 2.0 (CSCv2) sources to explore the potential of the ML approach and identify various biases, limitations, and bottlenecks that present themselves in these kinds of studies. We establish the framework and present a flexible and expandable Python pipeline, which can be used and improved by others. We also release the training data set of 2941 X-ray sources with confidently established classes. In addition to providing probabilistic classifications of 66,369 CSCv2 sources (21% of the entire CSCv2 catalog), we perform several narrower-focused case studies (high-mass X-ray binary candidates and X-ray sources within the extent of the H.E.S.S. TeV sources) to demonstrate some possible applications of our ML approach. We also discuss future possible modifications of the presented pipeline, which are expected to lead to substantial improvements in classification confidences.

Hui Yang↗
NASA NTRS2004

Earth Science Education Plan: Inspire the Next Generation of Earth Explorers

The Education Enterprise Strategy, the expanding knowledge of how people learn, and the community-wide interest in revolutionizing Earth and space science education have guided us in developing this plan for Earth science education. This document builds on the success of the first plan for Earth science education published in 1996; it aligns with the new framework set forth in the NASA Education Enterprise Strategy; it recognizes the new educational opportunities resulting from research programs and flight missions; and it builds on the accomplishments th'at the Earth Science Enterprise has made over the last decade in studying Earth as a system. This document embodies comprehensive, practicable plans for inspiring our children; providing educators with the tools they need to teach science, technology, engineering, and mathematics (STEM); and improving our citizens' scientific literacy. This plan describes an approach to systematically sharing knowledge; developing the most effective mechanisms to achieve tangible, lasting results; and working collaboratively to catalyze action at a scale great enough to ensure impact nationally and internationally. This document will evolve and be periodically reviewed in partnership with the Earth science education community.

Source record↗
NASA NTRS2011

Onboard Nonlinear Engine Sensor and Component Fault Diagnosis and Isolation Scheme

A method detects and isolates in-flight sensor, actuator, and component faults for advanced propulsion systems. In sharp contrast to many conventional methods, which deal with either sensor fault or component fault, but not both, this method considers sensor fault, actuator fault, and component fault under one systemic and unified framework. The proposed solution consists of two main components: a bank of real-time, nonlinear adaptive fault diagnostic estimators for residual generation, and a residual evaluation module that includes adaptive thresholds and a Transferable Belief Model (TBM)-based residual evaluation scheme. By employing a nonlinear adaptive learning architecture, the developed approach is capable of directly dealing with nonlinear engine models and nonlinear faults without the need of linearization. Software modules have been developed and evaluated with the NASA C-MAPSS engine model. Several typical engine-fault modes, including a subset of sensor/actuator/components faults, were tested with a mild transient operation scenario. The simulation results demonstrated that the algorithm was able to successfully detect and isolate all simulated faults as long as the fault magnitudes were larger than the minimum detectable/isolable sizes, and no misdiagnosis occurred

Tang, Liang↗
NASA NTRS2024

Terrestrial Proving Ground Capabilities Needed for Lunar In Situ Resource Utilization (ISRU) & Construction Concepts of Operation

Incorporating any new technology or system into a human exploration mission or architecture requires development well in advance of the mission to eliminate technology, cost, and schedule risk concerns. It is often stated that technologies need to be at a Technology Readiness Level (TRL) of 6, i.e. ‘system/subsystem model or prototype demonstration in a relevant environment (ground or space)’, by Authority To Proceed (ATP) or by the Preliminary Design Review (PDR) for the mission at the latest. There are two game changing capabilities for sustained human exploration of space that can have a significant effect on the overall exploration architecture and the technologies and systems included in the architecture. The first game changing capability, known as In Situ Resource Utilization (ISRU), involves the search for, acquisition, and processing of resources on the Moon and Mars into mission consumables and usable products, and the second is the ability to utilize space resources in the construction of roads, structures, and surface infrastructure. ISRU and surface construction capabilities have the potential to greatly reduce the cost and risk of human exploration while enabling sustained lunar surface and commercial operations. However, ISRU and surface construction systems are complex and must operate in extremely harsh environments, with abrasive regolith and pervasive dust, for long-periods of time, with potentially limited opportunities for maintenance and repair by humans. The complexity of these capabilities and operations also means that there are a limited number of companies that can design, build, and operate end-to-end systems on their own. The majority of the technologies being developed for these systems are by small companies and at the component or subsystem level. With the overarching strategy of the United States National Aeronautics and Space Administration (NASA) Space Technology Mission Directorate (STMD) to enable industry to implement ISRU and surface infrastructure for Artemis and space commercialization, it is therefore important to establish processes and capabilities to promote and foster collaborations among large and small companies involved in ISRU and surface infrastructure development. For ISRU and infrastructure systems and capabilities to be used in Artemis missions and future commercial lunar surface operations, a coordinated framework with virtual/physical integration and testing locations, or ‘Proving Grounds’, needs to be established and operated on a regular basis and open to all. This paper will discuss the ISRU and surface construction near and long-term concepts of operations, and review operations and lessons-learned from the previous ISRU analog field tests. From this information, requirements and capabilities will be proposed to support and enable the integration and testing of ISRU and construction systems with industry, academia, and international agencies, as well as what facilities and organizations could help establish these Proving Grounds.

