Search NASA⌕ Search

SEARCH · Search NASA

Results for “Augmented”

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 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
NASA NTRS2018

Automatic Speech Recognition for Launch Control Center Communication Using Recurrent Neural Networks with Data Augmentation and Custom Language Model

Transcribing voice communications in NASA’s launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.

Chow, Edward↗
NASA NTRS2018

Occluded Object Reconstruction for First Responders with Augmented Reality Glasses Using Conditional Generative Adversarial Networks

Firefighters suffer a variety of life-threatening risks, including line-of-duty deaths, injuries, and exposures to hazardous substances. Support for reducing these risks is important. We built a partially occluded object reconstruction method on augmented reality glasses for first responders. We used a deep learning based on conditional generative adversarial networks to train associations between the various images of flammable and hazardous objects and their partially occluded counterparts. Our system then reconstructed an image of a new flammable object. Finally, the reconstructed image was superimposed on the input image to provide "transparency". The system imitates human learning about the laws of physics through experience by learning the shape of flammable objects and the flame characteristics.

Chow, Edward↗
NASA NTRSDate not supplied

An Augmented Ground Station Architecture for Spacecraft-Initiated Communication Service Requests

Spacecraft performing science and exploration missions have increasingly complex and event-driven objectives, making communication needs difficult to predict in advance. Additional flexibility is required in space communication provider networks to effectively meet time-varying demand. We envision a framework for automated resource allocation in which requests for communications service are initiated by spacecraft based on current mission needs. We propose an augmented ground station configuration featuring a wide field-of-view antenna to receive transmissions from spacecraft requesting high-rate communications. A software suite to automate the service fulfillment process, including interfacing with external scheduling systems such as NASA’s Near Space Network, is described. Experimental results characterizing the physical-layer link between the wide field-of-view antenna and a software-defined radio testbed on the International Space Station are presented. We also discuss long-duration software testing on a ground-based testbed. Taken together, these proof-of-concept results demonstrate the feasibility of the concept to improve the responsiveness of space communications.

user-initiated service↗
NASA NTRSDate not supplied

Clinical Decision Support For Exploration Space Flight: Software Augmentation To Enhance Progressively Earth-Independent Medical Operations

This panel identifies the challenges of supporting medical events in deep space using integrated systems software to augment existing capabilities during increasingly Earth-independent missions where an asynchronous communication environment becomes routine. An interdisciplinary team of software designers, physicians, human factors engineers, and computational modelers applied their respective expertise to develop a roadmap for supporting the crew making medical decisions in more autonomous fashion with time-delayed ground support. The first presentation describes predictive modeling implemented to assist medical system design and address risk reduction using robust clinical decision support software. The second presentation details how operational and environmental challenges guide assumptions and, in turn, by what means requirements for medical decision-making in deep space are derived. The third presentation describes and defines the skills and capabilities an exploration spaceflight medical officer will need to perform effectively during extended-duration spaceflight missions. The fourth presentation covers the potential models and function of the software element for supporting clinical decisions. The final presentation covers how these elements may work together with ground support to provide comprehensive care despite deep space travel's extreme challenges and limitations.

Dana Levin↗
NASA NTRS2021

Contextual Segmentation of Fire Spotting Regions Through Satellite-Augmented Autonomous Modular Sensor Image

Globally, forest fires remain a significant threat to human and environmental wellbeing. Towards mitigating the impacts of forest fires, it is critical that accurate and updated information regarding not only the fire line, but also nearby human settlements, vegetation, and water sources is reported quickly to emergency services. However, while existing UAS-based fire detection methods are effective, they largely do not report the contextual environmental information necessary to best serve nearby communities in disaster response. Additionally, modern advancements in deep learning offer new approaches for image segmentation which may improve classification accuracy beyond current pixel-wise indices. In this work, we benchmark the performance of these modern segmentation techniques in locating both fire lines and environmental features in historical Autonomous Modular Sensor imagery. Furthermore, we augment these outputs with satellite imagery segmentation towards developing a robust contextual mapping tool for rapid emergency fire response and decision making.

