Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Transfer 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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

MULTI-OBJECTIVE REINFORCEMENT LEARNING FOR LOW-THRUST TRANSFER DESIGN BETWEEN LIBRATION POINT ORBITS

Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective reinforcement learning algorithm used to construct low-thrust transfers between periodic orbits in multi-body systems. Previous implementations of MRPPO have relied on a predefined reference transfer to successfully train each policy. In this paper, an algorithmic modification labeled the ‘moving reference’, is introduced to autonomously construct these reference trajectories during training. With this modification, MRPPO is used to recover various low-thrust transfers between two periodic orbits in the Earth-Moon circular restricted three-body problem to solve a multi-objective optimization problem. These results are then compared with the solutions recovered via a gradient descent optimization scheme to validate the performance of MRPPO with the moving reference modification

Christopher John Sullivan↗
NASA NTRS2021

Multi-objective Reinforcement Learning for Low-thrust Transfer Design Between Libration Point Orbits

Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective rein- forcement learning algorithm used to construct low-thrust transfers between pe- riodic orbits in multi-body systems. Previous implementations of MRPPO have relied on a predefined reference transfer to successfully train each policy. In this paper, an algorithmic modification labeled the ‘moving reference’, is introduced to autonomously construct these reference trajectories during training. With this modification, MRPPO is used to recover various low-thrust transfers between two periodic orbits in the Earth-Moon circular restricted three-body problem to solve a multi-objective optimization problem. These results are then compared with the solutions recovered via a gradient descent optimization scheme to validate the performance of MRPPO with the moving reference modification.

Anderson, Rodney L.↗
NASA NTRS2021

Multi-objective Reinforcement Learning for Low-thrust Transfer Design Between Libration Point Orbits

Multi-Reward Proximal Policy Optimization (MRPPO) is a multi-objective rein- forcement learning algorithm used to construct low-thrust transfers between pe- riodic orbits in multi-body systems. Previous implementations of MRPPO have relied on a predefined reference transfer to successfully train each policy. In this paper, an algorithmic modification labeled the ‘moving reference’, is introduced to autonomously construct these reference trajectories during training. With this modification, MRPPO is used to recover various low-thrust transfers between two periodic orbits in the Earth-Moon circular restricted three-body problem to solve a multi-objective optimization problem. These results are then compared with the solutions recovered via a gradient descent optimization scheme to validate the performance of MRPPO with the moving reference modification.

Anderson, Rodney L↗
NASA NTRS2022

A Deep Learning Approach to Fast Radiative Transfer

Due to the sheer volume of data, leveraging satellite instrument observations effectively in a data assimilation context for numerical weather prediction or for remote sensing requires a radiative transfer model as an observation operator that is both fast and accurate at the same time. Physics-based line-by-line radiative transfer (RT) models fulfil the requirement for accuracy, but are too slow and too costly in computational terms for operational applications. Therefore, fast methods were developed to be able to perform fast RT calculations using techniques such as spectral sampling or pre-computed look-up tables. The operational fast models currently calculate the absorption and scattering coefficients from the pre-computed regression coefficients and atmospheric state and cloud profiles. As a novel solution to this problem, this work investigates a deep learning approach to replace the regression coefficients in the fast RT models. A selection of hidden-layer neural network configurations is trained against atmospheric transmittance profile data computed by an accurate line-by-line model and their performance is evaluated and their advantages and disadvantages are discussed.

Machine learning↗
NASA NTRS1991

Neural network representation and learning of mappings and their derivatives

Discussed here are recent theorems proving that artificial neural networks are capable of approximating an arbitrary mapping and its derivatives as accurately as desired. This fact forms the basis for further results establishing the learnability of the desired approximations, using results from non-parametric statistics. These results have potential applications in robotics, chaotic dynamics, control, and sensitivity analysis. An example involving learning the transfer function and its derivatives for a chaotic map is discussed.

White, Halbert↗
NASA NTRS1992

Training effectiveness assessment: Methodological problems and issues

The U.S. military uses a large number of simulators to train and sustain the flying skills of helicopter pilots. Despite the enormous resources required to purchase, maintain, and use those simulators, little effort has been expended in assessing their training effectiveness. One reason for this is the lack of an evaluation methodology that yields comprehensive and valid data at a practical cost. Some of these methodological problems and issues that arise in assessing simulator training effectiveness, as well as problems with the classical transfer-of-learning paradigm were discussed.