ISRU↗
NASA NTRS2008

NASA's In Space Propulsion Technology Program Accomplishments and Lessons Learned

NASA's In-Space Propulsion Technology (ISPT) Program was managed for 5 years at the NASA MSFC and significant strides were made in the advancement of key transportation technologies that will enable or enhance future robotic science and deep space exploration missions. At the program's inception, a set of technology investment priorities were established using an NASA-wide, mission-driven prioritization process and, for the most part, these priorities changed little - thus allowing a consistent framework in which to fund and manage technology development. Technologies in the portfolio included aerocapture, advanced chemical propulsion, solar electric propulsion, solar sail propulsion, electrodynamic and momentum transfer tethers, and various very advanced propulsion technologies with significantly lower technology readiness. The program invested in technologies that have the potential to revolutionize the robotic exploration of deep space. For robotic exploration and science missions, increased efficiencies of future propulsion systems are critical to reduce overall life-cycle costs and, in some cases, enable missions previously considered impossible. Continued reliance on conventional chemical propulsion alone will not enable the robust exploration of deep space - the maximum theoretical efficiencies have almost been reached and they are insufficient to meet needs for many ambitious science missions currently being considered. By developing the capability to support mid-term robotic mission needs, the program was to lay the technological foundation for travel to nearby interstellar space. The ambitious goals of the program at its inception included supporting the development of technologies that could support all of NASA's missions, both human and robotic. As time went on and budgets were never as high as planned, the scope of the program was reduced almost every year, forcing the elimination of not only the broader goals of the initial program, but also of funding for over half of the technologies in the original portfolio. In addition, the frequency at which the application requirements for the program changed exceeded the development time required to mature technologies: forcing sometimes radical rescoping of research efforts already halfway (or more) to completion. At the end of its fifth year, both the scope and funding of the program were at a minimum despite the program successfully meeting all of it's initial high priority objectives. This paper will describe the program, its requirements, technology portfolio, and technology maturation processes. Also discussed will be the major technology milestones achieved and the lessons learned from managing a $100M+ technology program.

Johnson, Les C.↗
NASA NTRSDate not supplied

Adventures in cFS Unit Testing: Examining the Past to Explain the Present with an Eye toward the Future

An overview of my experiences writing unit tests for various projects with a specific focus on my work unit testing core Flight System (cFS) applications. I recount some of the direct personal experiences I have had that showed me the utility of having done unit testing for my projects. Many of the tips, tricks and pitfalls encountered during my time writing unit tests for the cFS app, CF, are examined. I also compare and contrast my cFS unit testing development with that of a parallel project, in which I write unit tests using RSpec, a testing framework for the Ruby programming language. I impart my complete methodology behind the CF app unit testing effort and the rationale for why I did it that way. Then I give some ideas for how you can do your own unit testing for cFS applications. You will also learn about my hopes for how unit testing cFS applications can be done going forward from where we are now.

