Search NASA⌕ Search

SEARCH · Search NASA

Results for “Association 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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

Lcross Lunar Impactor - Lessons Learned from a Small Satellite Mission

The Lunar CRater Observation and Sensing Satellite (LCROSS) launched with the Lunar Reconnaissance Orbiter (LRO) on June 18, 2009. While the science purpose of the LCROSS mission was to determine the presence of water-ice in a permanently-shadowed crater on the moon, the functional purpose was to be a pioneer for future low-cost, risk-tolerant small satellite NASA missions. Recent strategic changes at the Agency level have only furthered the importance of small satellite missions. NASA Ames Research Center and its industry partner, Northrop-Grumman, initiated this spacecraft project two-years after its co-manifest mission had started, with less than one-fifth the budget. With a $79M total cost cap (including operations and reserves) and 31-months until launch, LCROSS needed a game-changing approach to be successful. At the LCROSS Confirmation Review, the ESMD Associate Administrator asked the Project team to keep a close record of lessons learned through the course of the mission and share their findings with the Agency at the end of the mission. This paper summarizes the Project, the mission, its risk position, and some of the more notable lessons learned.

Andrews, Daniel↗
NASA NTRS2011

Mission X: Train Like an Astronaut. International Fitness Challenge

The Mission X, Train like an Astronaut, pilot project was a 2-year effort directed by the International Life Science Working Group. The pilot was funded by the Human Research Program and was lead by the Human Research Program Education and Outreach (HRPEO) project and supported by a group of space agencies providing in-kind resources. The aim was to identify an international educational outreach concept that would promote a life science topic utilizing the education and outreach expertise of the various space agencies working on the utilization of the International Space Station. This in turn serves as an inspiration for the younger generation to aspire to go further in school, and provides insight into the capability of a participating country to ensure the effort provided value for their communities and children. The pilot project developed the necessary tools to promote communications between the partners and to use materials and expertise from all the countries? space agencies. The Mission X Website (trainlikeanastronaut.org) provided a single repository for the educational activities as well as a place for the Challenge Teams to provide their progress in the international fitness challenge. It also added to the International flavor as different countries were able to share and learn about what was happening with all those involved in the 6-week challenge period. A point system was utilized to promote constructive, cooperative competition in which 4164 students participated. The points were used to help FitKid, Astro Charlie, "Walk-To-The-Moon". The 18 physical and educational Mission X activities were made available on the Mission X website in seven languages. The Mission X pilot project was considered a success in 1) the design, development, and implementation of the multi-language website, 2) the expansion of healthy lifestyle awareness, and 3) the concept for drawing an international educational community together to highlight global topics in association with human space exploration. Metrics (70 post-event surveys) and lessons learned were collated and assessed. Key Lessons Learned were 1) foster and strengthen partnerships at all levels, 2) enhance and standardize MX Training, and 3) further expansion of activities and methods to teach the importance of fitness and nutrition. Methods used to teach the importance of nutrition and fitness are provided in the report.

Lloyd, Charles↗
NASA NTRS1998

Preliminary Work for Examining the Scalability of Reinforcement Learning

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Clouse, Jeff↗
NASA NTRS2020

Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation System

Tropical cyclones are one of the costliest natural disasters globally because of the wide range of associated hazards. Thus, an accurate diagnostic model for tropical cyclone intensity can save lives and property. There are a number of existing techniques and approaches that diagnose tropical cyclone wind speed using satellite data at a given time with varying success. This paper presents a deep learning-based objective, diagnostic estimate of tropical cyclone intensity from infrared satellite imagery with 13.24 kt Root Mean Squared Error (RMSE). In addition, a visualization portal in a production system is presented that displays deep learning output and contextual information for end users, one of the first of its kind.