Nikhil Behari↗
NASA NTRSDate not supplied

Generalized Predictive Control for Active Stability Augmentation and Vibration Reduction on an Aeroelastic Tiltrotor Model

Tiltrotor aircraft are defining the state-of-the-art in vertical lift technology as they have the potential to greatly expand rotary-wing operational boundaries. However, they are often limited in forward flight speed due to complex coupled rotor and wing dynamic instabilities. The U.S. Army and NASA have been developing a new wind tunnel model, the TiltRotor Aeroelastic Stability Testbed(TRAST), to test proprotors in the NASA Langley Research Center Transonic Dynamics Tunnel (TDT) to investigate aeroelastic stability in cruise. The test is intended to provide high-quality research data for analytical tool development and validation. In addition, the TRAST model will support, develop, and mature new technologies for the design of advanced proprotor aircraft. Stability augmentation and vibration reduction during testing is planned with the use of an active control methodology known as Generalized Predictive Control(GPC). GPC is an autoregressive control law that experimentally acquires a system identification to derive the input-output relation of controls and corresponding sensors. This type of control law is especially useful for complex dynamic interactions that are difficult to explicitly model such as proprotor pylon instability, often referred to as whirl flutter. GPC has been successfully employed on other tiltrotor vehicles to suppress whirl flutter instabilities and vibrations. To aid in the characterization of the wind-tunnel model and in tool development, an analytical representation of the wind-tunnel model was developed using the rotorcraft comprehensive analysis system (RCAS) that simulates structural dynamics and aerodynamics. RCAS was used to derive state-space estimates of the physical plant at various flight conditions to test control law effectiveness. This paper will present an overview of the test article development, a description of RCAS, an explanation of the GPC methodology, and results of GPC being applied to state-space plant estimates of the TRAST model. In these simulations, GPC was effective at stabilizing the aircraft beyond the whirl-flutter boundary while simultaneously reducing vibrations across the flight regime. Additionally, a modern advancement to GPC, termed advanced GPC (AGPC), is introduced that enables a self-adapting system identification. Preliminary results show that AGPC is successful at self-correction as the plant changes from what was used for system identification.

tiltrotor↗
NASA NTRSDate not supplied

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning↗
NASA NTRSDate not supplied

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning↗
NASA NTRSDate not supplied

Testing of TVS Augmented Injectors for Tank-to-Tank Transfer of Cryogens

NASA is developing reusable cryogenic systems to enable manned missions to the Moon and Mars. These cryogenic systems will require replenishing cryogens on-orbit via a tanker or propellant depot with minimal loss to boil-off. Three additively manufactured injectors augmented with a Thermodynamic Venting System have been developed for use in tank-to-tank cryogenic fluid transfer. A Vented Chill/No-Vent Fill approach to tank-to-tank transfer has been the industry standard and is explored in this work with emphasis on injector spray patterns and compared to the Charge-Hold-Vent chill method.

Cryogenic Transfer↗
NASA NTRSDate not supplied

Testing of TVS Augmented Injectors for Tank-to-Tank Transfer of Cryogens

NASA is developing reusable cryogenic systems to enable manned missions to the Moon and Mars. These cryogenic systems will require replenishing cryogens on-orbit via a tanker or propellant depot with minimal loss to boil-off. Three additively manufactured injectors augmented with a Thermodynamic Venting System have been developed for use in tank-to-tank cryogenic fluid transfer. A Vented Chill/No-Vent Fill approach to tank-to-tank transfer has been the industry standard and is explored in this work with emphasis on injector spray patterns and compared to the Charge-Hold-Vent chill method.

Cryogenic Transfer↗
NASA NTRSDate not supplied

Experimental Testing of Advanced Generalized Predictive Control for Stability Augmentation and Vibration Reduction of Tiltrotor Aircraft

Generalized Predictive Control (GPC) is an advanced form of an adaptive control algorithm that uses experimentally acquired data to determine the input-output relationship of complex systems through a process called system identification (system ID). GPC has historically been applied to wind tunnel tests of dynamically-scaled tiltrotor aircraft for stability augmentation and vibration reduction since the complex nature of these dynamic systems does not lend itself well to traditional control theory. Advanced GPC (AGPC) improves upon traditional GPC by enabling self-adaptation as conditions change from those used to acquire the system ID and controller performance would normally erode. The present research expands upon previous analytical development and demonstration of AGPC with experimental demonstration. To support AGPC, this present work also identifies and describes figures of merit that define a good working controller and quantifies the uniqueness of the control inputs and quality of the system ID parameters. The present research demonstrates that AGPC consistently performs better than traditional GPC and can successfully adapt to changing conditions.

Active Controls↗
NASA NTRSDate not supplied

Recent Enhancements to Modeling Sonic Boom Propagation using Augmented Burgers’ Equation

Sonic boom propagation through the atmosphere is modeled with an augmented Burgers’ equation which includes nonlinearity and loss mechanisms. This work details an updated discretization of the governing equations which is fully conservative and duality preserving. Adjoint equations, for all the mechanisms involved, are re-derived and implemented using adjoint consistent discretizations. Computation of loudness metrics is performed using digital filters. The updated implementation is demonstrated and compared against the previous formulation for selected cases, and the differences are documented and discussed. The improved discretization results in faster mesh convergence of the loudness metrics and substantially de-creases runtime. In addition, the adjoint solutions provide mesh-converged gradients which are free from spurious oscillations.