"unit testing"↗
NASA NTRSDate not supplied

Climatology of Global Precipitation Measurement Mission Precipitation Regimes and Implications for Global Estimates of Vertical Winds

The Global Precipitation Measurement (GPM) mission Validation Network (VN) framework leverages over 118 ground-based polarimetric Doppler radars to validate a large subset of precipitation measurements and retrievals from the GPM Dual-frequency Precipitation Radar (DPR). Recently, GPM DPR reflectivity profiles within the VN have been classified according to their convective regime using unsupervised machine learning techniques. The archetypal regimes are stratiform, convective, mixed stratiform-convective (e.g., transition regions), and “other” (e.g., peripheral regions of light precipitation). Subcategories within these four primary regimes vary according to the characteristic depth of included reflectivity profiles, resulting in 12 main GPM DPR precipitation profile categories. Polarimetry of ground-based Doppler radars in the VN offers additional insights into the types of precipitation, while pairs of radars positioned near each other enable retrieval of vertical winds via dual-Doppler analysis. Geometrically matched to the DPR reflectivity profiles in the GPM VN, these ground-based data and retrievals contribute more detailed characterization of the distinct kinematic and microphysical structures associated with each of the 12 DPR precipitation regimes. DPR reflectivity profiles linked with wind in the VN are restricted to GPM overpasses of proximal radar pairs that allow dual-Doppler analysis. Although a limited subset of DPR profiles in the VN are matched with vertical motion, agreement between the reflectivity structures paired with wind data and those of the greater DPR dataset in the VN suggest that estimates of vertical motion may be inferred in regions without ground-based measurements. We present a climatology of the 12 convective regimes identified within the DPR VN dataset as well as early efforts to estimate the kinematic and microphysical structures of precipitation profiles within the greater GPM DPR dataset by applying machine learning techniques. Precipitation data paired with global estimates of vertical winds from these efforts offer early insight to and support upcoming missions to retrieve convective mass flux, including the Investigation of Convective Updrafts (INCUS) in the Tropics and the global Atmosphere Observing System (AOS).

Precipitation↗
NASA NTRSDate not supplied

Advancing Wildfire Monitoring with TEMPO and ML tools: Hourly Smoke and Fire‑Front Mapping and Near‑Surface NO₂ Predictions

Wildfires impose substantial impacts on communities and regions downwind of wildfire smoke. We present a TEMPO‑enabled workflow that generates value‑added Level‑3 smoke‑plume masks and fire‑front maps for large wildfires, such as 2024 Park Fire, using the self‑supervised deep learning system SIT‑FUSE, along with near‑surface NO₂ predictions produced by a foundation model (Microsoft Aurora). We conclude by outlining a roadmap for expanding these capabilities to additional Western U.S. wildfire events and for delivering actionable tools to stakeholders. This open-source, reproducible workflow provides a scalable framework for cross-agency wildfire monitoring to overcome traditional limitations in smoke-cloud discrimination and air-quality forecasting by incorporating TEMPO data and beyond.

Xiaohua Pan↗
NASA NTRS1994

Passive mapping and intermittent exploration for mobile robots

An adaptive state space architecture is combined with diktiometric representation to provide the framework for designing a robot mapping system with flexible navigation planning tasks. This involves indexing waypoints described as expectations, geometric indexing, and perceptual indexing. Matching and updating the robot's projected position and sensory inputs with indexing waypoints involves matchers, dynamic priorities, transients, and waypoint restructuring. The robot's map learning can be opganized around the principles of passive mapping.

Engleson, Sean P.↗
NASA NTRSDate not supplied

Development and Application of NASA SPoRT’s DustTracker-AI Model for Real-Time Identification and Tracking of Dust in Geostationary Satellite Imagery

The NASA Short-term Prediction Research and Transition (SPoRT) Center developed the DustTracker-AI model for identifying and tracking dust in NASA/NOAA Geostationary Operational Environmental Satellite (GOES) imagery in a real-time framework. A training dataset consisting of day and night dust cases was gathered over the southwestern consisting of 115 distinct images and over a million dust pixels and 256 million no dust pixels. The dataset was separated into training (60%), testing (20%), and validation (20%). A simple random forest machine learning model was developed originally to overcome the problem of night-time dust detection and has been expanded to a comprehensive day/night model for dust identification and tracking. This physically-based machine-learning approach uses NASA/NOAA GOES-16 Advanced Baseline Imager infrared imagery as inputs to the model. The model probability of dust output achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels for all dust images in the validation data set. In conjunction with developing the machine-learning model, the NASA Short-term Prediction Research and Transition Center (SPoRT) partnered with NOAA National Weather Service forecast offices to evaluate the model for utility in weather forecasting operations during the 2021 and 2023 late winter-spring seasons. Preliminary evaluation has indicated the majority of forecasters described the DustTracker-AI probabilities as having added confidence to interpreting the Dust RGB and other satellite products to objectively assess the dust extent and trends and increased the amount of time the dust plume could be tracked into the night as compared to use of the Dust RGB. More recently, SPoRT tested small scale events associated with thunderstorm outflow and burn scars to determine the model’s ability to capture local events. This presentation highlights design of the model, validation/evaluation of model performance, and example cases collected during end user product assessments.