Manil Maskey↗
NASA NTRS2011

Lessons Learned from the Space Shuttle Engine Cutoff System (ECO) Anomalies

The Space Shuttle Orbiter's main engine cutoff (ECO) system first failed ground checkout in April, 2005 during a first tanking test prior to Return-to-Flight. Despite significant troubleshooting and investigative efforts that followed, the root cause could not be found and intermittent anomalies continued to plague the Program. By implementing hardware upgrades, enhancing monitoring capability, and relaxing the launch rules, the Shuttle fleet was allowed to continue flying in spite of these unexplained failures. Root cause was finally determined following the launch attempts of STS-122 in December, 2007 when the anomalies repeated, which allowed drag-on instrumentation to pinpoint the fault (the ET feedthrough connector). The suspect hardware was removed and provided additional evidence towards root cause determination. Corrective action was implemented and the system has performed successfully since then. This white paper presents the lessons learned from the entire experience, beginning with the anomalies since Return-to-Flight through discovery and correction of the problem. To put these lessons in better perspective for the reader, an overview of the ECO system is presented first. Next, a chronological account of the failures and associated investigation activities is discussed. Root cause and corrective action are summarized, followed by the lessons learned.

Martinez, Hugo E.↗
NASA NTRS2014

Distributed System Design Checklist

This report describes a design checklist targeted to fault-tolerant distributed electronic systems. Many of the questions and discussions in this checklist may be generally applicable to the development of any safety-critical system. However, the primary focus of this report covers the issues relating to distributed electronic system design. The questions that comprise this design checklist were created with the intent to stimulate system designers' thought processes in a way that hopefully helps them to establish a broader perspective from which they can assess the system's dependability and fault-tolerance mechanisms. While best effort was expended to make this checklist as comprehensive as possible, it is not (and cannot be) complete. Instead, we expect that this list of questions and the associated rationale for the questions will continue to evolve as lessons are learned and further knowledge is established. In this regard, it is our intent to post the questions of this checklist on a suitable public web-forum, such as the NASA DASHLink AFCS repository. From there, we hope that it can be updated, extended, and maintained after our initial research has been completed.

Hall, Brendan↗
NASA NTRS2017

Interactive Exploration Robots: Human-Robotic Collaboration and Interactions

For decades, NASA has employed different operational approaches for human and robotic missions. Human spaceflight missions to the Moon and in low Earth orbit have relied upon near-continuous communication with minimal time delays. During these missions, astronauts and mission control communicate interactively to perform tasks and resolve problems in real-time. In contrast, deep-space robotic missions are designed for operations in the presence of significant communication delay - from tens of minutes to hours. Consequently, robotic missions typically employ meticulously scripted and validated command sequences that are intermittently uplinked to the robot for independent execution over long periods. Over the next few years, however, we will see increasing use of robots that blend these two operational approaches. These interactive exploration robots will be remotely operated by humans on Earth or from a spacecraft. These robots will be used to support astronauts on the International Space Station (ISS), to conduct new missions to the Moon, and potentially to enable remote exploration of planetary surfaces in real-time. In this talk, I will discuss the technical challenges associated with building and operating robots in this manner, along with lessons learned from research conducted with the ISS and in the field.

Fong, Terry↗
NASA NTRSDate not supplied

Generation of Continental Scale Percent Tree Cover Product Using Deep-learning and Multi-scale Remote Sensing Data

Spatially explicit percent tree cover (TC) estimation is critical for mapping forest aboveground biomass and its dynamics. While various TC products have been developed, there has not been a generalized framework that can be applied to diverse terrestrial ecosystems due to underlain extreme complexities. Deep learning algorithms can learn a spatial pattern and radiometric characteristics of tree canopy as a robust approximation of physical or empirical models, and thus have emerged as promising and efficient tools for large-scale TC mapping. In this study, we synergistically use very high-resolution aerial imageries (National Agriculture Imagery Program, NAIP) and medium resolution Landsat data to map continental-scale TC (CONUS and Mexico) through a hierarchical deep learning approach (Convolutional Neural Network), i.e., NAIP TC generated from a NAIP model is utilized to train a Landsat model. The produced TC product (hereafter, NEX-TC) is able to capture the spatial pattern of TC distribution and its changes driven by natural disturbance and human land management. We further explore and analyze the reliability and potential uncertainty of the NEX-TC by comparing it to lidar- (lidar-TC), National Land Cover Database (NLCD-TC), and MODIS Vegetation Continuous Field (MODIS-TC). This evaluation practice reveals that TC products based on passive optical sensors tend to underestimate TC across all land cover types while Landsat-based TCs (i.e., NEX-TC & NLCD-TC) perform better than the coarser MODIS TC estimate. Our results show that the NEX-TC is generally comparable to NLCD-TC but it particularly outperforms NLCD-TC and MODIS-TC over the dense forests where lidar-TC indicates >80% TC. These results indicate that our hierarchical deep learning approach and TC product will be effective and useful for characterizing large-scale tree cover and possibly associated carbon dynamics.

