SEARCH · Search NASA

Results for “Generative learning”

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.

SourceResearch connectionFrom yearThrough year

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

At least 235 records · Page 13

All sources NASA NTRS DOE OSTI

NASA NTRS1999

Use of the MATRIXx Integrated Toolkit on the Microwave Anisotropy Probe Attitude Control System

Recent advances in analytical software tools allow the analysis, simulation, flight code, and documentation of an algorithm to be generated from a single source, all within one integrated analytical design package. NASA's Microwave Anisotropy Probe project has used one such package, Integrated Systems' MATRIXx suite, in the design of the spacecraft's Attitude Control System. The project's experience with the linear analysis, simulation, code generation, and documentation tools will be presented and compared with more traditional development tools. In particular, the quality of the flight software generated will be examined in detail. Finally, lessons learned on each of the tools will be shared.

Ward, David K.↗

NASA NTRS2013

Cobra Fiber-Optic Positioner Upgrade

A prime focus spectrometer (PFS), along with corrective optics, will mount in place of the secondary mirror of the Subaru telescope on Mauna Kea, Hawaii. This will allow simultaneous observations of cosmologic targets. It will enable large-scale galactic archeology and dark energy surveys to help unlock the secrets of the universe. To perform these cosmologic surveys, an array of 2,400 optical fibers needs to be independently positioned within the 498-mm-diameter focal plane of the PFS instrument to collect light from galaxies and stars for spectrographic analyses. To allow for independent re-positioning of the fibers, a very small positioner (7.7 mm in diameter) is required. One hundred percent coverage of the focal plane is also required, so these small actuators need to cover a patrol region of 9.5 mm in diameter. To optimize the amount of light that can be collected, the fibers need to be placed within 5 micrometers of their intended target (either a star or galaxy). The Cobra Fiber Positioner was designed to meet the size and accuracy requirements stated above. Cobra is a two-degrees-of-freedom mechanism that can position an optical fiber in the focal plane of the PFS instrument to a precision of 5 micrometers. It is a theta-phi style positioner containing two rotary piezo tube motors with one offset from the other, which enables the optic fibers to be placed anywhere in a small circular patrol region. The patrol region of the actuator is such that the array of 2,400 positioners allows for full coverage of the instrument focal plane by overlapping the patrol areas. A second-generation Cobra positioner was designed based on lessons learned from the original prototype built in 2009. Improvements were made to the precision of the ceramic motor parts, and hard stops were redesigned to minimize friction and prevent jamming. These changes resulted in reducing the number of move iterations required to position the optical fiber within 5 micrometers of its target. At the time of this reporting, there are still many tests to be performed that will validate system level performance, but on an individual level, the Cobra positioner demonstrates excellent performance and will enable the PFS instrument to make unprecedented measurements of the universe. What is unique about the upgrades made to the Cobra positioner is the improved performance due to the design changes in the hard stops and the ceramic end caps of the motors. Other changes were made to reduce the unit cost of a Cobra positioner without affecting the performance, since thousands of these devices will have to be built for the PFS instrument.

Fisher, Charles D.↗

NASA NTRS2014

Introduction

The 2014 SPIE Sensing Technologies for Global Health, Military Medicine and Environmental Monitoring conference embraced a wealth of state-of-the-art information in basic and applied science. This event covered the latest developments in the following areas: Non-invasive Disease Diagnostics for Global Health- This opening series of two consecutive sessions focused on oral biospecimen based rapid assays and point-of-care devices for the detection of pathogens causing infectious diseases, biomarkers for cancer, and analytes for noncommunicable diseases such as diabetes. They also covered presentations on the human proteasome and microbiome with linkage to human diseases and diagnostic approaches. The sessions were built on the past experience and expertise of the National Institutes of Health, National Institutes of Dental and Craniofacial Research. Military Medicine I: Traumatic Brain Injury and PTSD-This assembly covered oral-biomarker based diagnostics for brain damage and TBI as well as prevention and rehabilitation technologies. Neurorehabilitation and noninvasive neuromodulation were also discussed as critical approaches for effective functioning. Military Medicine II: Physiology and Medicine of Extreme Environments and Spaceflight-This scientific segment showcased physiological, pharmacological and diagnostic sensing methodologies during spaceflight per the National Aeronautics and Space Administration as well as military-relevant toxicans and future sensing trends per the Department of Defense. It also included latest technologies to determine hydration status in warfighters, eye surgery using the latest laser technologies, and sensing tools for blood analysis.  Sensing Technologies for Disease Diagnostics and Environmental Monitoring-This closing series of two consecutive sessions provided the venues to learn and discuss more results on the next generation of diagnostic tools and field technologies for diseases, including biomarker detection by digital imaging, multiplex technologies, capillary electrophoresis and molecular platforms serving as labs-on-chips. This conference allowed cross-fertilization of ideas, projects and collaborative work by a multidisciplinary audience of national and international colleagues from the academia, industry and federal government: The National Institutes of Health, National Aeronautics and Space Administration, and the Department of Defense.

