Search NASA⌕ Search

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.

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

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Sampling Functions from Gaussian Processes and Structured Covariance Gaussian Networks

When learning aerodynamic models from data, it is critical to incorporate estimates of model uncertainty. This motivates the design of probabilistic aerodynamic databases which can be sampled to generate physically and statistically plausible aerodynamic models. In this talk we discuss how to sample deterministic functions from two different kinds of probabilistic models and demonstrate their use. First, Gaussian Process Regressors (GPRs) are a widely used probabilistic kernel-based model which can be thought of as Gaussian distributions over functions. GPRs are generally trained by maximizing the marginal likelihood of seeing the training data over the kernel parameter space. Sample functions are easily generated by drawing points from the Gaussian distribution at desired input points. However, when the points are not known ahead of time, the classical sampling approach is not possible since successive function samples will generate different function realizations. We present an approach for sampling consistent function evaluations from a GPR over multiple samples. Second, we describe a neural network architecture which learns a conditional Gaussian distribution by maximizing the marginal likelihood at each point in the input space. We then discuss and compare several options for generating sample functions which match this distribution. Finally, we demonstrate the use of these probabilistic aerodynamic models in an atmospheric reentry simulation.

Gaussian process regression↗
NASA NTRS1992

Automatic learning rate adjustment for self-supervising autonomous robot control

Described is an application in which an Artificial Neural Network (ANN) controls the positioning of a robot arm with five degrees of freedom by using visual feedback provided by two cameras. This application and the specific ANN model, local liner maps, are based on the work of Ritter, Martinetz, and Schulten. We extended their approach by generating a filtered, average positioning error from the continuous camera feedback and by coupling the learning rate to this error. When the network learns to position the arm, the positioning error decreases and so does the learning rate until the system stabilizes at a minimum error and learning rate. This abolishes the need for a predetermined cooling schedule. The automatic cooling procedure results in a closed loop control with no distinction between a learning phase and a production phase. If the positioning error suddenly starts to increase due to an internal failure such as a broken joint, or an environmental change such as a camera moving, the learning rate increases accordingly. Thus, learning is automatically activated and the network adapts to the new condition after which the error decreases again and learning is 'shut off'. The automatic cooling is therefore a prerequisite for the autonomy and the fault tolerance of the system.

Arras, Michael K.↗
NASA NTRS1997

A Critical Assessment of Protein Crystal Growth in Microgravity

Experiments to grow higher diffraction quality protein crystals in the microgravity environment of an orbiting spacecraft are one of the most frequently flown space experiments. Ground-based research has shown that convective flows occur even about protein crystals growing in the Earth's gravitational field. Further, this research has shown that the resultant flow velocities can cause growth cessation, and probably affect the measured X-ray data quality obtained. How flow deleteriously affects protein crystal growth (PCG) is still not known, and is the subject of ongoing research. Failing a rational method for ameliorating flow effects on Earth, one can, through NASA and other nations space agency sponsored programs, carry out protein crystal growth in the microgravity environment of an orbiting spacecraft. Early first generation PCG hardware was characterized by a very low success rate and a steep design learning curve. Subsequent hardware designs have improved upon their predecessors. Now the crystal grower has a wide variety of hardware configurations and crystal growth protocols to choose from, many of which implement "standard" laboratory protein crystal growth methods. While many of these are first or early second generation hardware the success rate, defined as growing crystals giving data better than has been obtained on Earth, is at least 20% overall and may be considerably higher if one only considers latter experiments. There are a large number of protein crystals grown every year, with hundreds of structures determined. Those crystallized in microgravity represent a small proportion of this total, and there is concern that the costs of the microgravity PCG program(s) do not justify such limited returns. Empirical evidence suggests that optimum crystal growth conditions in microgravity differ from those determined on Earth, further exacerbating the chances of success. Microgravity PCG is probably best suited for "mature" crystallizations, where one has considerable experience with the particular macromolecular system and has reached an apparent limit in diffraction resolution. Under such circumstances the cost of one or two successful flight experiments may more than offset the equivalent cost of several years effort to obtain the same improvement in data quality.