Cross, Kenneth D.↗
NASA NTRS2005

Software Engineering Research/Developer Collaborations in 2004 (C104)

In 2004, six collaborations between software engineering technology providers and NASA software development personnel deployed a total of five software engineering technologies (for references, see Section 7.2) on the NASA projects. The main purposes were to benefit the projects, infuse the technologies if beneficial into NASA, and give feedback to the technology providers to improve the technologies. Each collaboration project produced a final report (for references, see Section 7.1). Section 2 of this report summarizes each project, drawing from the final reports and communications with the software developers and technology providers. Section 3 indicates paths to further infusion of the technologies into NASA practice. Section 4 summarizes some technology transfer lessons learned. Section 6 lists the acronyms used in this report.

Pressburger, Tom↗
NASA NTRS2006

Software Engineering Research/Developer Collaborations in 2005

In CY 2005, three collaborations between software engineering technology providers and NASA software development personnel deployed three software engineering technologies on NASA development projects (a different technology on each project). The main purposes were to benefit the projects, infuse the technologies if beneficial into NASA, and give feedback to the technology providers to improve the technologies. Each collaboration project produced a final report. Section 2 of this report summarizes each project, drawing from the final reports and communications with the software developers and technology providers. Section 3 indicates paths to further infusion of the technologies into NASA practice. Section 4 summarizes some technology transfer lessons learned. Also included is an acronym list.

Pressburger, Tom↗
NASA NTRSDate not supplied

Using Federated Learning to Overcome Data Gravity in Space

Humans intend to take longer missions to outer space. Understanding the impact that space has on human health is paramount to the success of these missions. Controlled experiments with model organisms are run to infer the impact of space conditions on human health, but the data these experiments generate are too large to transfer to Earth for building models. The same is true for space-relevant data generated on Earth. Ideally, these datasets should be combined to improve statistical power and model accuracy without having to transfer data. Federated learning is such a method which trains an algorithm across decentralized computing systems, each of which has their own local copy of training and testing data. In this research, made possible by NASA@Work, the AI for Life in Space group at NASA demonstrates the use of federated learning to train an ensemble of causality inference models on a combination of data residing on the International Space Station (ISS) and in the cloud. Our work leverages CRISP, a causal inference platform developed during the 2020 Frontier Development Lab’s “Astronaut Health Challenge.” We also leverage the OpenFL federated learning library which was collaboratively developed at Intel and UPenn. We used publicly available data from the NASA Ames Life Sciences Data Archive to identify features in ionizing radiation experiments as causal of changes in cardiac blood velocity. This research demonstrates, for the first time, the possibility of running machine learning algorithms on datasets separated by astronomical distances. In this experiment, all the data were generated in terra, half of which were transferred to the ISS and analyzed on the Spaceborne Computer. In the future, our research will leverage federated learning on data generated in situ on the ISS with data generated terrestrially to predict the impact of spaceflight on mammalian female reproductive capacity.

James Casaletto↗
NASA NTRS1996

The cerebellum: a neuronal learning machine?

Comparison of two seemingly quite different behaviors yields a surprisingly consistent picture of the role of the cerebellum in motor learning. Behavioral and physiological data about classical conditioning of the eyelid response and motor learning in the vestibulo-ocular reflex suggests that (i) plasticity is distributed between the cerebellar cortex and the deep cerebellar nuclei; (ii) the cerebellar cortex plays a special role in learning the timing of movement; and (iii) the cerebellar cortex guides learning in the deep nuclei, which may allow learning to be transferred from the cortex to the deep nuclei. Because many of the similarities in the data from the two systems typify general features of cerebellar organization, the cerebellar mechanisms of learning in these two systems may represent principles that apply to many motor systems.