Wotring, Virginia E.↗

NASA NTRS2016

Preparations for Integrating Space-Based Total Lightning Observations into Forecast Operations

NASA's Short-term Prediction Research and Transition (SPoRT) Center has been a leader in collaborating with the United States National Weather Service (NWS) offices to integrate ground-based total lightning (intra-cloud and cloud-to-ground) observations into the real-time operational environment. For much of these collaborations, the emphasis has been on training, dissemination of data to the NWS AWIPS system, and focusing on the utility of these data in the warning decision support process. A shift away from this paradigm has occurred more recently for several reasons. For one, SPoRT's collaborations have expanded to new partners, including emergency managers and the aviation community. Additionally, and most importantly, is the impending launch of the GOES-R Geostationary Lightning Mapper (GLM). This has led to collaborative efforts to focus on additional forecast needs, new data displays, develop training for GLM uses based on the lessons learned from ground-based lightning mapping arrays, and ways to better relate total lightning data to other meteorological parameters. This presentation will focus on these efforts to prepare the operational end user community for GLM with an eye towards sharing lessons learned as EUMETSAT prepares for the Meteosat Third Generation Lightning Imager. This will focus on both software and training needs. In particular, SPoRT has worked closely with the Meteorological Development Laboratory to create the total lightning tracking tool. This software allows for NWS forecasters to manually track storms of interest and display a time series trend of observations. This tool also has been expanded to work on any gridded data set allowing for easy visual comparisons of multiple parameters in addition to total lightning. A new web display has been developed for the ground-based observations that can be easily extended to satellite observations. This paves the way for new collaborations outside of the NWS, both domestically and internationally, as the web display will be functional on PCs and mobile devices. Furthermore, SPoRT has helped developed the software plug-in to visualize GLM data. Examples using the official GLM proxy product will be used to provide a glimpse as to what real-time GLM and likely MTG-LI data will be in the near future.

GLM↗

NASA NTRS2018

Fuzzy Modeling and Parallel Distributed Compensation for Aircraft Flight Control from Simulated Flight Data

A method is described that combines fuzzy system identification techniques with Parallel Distributed Compensation (PDC) to develop nonlinear control methods for aircraft using minimal a priori knowledge, as part of NASA’s Learn-to-Fly initiative. A fuzzy model was generated with simulated flight data, and consisted of a weighted average of multiple linear time invariant state-space cells having parameters estimated using the equation-error approach and a least-squares estimator. A compensator was designed for each subsystem using Linear Matrix Inequalities (LMI) to guarantee closed-loop stability and performance requirements. This approach is demonstrated using simulated flight data to automatically develop a fuzzy model and design control laws for a simplified longitudinal approximation of the F-16 nonlinear flight dynamics simulation. Results include a comparison of flight data with the estimated fuzzy models and simulations that illustrate the feasibility and utility of the combined fuzzy modeling and control approach.

Weinstein, Rose↗

NASA NTRS2018

The Zwicky Transient Facility: Data Processing, Products, and Archive

The Zwicky Transient Facility (ZTF) is a new robotic time-domain survey currently in progress using the Palomar 48-inch Schmidt Telescope. ZTF uses a 47 square degree field with a 600 megapixel camera to scan the entire northern visible sky at rates of ∼3760 square degrees/hour to median depths of g ~ 20.8 and r ~ 20.6 mag (AB, 5σ in 30 sec). We describe the Science Data System that is housed at IPAC, Caltech. This comprises the data-processing pipelines, alert production system, data archive, and user interfaces for accessing and analyzing the products. The real-time pipeline employs a novel image-differencing algorithm, optimized for the detection of point-source transient events. These events are vetted for reliability using a machine-learned classifier and combined with contextual information to generate data-rich alert packets. The packets become available for distribution typically within 13 minutes (95th percentile) of observation. Detected events are also linked to generate candidate moving-object tracks using a novel algorithm. Objects that move fast enough to streak in the individual exposures are also extracted and vetted. We present some preliminary results of the calibration performance delivered by the real-time pipeline. The reconstructed astrometric accuracy per science image with respect to Gaia DR1 is typically 45 to 85 milliarcsec. This is the RMS per-axis on the sky for sources extracted with photometric S/N ≥10 and hence corresponds to the typical astrometric uncertainty down to this limit. The derived photometric precision (repeatability) at bright unsaturated fluxes varies between 8 and 25 millimag. The high end of these ranges corresponds to an airmass approaching ∼2—the limit of the public survey. Photometric calibration accuracy with respect to Pan-STARRS1 is generally better than 2%. The products support a broad range of scientific applications: fast and young supernovae; rare flux transients; variable stars; eclipsing binaries; variability from active galactic nuclei; counterparts to gravitational wave sources; a more complete census of Type Ia supernovae; and solar-system objects.