Landsat↗
NASA NTRS1995

Line Pilots' Attitudes about and Experience with Flight Deck Automation: Results of an International Survey and Proposed Guidelines

A survey of line pilots' attitudes about flight deck automation was conducted by the Royal Air Force Institute of Aviation Medicine (RAF IAM, Farnborough, UK) under the sponsorship of the United Kingdom s Civil Aviation Authority and in cooperation with IATA (the International Air Transport Association). Survey freehand comments given by pilots operating 13 types of commercial transports across five manufacturers (Airbus, Boeing, British Aerospace, Lockheed, and McDonnell-Douglas) and 57 air carriers/organizations were analyzed by NASA. These data provide a "lessons learned" knowledge base which may be used for the definition of guidelines for flight deck automation and its associated crew interface within the High Speed Research Program. The aircraft chosen for analysis represented a progression of levels of automation sophistication and complexity, from "Basic" types (e.g., B727, DC9), through "Transition" types (e.g., A300, Concorde), to two levels of glass cockpits (e.g., Glass 1: e.g., A310; Glass 2: e.g., B747-400). This paper reports the results of analyses of comments from pilots flying commercial transport types having the highest level of automation sophistication (B757/B767, B747-400, and A320). Comments were decomposed into five categories relating to: (1) general observations with regard to flight deck automation; comments concerning the (2) design and (3) crew understanding of automation and the crew interface; (4) crew operations with automation; and (5) personal factors affecting crew/automation interaction. The goal of these analyses is to contribute to the definition of guidelines which may be used during design of future aircraft flight decks.

Rudisill, Marianne↗
NASA NTRSDate not supplied

Quantum Hardware-Enabled Molecular Dynamics via Transfer Learning

The ability to perform ab initio molecular dynamics simulations using potential energy surfaces provided by quantum computers would open the door to virtually exact dynamics for a variety of chemical and biochemical systems, with impacts on catalysis and biophysics. Nonetheless, performing molecular dynamics on surfaces produced by quantum hardware has been hampered by the noisy energies typically produced by quantum computers and challenges associated with computing gradients and scaling to large systems interest. A recent set of advances in machine learning, known as transfer learning, provides a new path forward for molecular dynamics simulations on quantum hardware. Transfer learning offers a workaround, where one first trains models on larger, less accurate classical datasets and then refines them on smaller, more accurate quantum datasets. We explore this approach by training machine learning models to predict a molecule's potential energy based on its geometric structure using Behler-Parrinello neural networks. When successfully trained, the model enables energy gradient predictions necessary for dynamic simulations. To reduce the quantum resources needed, the model is initially trained with data derived from classical density functional theory and subsequently refined with a smaller dataset obtained from a variational quantum eigensolver optimization of the unitary coupled cluster ansatz. We show that this approach significantly reduces the size of the needed quantum training dataset while capturing the high accuracies needed within quantum chemistry simulations. The success of this two-step training method opens more opportunities to apply machine learning models on quantum data, a significant stride towards efficient quantum-classical hybrid computational models.

quantum computing↗
NASA NTRS2018

Generating Exploration Mission-3 Trajectories to a 9:2 NRHO using Machine Learning