Pusey, Marc↗
NASA NTRSDate not supplied

Probabilistic Calibration of Expensive Models using Efficiently Trained Surrogates

Calibration of computational models in the presence of uncertainty is often cast as a Bayesian inference problem and solved via sampling methods, e.g., Markov chain Monte Carlo. When the computational model is expensive, this task becomes intractable due to the large number of samples required to accurately estimate the posterior distribution of the calibration parameters. A popular solution to this problem is to use machine learning to develop a faster-to-evaluate, lower-fidelity substitute for the original model to serve as a surrogate while solving the inference problem. Although considered an offline cost, generating training data to construct this surrogate model can still be an expensive task in practice. An active learning algorithm is presented that focuses training on improving surrogate accuracy specifically in and around the bulk of the posterior distribution, as this is where the model is exercised during calibration. Candidate samples are drawn from families of distributions related to an approximation of the posterior. The sample maximizing predictive variance is then selected for evaluation by the original computational model, yielding a label for the training point. Iterating this approach increases efficiency relative to space filling designs (e.g., Latin hypercube sampling) by avoiding low probability points. Practical considerations are discussed, including the benefits of using a sequential Monte Carlo sampling approach, convergence heuristics, and the importance of both exploration and exploitation given that the true posterior is unknown a priori.

uncertainty quantification↗
NASA NTRS2007

Hydra Rendezvous and Docking Sensor

The U.S. technology to support a CEV AR&D activity is mature and was developed by NASA and supporting industry during an extensive research and development program conducted during the 1990's and early 2000 time frame at the Marshall Space Flight Center. Development and demonstration of a rendezvous/docking sensor was identified early in the AR&D Program as the critical enabling technology that allows automated proxin~ity operations and docking. A first generation rendezvous/docking sensor, the Video Guidance Sensor (VGS) was developed and successfully flown on STS 87 and again on STS 95, proving the concept of a video-based sensor. Advances in both video and signal processing technologies and the lessons learned from the two successful flight experiments provided a baseline for the development of a new generation of video based rendezvous/docking sensor. The Advanced Video Guidance Sensor (AVGS) has greatly increased performance and additional capability for longer-range operation. A Demonstration Automatic Rendezvous Technology (DART) flight experiment was flown in April 2005 using AVGS as the primary proximity operations sensor. Because of the absence of a docking mechanism on the target satellite, this mission did not demonstrate the ability of the sensor to co~ltrold ocking. Mission results indicate that the rendezvous sensor operated successfully in "spot mode" (2 km acquisition of the target, bearing data only) but was never commanded to "acquire and track" the docking target. Parts obsolescence issues prevent the construction of current design AVGS units to support the NASA Exploration initiative. This flight proven AR&D technology is being modularized and upgraded with additional capabilities through the Hydra project at the Marshall Space Flight Center. Hydra brings a unique engineering approach and sensor architecture to the table, to solve the continuing issues of parts obsolescence and multiple sensor integration. This paper presents an approach to sensor hardware trades, to address the needs of future vehicles that may rendezvous and dock with the International Space Station (ISS). It will also discuss approaches for upgrading AVGS to address parts obsolescence, and concepts for modularizing the sensor to provide configuration flexibility for multiple vehicle applications. Options for complementary sensors to be integrated into the multi-head Hydra system will also be presented. Complementary sensor options include ULTOR, a digital image correlator system that could provide relative six-degree-of-freedom information independently from AVGS, and time-of-flight sensors, which determine the range between vehicles by timing pulses that travel from the sensor to the target and back. Common targets and integrated targets, suitable for use with the multi-sensor options in Hydra, will also be addressed.