Sonic Boom↗
NASA NTRSDate not supplied

Experimental Testing of Advanced Generalized Predictive Control for Stability Augmentation and Vibration Reduction of Tiltrotor Aircraft

Generalized Predictive Control (GPC) is an advanced form of an adaptive control algorithm that uses experimentally acquired data to determine the input-output relationship of complex systems through a process called system identification (system ID). GPC has historically been applied to wind tunnel tests of dynamically-scaled tiltrotor aircraft for stability augmentation and vibration reduction since the complex nature of these dynamic systems does not lend itself well to traditional control theory. Advanced GPC (AGPC) improves upon traditional GPC by enabling self-adaptation as conditions change from those used to acquire the system ID and controller performance would normally erode. The present research expands upon previous analytical development and demonstration of AGPC with experimental demonstration. To support AGPC, this present work also identifies and describes figures of merit that define a good working controller and quantifies the uniqueness of the control inputs and quality of the system ID parameters. The present research demonstrates that AGPC consistently performs better than traditional GPC and can successfully adapt to changing conditions.

Active Controls↗
NASA NTRSDate not supplied

Overview of Mars Sample Return – Earth Entry System Woven Roughness Heating Augmentation Test in NASA Langley’s Mach 6 Wind Tunnel

The Mars Sample Return Mission (MSR) is a planned NASA flagship mission in which a sample retrieval lander (SRL) with a rover will be flown to Mars to obtain sample tubes on the surface that were dropped by the Mars 2020 rover [1]. After obtaining the sam-ples, the rover will return and ascend back to Martian orbit onboard the Mars Ascent Vehicle (MAV). Upon return to Earth orbit, the samples will perform Entry, Descent, and Landing (EDL) with the Earth Entry Sys-tem (EES) architecture, and land in Utah. The EES vehicle will utilize a HEEET-variant as its TPS, which will be the first time a woven TPS will be used on a flagship NASA mission [2]. This TPS offers a unique challenge for Computational Fluid Dynamics (CFD) modeling of the aerothermal envi-ronment of the vehicle, as woven roughness heating augmentation has not been extensively investigated experimentally. As a result, in order to validate com-putational models for woven roughness heating aug-mentation, a wind tunnel test campaign at NASA Langley Research Center’s Mach 6 wind tunnel was performed in April of 2023. This test campaign consisted of over a hundred runs with Reynolds numbers spanning from 1-7 mil-lion 1/ft and with six separate wind tunnel models used. A second campaign with a suite of new models will be conducted in Summer 2023 as well as a cam-paign with a flat plate model, both of which are of great interest to the MSR-EES project. The data obtained from this test are extremely vital for the MSR mission, as they will validate CFD roughness heating models which will be directly used to design the TPS of the EES portion of MSR and characterize the heating environment that the entry ve-hicle will experience. Further extensions of the MSR-EES test campaign will continue to provide validation data for developing more effective computational tools.

Jonathan Cheatwood↗
NASA NTRS2023

Augmented Reality Tool for Operationally Relevant 3D Sensorimotor Assessments

This project will leverage existing capabilities of an augmented reality (AR) sensorimotor assessment tool. Currently, the tool mimics the capabilities of validated 2-dimensional (2D) assessments. While this modality is well-aligned with seated interactions with flight-deck displays, extravehicular activity (EVA) tasks will require full body mobility wherein astronauts reach and bend in a 3-dimensional (3D) space. These types of motions, naturally including head movements, are known to elicit experiences of disorientation. Thus, sensorimotor assessments that include these stimulations and larger movements are important for understanding astronaut readiness prior to initial EVAs. The proposed effort will extend the current 2D eye-hand coordination task in AR to a 3D task designed to evaluate dynamic balance and eye-hand-body coordination. The new module will extend the range of motion and interaction space such that it better aligns with operational task needs for astronaut readiness evaluation.