The purpose of this thesis is to design a machine learning algorithm platform that provides expanded knowledge of mission availability through a launch season by improving trajectory resolution and introducing launch mission forecasting. The specific scenario addressed in this paper is one in which data is provided for four deterministic translational maneuvers through a mission to a Near Rectilinear Halo Orbit (NRHO) with a 9:2 synodic frequency. Current launch availability knowledge under NASA's Orion Orbit Performance Team is established by altering optimization variables associated to given reference launch epochs. This current method can bean abstract task and relies on an orbit analyst to structure a mission based on an established mission design methodology associated to the performance of Orion and NASA's Space Launch System. Introducing a machine learning algorithm trained to construct mission scenarios within the feasible range of known trajectories reduces the required interaction of the orbit analyst by removing the needed step of optimizing the orbit to fit an expected translational response required of the spacecraft. In this study, k-Nearest Neighbor and Bayesian Linear Regression successfully predicted classical orbital elements for the launch windows observed. However both algorithms had limitations due to their approaches to model fitting. Training machine learning algorithms off of classical orbital elements introduced a repetitive approach to reconstructing mission segments for different arrival opportunities through the launch window and can prove to be a viable method of launch window scan generation for future missions.

Guzman, Esteban↗
NASA NTRS1991

Learning control of inverted pendulum system by neural network driven fuzzy reasoning: The learning function of NN-driven fuzzy reasoning under changes of reasoning environment

Whereas conventional fuzzy reasonings are associated with tuning problems, which are lack of membership functions and inference rule designs, a neural network driven fuzzy reasoning (NDF) capable of determining membership functions by neural network is formulated. In the antecedent parts of the neural network driven fuzzy reasoning, the optimum membership function is determined by a neural network, while in the consequent parts, an amount of control for each rule is determined by other plural neural networks. By introducing an algorithm of neural network driven fuzzy reasoning, inference rules for making a pendulum stand up from its lowest suspended point are determined for verifying the usefulness of the algorithm.

Hayashi, Isao↗
NASA NTRS2000

Tropical Rainfall Measuring Mission (TRMM) Satellite: Assessment and Lessons Learned After Three Flight Years

Tropical Rain Measuring Mission (TRMM) is an experiment in measuring rainfall and the associated latent heat release from space. A primary goal is to help in initializing the large-scale weather and climate models for crucial improvement in location and profile of atmospheric heat release. For this, precipitation and latent heating profiles are needed. This goal requires cloud-resolving models. The basic approach was to use passive microwave and rain radar in combination to issue a limited number of products, improving the retrieval algorithms by testing during flight, so the products are updated annually. Despite a tight budget, the TRMM observatory and data system worked excellently from launch for the past three years. A basic philosophy has been to do physical validation as much as possible, in preference to empirical adjustments for algorithm improvement. Additional information is contained in the original extended abstract.

Simpson, Joanne↗
NASA NTRSDate not supplied

Communication Demand in the National Airspace - A Federated Learning Approach

Within the national airspace system (NAS), efficient use of spectrum remains a challenge; as UAS and UAM missions evolve, the amount of mission-critical aircraft communications are expected to significantly grow. To accommodate the increased demand, NASA Glenn Research Center is investigating artificial intelligence approaches that could dynamically allocate spectrum; however, these solutions are driven by communication and aviation data items, many of which are not directly available. One such cornerstone data item is communication demand, parameterizing the needs within a sector in terms that may directly inform spectrum allocation, such as channel access duration, bandwidth, and modulation type. This paper considers the complexity of predicting communication demand as a function of NAS behaviors. Unlike prior prediction work in communications, this research must consider how the NAS may be impacted by external factors - such as convective weather and closures - rather than estimating demand from time-series forecasting alone. Much of this research considers a federated learning design to predict communication events in terms of the type of event occurring (sector coordination, conflict resolution, etc.). To do so, an investigation of products from Sherlock Data Warehouse is conducted, identifying the trends, sufficiency, and correlations of each product to identified events. Additionally, a preliminary discussion for inferring associations between these event types and their communication parameters (duration, bandwidth, modulation) is presented. By utilizing federated learning, imbalances in the types of events and data present throughout the NAS can inform local models without impairing global training. Furthermore, the two-stage approach proposed allows for robust and speculative communication modelling, as communication techniques continue to evolve. As a result, this model enables a generalized approach to understanding NAS communications which is able to inform long-term changes to aviation spectrum management.