Roe, Fred↗
NASA NTRSDate not supplied

In-Situ XRD/XRF to Support Life Detection on Mars

X-ray diffraction / X-ray fluorescence (XRD/XRF) analysis provides the most comprehensive mineralogical / compositional characterization of rocks and soils of any flight-capable technique. XRD data provide quantitative mineralogy (including abundance of X-ray amorphous materials) and crystal chemistry (structure, elemental composition and valence state), and XRF data provide complimentary major, minor, and some trace element abundances. Both types of data are important in evaluating habitability (environment of formation) and biosignature preservation/degradation (post-depositional diagenetic change). Whether or not a relict biosignature is detected, the mineral assemblage and its geochemistry can be used to determine the habitability of an ancient environment (e.g., salinity, pH, temperature), and to identify potential sources of energy for life (e.g., elements in different redox states). In this respect, a null result (a habitable environment lacking evidence of life) can play an important role in constraining the parameters of the search. Conversely, diagenetic alteration (taphonomic change) resulting from post-depositional variations in temperature, pressure or fluid chemistry can preserve evidence of biogenicity, erase such evidence completely or indeed can provide for post-depositional habitable conditions in the subsurface. XRD / XRF data are critical to these determinations. The CheMin instrument on the Mars Science Laboratory (MSL) Curiosity rover is the first XRD instrument flown in space. CheMin operates in transmission geometry with a Co X-ray source to minimize fluorescence from iron. Diffracted photons are collected with an energy-sensitive charge-coupled device (CCD). The position of the diffracted photons provides structural information for minerals, whereas the energy of sample-generated X-ray fluorescence photons provides elemental information, though these XRF data are qualitative. Mineralogical data from the CheMin XRD identified the three circumstances above: habitable depositional environments (e.g., Yellowknife Bay), habitable subsurface/diagenetic environments (e.g., throughout the Murray formation), and diagenetic conditions that may destroy evidence of habitability (e.g., oxidative and acidic environments at Vera Rubin ridge). Technological advances in X-ray technology and lessons learned from the operation of CheMin on Mars have resulted in a next-generation XRD/XRF, called CheMinX. Replacement of CheMin’s CCD with an array of hybrid pixel detectors and improvements in focusing optics dramatically decrease analysis time (15 minutes vs. 22 hours for MSL-CheMin) and result in a better angular resolution (0.18 vs. 0.30 °2θ for MSL-CheMin). This increased resolution improves mineral detection, including discrimination between types of pyroxenes, which is not possible with MSL-CheMin data. The hybrid pixel detectors do not require cooling like the MSL-CheMin CCD, therefore reducing the power needed to operate CheMinX. CheMinX has a silicon-drift detector (SDD) to measure fluoresced photons, enabling the quantification of major, minor, and some trace elements via XRF. XRD/XRF data are collected simultaneously in CheMinX, obviating the need for multiple compositional instruments. The CheMinX design also improves upon MSL-CheMin’s sample handling. Instead of sample cells on wheel, which are often not reusable and add complexity in commanding the instrument, CheMinX has single-use cells in a cartridge/dispenser configuration. Because of these improvements, CheMinX is an ideal instrument for Discovery-class life-detection missions, including Mars Life Explorer that was recommended for development in the Planetary Science and Astrobiology Decadal Survey 2023-2032.

E B Rampe↗
NASA NTRS1989

Reactive behavior, learning, and anticipation

Reactive systems always act, thinking only long enough to 'look up' the action to execute. Traditional planning systems think a lot, and act only after generating fairly precise plans. Each represents an endpoint on a spectrum. It is argued that primitive forms of reasoning, like anticipation, play an important role in reducing the cost of learning and that the decision to act or think should be based on the uncertainty associated with the utility of executing an action in a particular situation. An architecture for an adaptable reactive system is presented and it is shown how it can be augmented with a simple anticipation mechanism that can substantially reduce the cost and time of learning.