Connor H Welch↗
NASA NTRS2014

MARGInS: Model-Based Analysis of Realizable Goals in Systems

Under NASAs Constellation effort, the Exploration Technology Development Program funded research toward a system validation capability that applied machine learning and test-case generation techniques to the analysis of black-box system behavior. The behavior analysis capability scaled to spaces of hundreds of input parameters and tens of thousands of test cases. Aerospace systems at the vehicle level, especially those systems which contain some level of autonomy, are best described by hybrid and non-linear mathematics. Even simplified models of such systems need parameter dimensionalities in the hundreds or thousands of parameters in order to capture sufficient fidelity. The System Safety Assessments (such as those described in the SAE ARP 4761A Safety Assessment Process guidelines) for these systems are prone to errorinteractions between the vehicles subsystems are complex, and can display emergent behaviors. NASA captured this new analysis in the Model-based Analysis of Realizable Goals in Systems (MARGInS) tool and applied it to the Pad Abort 1 (PA-1) simulation as part of the independent validation and verification cycle before the PA-1 flight test in May of 2010. MARGInS evaluated the adherence of the high-fidelity simulation to its requirements, and deter- mined the margins to failure from the expected nominal input conditions. Following the PA-1 test, the capabilities within the MARGInS framework have been extended with sophisticated statistical and white-box test case generation techniques and applied to other NASA missions. The frame- work now includes a critical factors analysis that was applied to NASAs Orion simulation and design. NASAs Aeronautics Research Mission Directorate (ARMD) leveraged the existing MARGInS framework for work on aviation safety for civil transport vehicles and for research on autonomy issues. The NASA ARMD effort created a time series output prediction capability that has been used to characterize trajectories for a plane with an adaptive control system, and a safety boundary detection capability that has been applied to an air traffic control concept of operation for the Federal Aviation Administration. The statistical and machine- learning based techniques within MARGInS have been successfully combined with concolic execution to improve the coverage of a critical unit by driving system-level inputs. The use case driving the concolic execution and MARGInS integration was inspired by the Air France 447 disaster in which the loss of a critical functionality (the airspeed calculation from the pitot tubes) led to loss of the entire plane with the people aboard. To illustrate capabilities and limitations, we will highlight the analyses for the applications listed above. We will then discuss the future plans for MARGInS and its interfaces with other tools.

Validation↗
NASA NTRS2022

A Generalized Approach to Aircraft Trajectory Prediction via Supervised Deep Learning

As research advances diverse forms and missions of aircraft, the National Airspace System (NAS) will become increasingly crowded, limiting current communications resources to accommodate aviation operations. Ongoing research proposes a paradigm of airspace communications, such that resources are autonomously and dynamically allocated via intelligent agents; this allocation requires accurate representations of the NAS, including the predicted positions of aircraft. State-of-the-art research emphasizes the importance of a hybrid-recurrent framework for trajectory prediction and compares the impact of commonly considered weather data on prediction accuracy. However, current research has been limited in its scope of efforts, frequently utilizing a unique flight route, architecture, set of weather data, and date range. This article considers the challenges of generalizing hybrid-recurrent predictive models for flight trajectories. Results illustrate an increase in error variance when identical models are trained over a generalized set of flights; this may be mitigated with careful tuning of hyperparameters, both in the network structure and optimization algorithms. Even so, an irreducible vertical error was identified, resulting from the complex takeoff and landing procedures which can not be correlated to functions of weather or additional assumptions of aircraft behavior. Finally, the use of a test route indicates that generalized models still do not possess sufficient knowledge for general aircraft predictions, with mean error increases ranging from 70-500%. These results illustrate the need for continued efforts on improving model versatility, as well as potential limitations for spectrum allocation near airports and other centers.

Nathan Schimpf↗