Non-NASA Center↗
NASA NTRS2024

3D Cloud Masking Across A Broad Swath Using Multi-Angle Polarimetry and Deep Learning

Understanding the 3-dimensional structure of clouds is of crucial importance to modeling our changing climate. Active sensors, such as radar and lidar, provide accurate vertical cloud profiles, but are mostly restricted to along-track sampling. Passive sensors can capture a wide swath, but struggle to see beneath cloud tops. In essence, both types of products are restricted to two dimensions: as a cross-section in the active case, and an image in the passive case. However, multi-angle sensor configurations contain implicit information about 3D structure, due to parallax and atmospheric path differences. Extracting that implicit information can be challenging, requiring computationally expensive radiative transfer techniques. Machine learning, as an alternative, may be able to capture some of the complexity of a full 3D radiative transfer solution with significantly less computational expense. In this work, we make three contributions towards understanding 3D cloud structure from multi-angle polarimetry. First, we introduce a large-scale, publicly available dataset that fuses existing cloud products into a format more amenable to machine learning. This dataset treats multi-angle polarimetry as an input, and radar-based vertical cloud profiles as an output. Second, we describe and evaluate strong baseline machine learning models based that predict these profiles from the passive imagery. Notably, these models are trained only on center-swath labels, but can predict cloud profiles over the entire passive imagery swath. Third, we leverage the information-theoretic nature of machine learning to draw conclusions about the relative utility of various sensor configurations, including spectral channels, viewing angles, and polarimetry. These findings have implications for Earth-observing missions such as NASA’s Plankton, Aerosol, Cloud-ocean Ecosystem (PACE) and Atmosphere Observing System (AOS) missions, as well as in informing future applications of computer vision to atmospheric remote sensing.

clouds↗
NASA NTRSDate not supplied

A Machine Learning Framework for Error Compensation in Radiative Transfer Calculations

Radiative heat transfer influences the amount of heat flux transferred to the surface of the hypersonic vehicle, which is essential to evaluate the performance of thermal protection systems. The radiative heat flux is found to be computationally prohibitive while accounting for the variation in spatial, angular, and spectral domains. A new methodology has been recently developed to alleviate the cost of computation in the spectral domain by constructing flow-agnostic reduced-order models (ROMs). The developed spectral ROM databases provide grouping strategies that account for non-equilibrium absorption and emission as well as interaction between disparate species due to spectral overlap in associated radiative processes. However, the developed ROMs need to be optimized for a specific combination of interacting gas species and would need to re-calibrated in case individual species are added/omitted. In this work, we use various machine learning (ML) techniques to approximate the radiative intensities determined by a ROM optimized for a specific gas mixture. The ML model relies on the ROM databases developed for a single species which ignores any spectral overlap. Thus, radiation evaluation starts with a simple summation of radiative intensities predicted using these non-calibrated ROMs for the contributing species. The ML framework then provides a correction to account for the interplay in the frequency, i.e., emission of photons by one species and absorption by another, and yields mixture-specific radiation fields. Once trained on the individual ROM databases, the ML framework offers instantaneous corrections that serves as a time/cost effective alternative to the optimization of ROMs for a specific gas mixture. The ML framework is trained on both the high fidelity and ROM evaluated line of sight (LOS) data from Orion, Stardust, and FIRE II cases to obtain a general purpose correction model for earth re-entry scenarios when radiation contributions from both atomic nitrogen and atomic oxygen are considered. A geometric length scale parameter is used in the training process to account for errors introduced in the ROM databases as a consequence of high optical thickness. The efficacy of the ML framework is underscored through extensive analysis of train and test errors with respect to all the re-entry scenarios. The applicability of such an ML framework was further corroborated by embedding it in a state-of-the-art US3D - NERO system for determining the radiative heat flux transferred to the hypersonic vehicle surface.

Radiation↗
NASA NTRS2015

Effects of False Tilt Cues on the Training of Manual Roll Control Skills

This paper describes a transfer-of-training study performed in the NASA Ames Vertica lMotion Simulator. The purpose of the study was to investigate the effect of false tilt cues on training and transfer of training of manual roll control skills. Of specific interest were the skills needed to control unstable roll dynamics of a mid-size transport aircraft close to the stall point. Nineteen general aviation pilots trained on a roll control task with one of three motion conditions: no motion, roll motion only, or reduced coordinated roll motion. All pilots transferred to full coordinated roll motion in the transfer session. A novel multimodal pilot model identification technique was successfully applied to characterize how pilots' use of visual and motion cues changed over the course of training and after transfer. Pilots who trained with uncoordinated roll motion had significantly higher performance during training and after transfer, even though they experienced the false tilt cues. Furthermore, pilot control behavior significantly changed during the two sessions, as indicated by increasing visual and motion gains, and decreasing lead time constants. Pilots training without motion showed higher learning rates after transfer to the full coordinated roll motion case.

simulators↗