Nathan Schimpf↗
NASA NTRSDate not supplied

A Federated Learning Approach to Predicting Communication Demand in the National Airspace

Within the national airspace system (NAS), efficient use of spectrum remains a challenge; as UAS and UAM missions evolve, the amount of mission-critical aircraft communications are expected to significantly grow. To accommodate the increased demand, NASA Glenn Research Center is investigating artificial intelligence approaches that could dynamically allocate spectrum; however, these solutions are driven by communication and aviation data items, many of which are not directly available. One such cornerstone data item is communication demand, parameterizing the needs within a sector in terms that may directly inform spectrum allocation, such as channel access duration, bandwidth, and modulation type. This paper considers the complexity of predicting communication demand as a function of NAS behaviors. Unlike prior prediction work in communications, this research must consider how the NAS may be impacted by external factors - such as convective weather and closures - rather than estimating demand from time-series forecasting alone. Much of this research considers a federated learning design to predict communication events in terms of the type of event occurring (sector coordination, conflict resolution, etc). To do so, an investigation of products from Sherlock Data Warehouse is conducted, identifying the trends, sufficiency, and correlations of each product to identified events. Additionally, a preliminary discussion for inferring associations between these event types and their communication parameters (duration, bandwidth, modulation) is presented. By utilizing federated learning, imbalances in the types of events and data present throughout the NAS can inform local models without impairing global training. Furthermore, the two-stage approach proposed allows for robust and speculative communication modelling, as communication techniques continue to evolve. As a result, this model enables a generalized approach to understanding NAS communications which is able to inform long-term changes to aviation spectrum management.

Nathan Schimpf↗
NASA NTRS2001

Solving and Learning Soft Temporal Constraints: Experimental Scenario and Examples

Soft temporal constraint problems allow to describe in a natural way scenarios where events happen over time and preferences are associated to event distances and durations. However, sometimes such local preferences are difficult to set, and it may be easier instead to associate preferences to some complete solutions of the problem. To model everything in a uniform way via local preferences only, and also to take advantage of the existing constraint solvers which exploit only local preference use machine learning techniques which learn the local preferences from the global ones. In this paper we describe the existing framework for both solving and learning preferences in temporal constraint problems, the implemented modules, the experimental scenario, and preliminary results on some examples.

Rossi, F.↗
NASA NTRS1990

Investigating motion sickness using the conditioned taste aversion paradigm

The avoidance of foods which are associated with uncomfortable or aversive internal states has long been recognized. Many people are aware, either directly or via anecdotal reports, of individuals who avoid foods which were eaten just before the onset of sickness. Awareness of this phenomenon can be traced to the writings of John Locke. The disruption of diet during cancer therapy is sometimes ascribed to the attribution of an unpleasant quality to foods eaten preceding the sickness induced by therapy itself. In addition, it has long been recognized by the manufacturers of rodent poisons that animals avoid the injection of food treated with nonlethal doses of poison. An important part of the laboratory study of this phenomenon was directed toward studying the role learning plays in this type of avoidance behavior. Following the lead of Garcia and his associates, this avoidance has come to be interpreted as arising from a form of classical conditioning. In typical laboratory studies of this behavior, a novel food is ingested just prior to exposure to some stimulus, commonly poisoning or irradiation, which produces illness. Following the terminology of classical conditioning, it is common to describe this procedure as one of 'pairing' a conditioned stimulus (CS), the novel food, with an unconditioned stimulus (US), the illness induced by toxicosis or irradiation. Avoidance of the food in succeeding feeding opportunities is viewed as a learned response or a conditioned taste aversion (CTA). Garcia et al. asserted that motion sickness could produce 'gustatory' aversions, but passive motion was first reported as an US to establish CTA by Green and Rachlin. The purpose is to review the manner in which CTA has been used to study motion sickness. Numerous reviews concentrating on other aspects of CTA are available in the existing literature. Readers are encouraged to consult the various papers and edited books for extensive information on other aspects of this literature.

Robert A Fox↗