Frank J. Masci↗

NASA NTRSDate not supplied

Authoring, Analyzing, and Monitoring Requirements for a Lift-Plus-Cruise Aircraft

Requirements specification and analysis is widely applied to ensure the correctness of industrial systems in safety critical domains. Requirements are often initially written in natural language, which is highly ambiguous, and as a second step transformed into a language with rigorous semantics for formal analysis. [Question/problem] In this paper, we report on our experience in requirements creation and analysis, as well as run-time monitor generation using the Formal Requirement Elicitation Tool (FRET), on an industrial case study for a Lift-Plus-Cruise concept aircraft. [Principal ideas/results] We study the creation of requirements directly in the structured language of FRET without a prior definition of the same requirements in natural language. We focus on requirements describing state machines and discuss the challenges that we faced, in terms of creating requirements and generating monitors. We demonstrate how realizability, i.e., checking whether a requirements specification can be implemented, is crucial for understanding temporal interdependencies among requirements. [Contribution] Our study is the first complete attempt at using FRET to create industrial, realizable requirements and generate run-time monitors. Insight from lessons learned was materialized into new features in the FRET and JKind analysis frameworks.

Requirements engineering↗

NASA NTRSDate not supplied

Authoring, Analyzing, and Monitoring Requirements for a Lift-Plus-Cruise Aircraft

Requirements specification and analysis is widely applied to ensure the correctness of industrial systems in safety critical domains. Requirements are often initially written in natural language, which is highly ambiguous, and as a second step transformed into a language with rigorous semantics for formal analysis. In this paper, we report on our experience in requirements creation and analysis, as well as run-time monitor generation using the Formal Requirement Elicitation Tool (FRET), on an industrial case study for a Lift-Plus-Cruise concept aircraft. We study the creation of requirements directly in the structured language of FRET without a prior definition of the same requirements in natural language. We focus on requirements describing state machines and discuss the challenges that we faced, in terms of creating requirements and generating monitors. We demonstrate how realizability, i.e., checking whether a requirements specification can be implemented, is crucial for understanding temporal interdependencies among requirements. Our study is the first complete attempt at using FRET to create industrial, realizable requirements and generate run-time monitors. Insight from lessons learned was materialized into new features in the FRET and JKind analysis frameworks.

Requirements engineering↗

NASA NTRS2023

Neural-Based Compression Scheme for Solar Image Data

Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold decision to make. Stronger compression methods, by distorting the data, can increase data throughput at the cost of accuracy which could affect scientific analysis of the data. On the other hand, preserving subtle details in the compressed data requires a high amount of data to be transferred, reducing the desired gains from compression. In this work, we propose a neural network-based lossy compression method to be used in NASA’s data-intensive imagery missions. We chose NASA’s Solar Dynamics Observatory (SDO) mission which transmits 1.4 terabytes of data each day as a proof of concept for the proposed algorithm. In this work, we propose an adversarially trained neural network, equipped with local and non-local attention modules to capture both the local and global structure of the image resulting in a better trade-off in rate-distortion (RD) compared to conventional hand-engineered codecs. The RD variational autoencoder used in this work is jointly trained with a channel-dependent entropy model as a shared prior between the analysis and synthesis transforms to make the entropy coding of the latent code more effective. We also studied how optimizing perceptual losses could help our neural compressor to preserve high-frequency details of the data in the reconstructed compressed image. Our neural image compression algorithm outperforms currently-in-use and state-of-the-art codecs such as JPEG and JPEG-2000 in terms of the RD performance when compressing extreme-ultraviolet (EUV) data. As a proof of concept for use of this algorithm in SDO data analysis, we have performed coronal hole (CH) detection using our compressed images, and generated consistent segmentations, even at a compression rate of ∼ 0.1 bits per pixel (compared to 8 bits per pixel on the original data) using EUV data from SDO.