Whitehead, Steven D.↗
NASA NTRS2019

Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties

Properly assessing the asteroid threat depends on the knowledge of asteroid pre-entry parameters, such as size, velocity, mass, density, and strength. Although a vast number of possible bodies to study exist, such characterization of asteroid populations is currently limited by substantial costs associated with space rendezvous missions and rare meteorite findings. As asteroids fragment, ablate, and decelerate in the atmosphere, they emit light detectable by ground-based and space-borne instruments. Earth’s atmosphere, thus, becomes an accessible laboratory that enables impactor risk assessments by facilitating inference of the pre-entry parameters. These asteroid pre-entry conditions are typically deduced by modeling the entry and breakup physics that best reproduce the observed light or energy deposition curve. However, this process requires extensive manual trial-and-error of uncertain modeling parameters. Automating meteor modeling and inference would improve property distributions used in risk assessments and enable population characterization as more light curves become more readily available through the presence of space assets and ground-based camera networks. We previously developed a genetic algorithm to automate meteor modeling by using the fragment-cloud model (FCM) to search for the values of the FCM input parameters (e.g., diameter) that generate energy deposition profiles that match the observed one. Now, we apply deep learning to infer asteroid diameter, velocity, and density from observed energy deposition curves. We trained and tested our neural network models with synthetic energy deposition curves modeled using the FCM rubble pile implementation. We present an application of a 1D convolutional neural network and compare its performance to other attempted regressors and machine learning techniques, such as a fully connected neural network and Random Forest regression, to demonstrate its capabilities. We validate our model weights and approach using the Chelyabinsk, Tagish Lake, Benešov, Košice, and Lost City meteors.

Tarano, Ana Maria↗
NASA NTRS1988

Genetic algorithms for adaptive real-time control in space systems

Genetic Algorithms that are used for learning as one way to control the combinational explosion associated with the generation of new rules are discussed. The Genetic Algorithm approach tends to work best when it can be applied to a domain independent knowledge representation. Applications to real time control in space systems are discussed.

Vanderzijp, J.↗
NASA NTRS1993

NETS

NETS development tool provides environment for simulation and development of neural networks - computer programs that "learn" from experience. Written in ANSI standard C, program allows user to generate C code for implementation of neural network.

Baffes, Paul T.↗
NASA NTRS2002

Multi-Zone Liquid Thrust Chamber Performance Code with Domain Decomposition for Parallel Processing

Computational Fluid Dynamics (CFD) has considerably evolved in the last decade. There are many computer programs that can perform computations on viscous internal or external flows with chemical reactions. CFD has become a commonly used tool in the design and analysis of gas turbines, ramjet combustors, turbo-machinery, inlet ducts, rocket engines, jet interaction, missile, and ramjet nozzles. One of the problems of interest to NASA has always been the performance prediction for rocket and air-breathing engines. Due to the complexity of flow in these engines it is necessary to resolve the flowfield into a fine mesh to capture quantities like turbulence and heat transfer. However, calculation on a high-resolution grid is associated with a prohibitively increasing computational time that can downgrade the value of the CFD for practical engineering calculations. The Liquid Thrust Chamber Performance (LTCP) code was developed for NASA/MSFC (Marshall Space Flight Center) to perform liquid rocket engine performance calculations. This code is a 2D/axisymmetric full Navier-Stokes (NS) solver with fully coupled finite rate chemistry and Eulerian treatment of liquid fuel and/or oxidizer droplets. One of the advantages of this code has been the resemblance of its input file to the JANNAF (Joint Army Navy NASA Air Force Interagency Propulsion Committee) standard TDK code, and its automatic grid generation for JANNAF defined combustion chamber wall geometry. These options minimize the learning effort for TDK users, and make the code a good candidate for performing engineering calculations. Although the LTCP code was developed for liquid rocket engines, it is a general-purpose code and has been used for solving many engineering problems. However, the single zone formulation of the LTCP has limited the code to be applicable to problems with complex geometry. Furthermore, the computational time becomes prohibitively large for high-resolution problems with chemistry, two-equation turbulence model, and two-phase flow. To overcome these limitations, the LTCP code is rewritten to include the multi-zone capability with domain decomposition that makes it suitable for parallel processing, i.e., enabling the code to run every zone or sub-domain on a separate processor. This can reduce the run time by a factor of 6 to 8, depending on the problem.