Sarah Catherine Moudy↗
NASA NTRS2023

Chile Wildland Fires: Augmenting Wildfire Risk Assessment Efforts with Satellite-based Measurements of Soil Moisture and Vegetation Health in Central and South-Central Chile

Since 2010, Central and South-Central Chile have recorded abnormally low annual precipitation, resulting in over a decade-long megadrought. This water deficit has driven more severe wildfires, which begin earlier in the year, last longer, and burn over significantly larger areas. Past studies indicated wildland fires propagate following vegetation stress and under certain soil moisture conditions. Our work further investigated the drivers of the unprecedented wildfire that devastated Central and South-Central Chile in 2017 and 2023. To that end, we leveraged NASA Earth observations from space to explore the link between terrestrial variables and wildland fires. We first delineated the burnt extent using data from Landsat 9 Operational Land Imager 2 (OLI-2), along with the combined information from Terra + Aqua Moderate Resolution Imaging Spectroradiometer (MODIS). Next, we analyzed vegetation health based on the Normalized Difference Vegetation Index (NDVI) and evapotranspiration (ET) products of Terra MODIS. Furthermore, we examined soil moisture data from the Soil Moisture Active Passive (SMAP) mission. As the megadrought continues, we found greater anomalies and stress in vegetation indices across the region. We also identified certain pre-fire conditions in soil moisture and evapotranspiration in the days and months leading to the recent wildfires. We compared these findings against control areas that were not impacted by wildfires. Using satellite-based NASA Earth observations, we were able to provide insights into potential indicators of wildfire risk, which can augment future risk assessment and management efforts.

Benjamin D Goffin↗
NASA NTRS2023

Joint Augmented Reality Visual Informatics System: Concept of Operations

NASA proposed requirements for a digital display for an EVA spacesuit to provide relevant information to the crew member. The Joint Augmented Reality Visual Informatics System (Joint AR) project pursued four years of research and development towards a suit-display system in a near-eye, AR form factor. The project was responsible for developing software (custom graphics engine and core flight software), physical hardware prototyping (controls, projection display optics, suited display platform), virtual prototyping platform (a virtual reality testbed), and human-in-the-loop (HITL) operational testing informed by EVA flight controllers, crew members, and human factors engineers for con-ops definition. This document contains substantial updates to CTSD-ADV-1788 Rev. Basic. This revision was produced by the project to summarize the use-cases and and user experiences developed throughout the project, and refine the Basic revision originally drafted at the beginning of the project life cycle. The primary purpose of this document is to summarize and make available the scenario development efforts that have been pursued and explored within the Joint AR project. This includes descriptions of the scenarios themselves as well as corresponding potential of advanced informatics displays to support those specified scenarios. In doing so, this document provides a variety of approaches to deconstruct and hypothesize how future technological capabilities so that with future EVA work demands can be satisfied within future human planetary spaceflight missions.

Matthew Miller↗
NASA NTRS2023

The Historical Greenland Climate Network (GC-Net) Curated and Augmented Level-1 Dataset

The Greenland Climate Network (GC-Net) consists of 31 automatic weather stations (AWSs) at 30 sites across the Greenland Ice Sheet. The first site was initiated in 1990, and the project has operated almost continuously since 1995 under the leadership of the late Konrad Steffen. The GC-Net AWS measured air temperature, relative humidity, wind speed, atmospheric pressure, downward and reflected shortwave irradiance, net radiation, and ice and firn temperatures. The majority of the GC-Net sites were located in the ice sheet accumulation area (17 AWSs), while 11 AWSs were located in the ablation area, and two sites (three AWSs) were located close to the equilibrium line altitude. Additionally, three AWSs of similar design to the GC-Net AWS were installed by Konrad Steffen's team on the Larsen C ice shelf, Antarctica. After more than 3 decades of operation, the GC-Net AWSs are being decommissioned and replaced by new AWSs operated by the Geological Survey of Denmark and Greenland (GEUS). Therefore, making a reassessment of the historical GC-Net AWS data is necessary. We present a full reprocessing of the historical GC-Net AWS dataset with increased attention to the filtering of erroneous measurements, data correction and derivation of additional variables: continuous surface height, instrument heights, surface albedo, turbulent heat fluxes, and 10 m ice and firn temperatures. This new augmented GC-Net level-1 (L1) AWS dataset is now available at https://doi.org/10.22008/FK2/VVXGUT (Steffen et al., 2023) and will continue to be refined. The processing scripts, latest data and a data user forum are available at https://github.com/GEUS-Glaciology-and-Climate/GC-Net-level-1-data-processing (last access: 30 November 2023). In addition to the AWS data, a comprehensive compilation of valuable metadata is provided: maintenance reports, yearly pictures of the stations and the station positions through time. This unique dataset provides more than 320 station years of high-quality atmospheric data and is available following FAIR (findable, accessible, interoperable, reusable) data and code practices.

Greenland Climate Network↗