Image coding↗

NASA NTRS1995

Locomotion training of legged robots using hybrid machine learning techniques

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Simon, William E.↗

NASA NTRS2015

Model Generation to Support Model-Based Testing Applied on NASA DAT - An Experience Report

Model-based Testing (MBT), where a model of the system under tests (SUT) behavior is used to automatically generate executable test cases, is a promising and versatile testing technology. Nevertheless, adoption of MBT technologies in industry is slow and many testing tasks are performed via manually created executable test cases (i.e. test programs such as JUnit). In order to adopt MBT, testers must learn how to construct models and use these models to generate test cases, which might be a hurdle. An interesting observation in our previous work is that the existing manually created test cases often provided invaluable insights for the manual creation of the testing models of the system. In this paper we present an approach that allows the tester to first create and debug a set of test cases. When the tester is happy with the test cases, the next step is to automatically generate a model from the test cases. The generated model is derived from the test cases, which are actions that the system can perform (e.g. a button clicks) and their expected outputs in form of assert statements (e.g. assert data entered). The model is a Finite State Machine (FSM) model that can be employed with little or no manual changes to generate additional test cases for the SUT. We successfully applied the approach in a feasibility study to the NASA Data Access Toolkit (DAT), which is a web-based GUI. One compelling finding is that the test cases that were generated from the automatically generated models were able to detect issues that were not detected by the original set of manually created test cases. We present the findings from the case study and discuss best practices for incorporating model generation techniques into an existing testing process.

State Machines↗

NASA NTRS2021

NASA SpaceCube Edge TPU SmallSat Card for Autonomous Operations and Onboard Science-Data Analysis

Using state-of-the-art artificial intelligence (AI)frameworks onboard spacecraft is challenging because common spacecraft processors cannot provide comparable performance to datacenters with server-grade CPUs and GPUs available for terrestrial applications and advanced deep-learning networks. This limitation makes small, lo w-p o we r AI microchip architectures, such as the Google Coral Edge Tensor Processing Unit (TPU), attractive for space missions where the application-specific design enables both high-performance and power-efficient computing for AI applications. To address these challenging considerations for space deployment, this research introduces the design and capabilities of a CubeSat-sized Edge TPU-based co-processor card, known as the SpaceCube Low-power Ed g e Artificial Intelligence Resilient Node (SC-LEARN). This design conforms to NASA’s CubeSat Card Specification (CS2) for integration into next-generation SmallSat and CubeSat systems. This paper describes the overarching architecture and design of the SC-LEARN, as well as, the supporting test card designed for rapid prototyping and evaluation. The SC-LEARN was developed with three operational modes: (1) a high-performance parallel-processing mode,(2)a fault-tolerant mode for onboard resilience, and (3) a power-saving mode with cold spares. Importantly, this research also elaborates on both training and quantization of Tensor Flow models for the SC-LEARN for use onboard with representative, open-source datasets. Lastly, we describe future research plans, including radiation-beam testing and flight demonstration.

Advanced avionics↗

NASA NTRSDate not supplied

Increasing accessibility to deep learning-based analytics for space biology: pretrained models, transfer learning, and analytics platform development

Biological systems react in complex ways to the stressors of spaceflight, and the data capturing these relationships is concomitantly high-dimensional and complex. Deep learning and machine learning approaches are increasingly popular as an analytical approach for space biosciences, due to their ability to model complex relationships in complex data. However, such approaches often require large datasets and extensive computational resources. New approaches that minimize data sizes and computational power needed to leverage machine learning, and resources that make these approaches accessible, are needed to increase accessibility and adoption of machine learning in the space biosciences. Transfer learning, in which a pretrained model of broad utility is trained on a large dataset, and subsequently reused on downstream applications for which data is more limited, is one approach to minimizing data and computational intensity of deep learning applications. This transfer learning approach results in more performant models in high-dimensional, low-sample-size settings such as space biology, as compared to training models on limited data from scratch. This presentation will outline efforts to generate pretrained models for the space biology community, and highlight transfer learning applications modeling microbial antibiotic resistance during spaceflight. Finally, in order to increase accessibility of these models and tools, as well as others, for the broader space biology community, we present a modeling and analysis platform facilitating machine learning applications in space biology. This platform streamlines machine learning training and analysis in a notebook format, facilitates download and use of space biology data from the NASA GeneLab database, and can be utilized on NASA-hosted servers or downloaded and hosted locally. This effort, as part of the AI4LS (Artificial Intelligence for Life in Space) working group, will increase accessibility, feasibility, and performance of machine learning approaches for the space biology community.