Homayun K. Navaz↗
NASA NTRS2009

NASA Tech Briefs, November 2009

Topics covered include: Cryogenic Chamber for Servo-Hydraulic Materials Testing; Apparatus Measures Thermal Conductance Through a Thin Sample from Cryogenic to Room Temperature; Rover Attitude and Pointing System Simulation Testbed; Desktop Application Program to Simulate Cargo-Air-Drop Tests; Multimodal Friction Ignition Tester; Small-Bolt Torque-Tension Tester; Integrated Spacesuit Audio System Enhances Speech Quality and Reduces Noise; Hardware Implementation of a Bilateral Subtraction Filter; Simple Optoelectronic Feedback in Microwave Oscillators; Small X-Band Oscillator Antennas; Free-Space Optical Interconnect Employing VCSEL Diodes; Discrete Fourier Transform Analysis in a Complex Vector Space; Miniature Scroll Pumps Fabricated by LIGA; Self-Assembling, Flexible, Pre-Ceramic Composite Preforms; Flight-speed Integral Image Analysis Toolkit; Work Coordination Engine; Multi-Mission Automated Task Invocation Subsystem; Autonomously Calibrating a Quadrupole Mass Spectrometer; Determining Spacecraft Reaction Wheel Friction Parameters; Composite Silica Aerogels Opacified with Titania; Multiplexed Colorimetric Solid-Phase Extraction; Detecting Airborne Mercury by Use of Polymer/Carbon Films; Lattice-Matched Semiconductor Layers on Single Crystalline Sapphire Substrate; Pressure-Energized Seal Rings to Better Withstand Flows; Rollerjaw Rock Crusher; Microwave Sterilization and Depyrogenation System; Quantifying Therapeutic and Diagnostic Efficacy in 2D Microvascular Images; NiF2/NaF:CaF2/Ca Solid-State High-Temperature Battery Cells; Critical Coupling Between Optical Fibers and WGM Resonators; Microwave Temperature Profiler Mounted in a Standard Airborne Research Canister; Alternative Determination of Density of the Titan Atmosphere; Solar Rejection Filter for Large Telescopes; Automated CFD for Generation of Airfoil Performance Tables; Progressive Classification Using Support Vector Machines; Active Learning with Irrelevant Examples; A Data Matrix Method for Improving the Quantification of Element Percentages of SEM/EDX Analysis; Deployable Shroud for the International X-Ray Observatory; Improved Model of a Mercury Ring Damper; Optoelectronic pH Meter: Further Details; X-38 Advanced Sublimator; and Solar Simulator Represents the Mars Surface Solar Environment.

Source record↗
NASA NTRS2010

Sun-Earth Day: Reaching the Education Audience by Informal Means

For ten years the Sun-Earth Day program has promoted Heliophysics education to ever larger audiences through events centered on attractive annual themes. What originally started out as a one day event quickly evolved into a series of programs and events that occur throughout the year culminating with a celebration on or near the Spring Equinox. The events are often formal broadcasts or webcasts seeking to convey the science behind the latest solar-terrestrial mission discoveries. This has been quite successful, but it is clear that the younger generation increasingly depends on social networking approaches and informal news transmission for learning what is happening in the world around them. For 2010, the Sun-Earth Day team put emphasis on using informal approaches to bring the theme to the audience. The main event, a webcast from the NASA booth at the National Science Teachers Association (NSTA) annual meeting by the NASA EDGE group, took a lighthearted and offbeat approach to interviewing scientists and educators about Heliophysics news. NASA EDGE programs are unscripted and unpredictable, and that represents a different approach to getting the message across. The webcast was supplemented by a number of social networking avenues. The Sun-Earth Day program explored a wide range of social media applications including Facebook, Twitter, NING, podcasting, iPhone apps, etc. Each of these offers unique and effective methods to promote Heliophysics content and mission related highlights. The facebook site was quite popular and message posting there told the Sun-Earth Day story piece by piece. The same could be said of twittering and the tweetup held at the NSTA site. Has all of this been effective? Results are still being gathered, but anecdotal responses from the world seem very positive. What other methods might be used in the future to bring the science to a personal hands-on, interactive experience? Outcomes: Participants will: (1) Be introduced to the Sun-Earth Day program and its evolution through a decade of programs; (2) Hear about the methods used to communicate and educate through the years and how well they have worked; and (3) Be acquainted with the latest usage of social networking and informal education approaches and how well they have worked

Thieman, J.↗
NASA NTRS2006

Space Exploration: A Risk for Neural Stem Cells

During spaceflights beyond low Earth orbit, astronauts are exposed to potentially carcinogenic and tissue damaging galactic cosmic rays, solar proton events, and secondary radiation that includes neutrons and recoil nuclei produced by nuclear reactions in spacecraft walls or in tissue (1). Such radiation risk may present a significant health risk for human exploration of the moon and Mars. Emerging evidence that generation of new neurons in the adult brain may be essential for learning, memory, and mood (2) and that radiation is deleterious to neurogenesis (3-5) underscores a previously unappreciated possible risk to the cognitive functions and emotional stability of astronauts exposed to radiation in space. Here we use a novel reporter mouse line to identify at-risk populations of stem and progenitor cells in the brain and find, unexpectedly, that quiescent stem-like cells (rather than their rapidly dividing progeny) in the hippocampus constitute the most vulnerable cell population. This finding raises concerns about the possible risks facing astronauts on long duration space missions.

Encinas, Juan M.↗
NASA NTRS2015

U.S. Spacesuit Knowledge Capture Status and Initiatives in Fiscal Year 2014

Since its 2008 inception, the NASA U.S. Spacesuit Knowledge Capture (KC) program has shared historical spacesuit information with engineers and other technical team members to expand their understanding of the spacesuit's evolution, known capability and limitations, and future desires and needs for its use. As part of the U.S. Spacesuit KC program, subject-matter experts have delivered presentations, held workshops, and participated in interviews to share valuable spacesuit lessons learned to ensure this vital information will survive for existing and future generations to use. These events have included spacesuit knowledge from the inception of NASA's first spacesuit to current spacesuit design. To ensure that this information is shared with the entire NASA community and other interested or invested entities, these KC events were digitally recorded and transcribed to be uploaded onto several applicable NASA Web sites. This paper discusses the various Web sites that the KC events are uploaded to and possible future sites that will channel this information.

Chullen, Cinda↗
NASA NTRS2010

Lessons Learned in Architecting Human Spaceflight Programs

This paper discusses the fundamentals of architecting a major human spaceflight program and the lessons that can be learned from Constellation. Constellation is/was NASA's program to implement a new generation of human exploration missions to the moon and beyond. It is/was a tightly-coupled program where a unique set of architectural challenges can be seen and evaluated to better understand how architecting of such systems can be improved upon in the future. While the specific issues discussed in this paper derive from the current Constellation architecture they share threads with previously-crewed systems including Apollo and Shuttle and are likely to be common to any human exploration system or system of significant technical and programmatic complexity.

Muirhead, Brian↗
NASA NTRS2021

Monte Carlo Tree Search Methods for the Earth-Observing Satellite Scheduling Problem

This work explores on-board planning for the single spacecraft, multiple ground station Earth-observing satellite scheduling problem through artificial neural network function approximation of state–action value estimates generated by Monte Carlo tree search (MCTS). An extensive hyperparameter search is conducted for MCTS on the basis of performance, safety, and downlink opportunity utilization to determine the best hyperparameter combination for data generation. A hyperparameter search is also conducted on neural network architectures. The learned behavior of each network is explored, and each network architecture’s robustness to orbits and epochs outside of the training distributions is investigated. Furthermore, each algorithm is compared with a genetic algorithm, which serves to provide a baseline for optimality. MCTS is shown to compute near-optimal solutions in comparison to the genetic algorithm. The state–action value networks are shown to match or exceed the performance of MCTS in six orders of magnitude less execution time, showing promise for execution on board spacecraft.

Adam P. Herrmann↗
NASA NTRSDate not supplied

Improving Sim-to-Real Transfer in Vision-Based Robot Navigation Via Instance-Level GAN-Based Data Augmentation

Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.

artificial intelligence↗