Adrienne Hoarfrost↗

NASA NTRSDate not supplied

Ideas for Applying Artificial Intelligence to NASA Lessons Learned

Artificial intelligence is it tool that has existed for many years. Recent developments in generative AI has rapidly expanded the applications for this tool across many domains such as writing, analyzing, summarizing, creating videos, creating graphics and others. Charts in this presentation will prompt attendees to discuss the pros and cons, and potential validation methodology for imbedding artificial intelligence tools in the NASA lessons learned knowledge sharing environment.

Knowledge Management↗

NASA NTRS2021

Scheduling the NASA Deep Space Network with Deep Reinforcement Learning

With three complexes spread evenly across the Earth, NASA’s Deep Space Network (DSN) is the primary means of communications as well as a significant scientific instrument for dozens of active missions around the world. A rapidly rising number of spacecraft and increasingly complex scientific instruments with higher bandwidth requirements have resulted in demand that exceeds the network’s capacity across its 12 antennae. The existing DSN scheduling process operates on a rolling weekly basis and is time-consuming; for a given week, generation of the final baseline schedule of spacecraft tracking passes takes roughly 5 months from the initial requirements submission deadline, with several weeks of peer-to-peer negotiations in between. This paper proposes a deep reinforcement learning (RL) approach to generate candidate DSN schedules from mission requests and spacecraft ephemeris data with demonstrated capability to address real-world operational constraints. A deep RL agent is developed that takes mission requests for a given week as input, and interacts with a DSN scheduling environment to allocate tracks such that its reward signal is maximized. A comparison is made between an agent trained using Proximal Policy Optimization and its random, untrained counterpart. The results represent a proof-of-concept that, given a well-shaped reward signal, a deep RL agent can learn the complex heuristics used by experts to schedule the DSN. A trained agent can potentially be used to generate candidate schedules to bootstrap the scheduling process and thus reduce the turnaround cycle for DSN scheduling.

Wilson, Brian↗

NASA NTRSDate not supplied

TPS Certification by Analysis: Model-Driven Characterization of Properties and Failure in Woven Thermal Protection Systems

Woven, ablative thermal protection system (TPS) materials provide a robust option for aggressive (re)entries and thus have been baselined for the upcoming Mars Sample Return (MSR) mission's Earth Entry System (EES). The reliability requirements for MSR-EES necessitate understanding of material property variability, which could be significant given the complex structure and anisotropic nature of properties in TPS weaves, as well as the response to potential impact with micrometeoroids or orbital debris during the EES re-entry. The TPS Certification by Analysis effort within the Entry Systems Modeling project seeks to provide computational models and analyses that support the certification against such material-based risks. For the present talk, focus will be given to the characterization of baseline woven TPS material properties and mechanical failure limits, which entails (1) use of computational techniques (e.g., machine learning) to interpret computed tomography images of the weave to generate representative structural models and (2) application of multiscale material modeling approaches to characterize thermomechanical and failure properties.

thermal protection systems↗

NASA NTRS1992

An expert system for monitoring dynamic aspects of RCS

An expert system (ARC) based on the MIMIC(2) framework is being developed for assistance in monitoring the Space Shuttle reaction control system (RCS) and in training RCS mission controllers. ARC has four components: a hypothesis generator, a model-constructor, a model-simulator and a matcher. The hypothesis generator examines current readings of sensors to generate a set of hypotheses. The model constructor generates models from these hypotheses. The simulator predicts future behaviors of the system. The matcher validates hypotheses by testing the predicted states against real data. The hypothesis generator postulates faults using model-based reasoning (MBR), learned rules from real data, and expert-defined rules. The simulator uses a qualitative QSIM model of the RCS which can handle both nominal modes as well as a variety of fault models. This allows the simulator to simulate the system even when one or more components have degraded. Finally, the matcher is responsible for comparing readings against predictions and calculating confidence in a particular hypothesis.

Kulkarni, Deepak↗

NASA NTRS1993

New Technologies for Space Avionics, 1993

The report reviews a 1993 effort that investigated issues associated with the development of requirements, with the practice of concurrent engineering and with rapid prototyping, in the development of a next-generation Reaction Jet Drive Controller. This report details lessons learned, the current status of the prototype, and suggestions for future work. The report concludes with a discussion of the vision of future avionics architectures based on the principles associated with open architectures and integrated vehicle health management.

Aibel, David W.↗