Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 397 records · Page 22

Using Knowledge-Based Systems to Support Learning of Organizational Knowledge: A Case Study

This paper describes the deployment of a knowledge system to support learning of organizational knowledge at the Jet Propulsion Laboratory (JPL), a US national research laboratory whose mission is planetary exploration and to 'do what no one has done before.' Data collected over 19 weeks of operation were used to assess system performance with respect to design considerations, participation, effectiveness of communication mechanisms, and individual-based learning. These results are discussed in the context of organizational learning research and implications for practice.

knowledge management↗

Learning from Space Entrepreneurs

The early days of rocketry and space exploration in the United States were marked by incredibly rapid progress: a seemingly endless parade of firsts. Not coincidentally, this period also saw more than its fair share of failure, especially in the infamous "kaputnik" days prior to the successful launch of Explorer. Without a standard canon of known quantities to turn to, the early pioneers of rocketry and space flight were forced to dream up new ideas that ranged from the elegant to the bizarre and to accept the fact that the price of radical progress is occasional failure. Nowadays, rapid prototyping and testing have slowed, as we rely more and more on the extensive knowledge pined by our predecessors and on the embarrassment of riches modern engineers get from computational modeling and computer assisted design. In many cases, this leads to much improved or phenomenally more efficient designs. It also, however, fosters a culture so terrified of failure that we over-engineer and overanalyze everything, often tweaking designs for decades before a new system takes flight. (This is not a problem unique to rockets; the same phenomenon seems to have occurred in high-performance jets.) This is one reason why it was possible for President Kennedy to dream of the completion of the Mercury and Gemini missions and a successful landing on the moon in under a decade, while returning to the moon may take nearly twice as long. Lacking access to the tremendous computational resources of the national space program-and, just as importantly, removed from the harsh judgment of public shareholders or congressional appropriations committees-the hungry entrepreneurs who compete for our prizes tend not to display such fear of failure. Instead, most of them follow a rapid "build, test, fly" program. They are willing to throw a handful of concepts against the wall and see what sticks. They often go from drawing on the back of a napkin to firing engines or even flying vehicles in a matter of weeks or months, learning valuable lessons along the way. Indeed, our teams have repeatedly learned many of the most valuable lessons after only a few moments of working with real hardware-lessons that could never have been learned from a CAD drawing, like finding the failure modes of different welding practices or tracking down the interference between an onboard camera and a GPS unit. As Paul Breed, the leader of a Northrop Grumman Lunar Lander Challenge team (playfully called Unreasonable Rocket), is fond of saying, "In computer simulations the plumbing never leaks. In real life, it always does."

Pomerantz, William↗

Lessons Learned from Recent Failure and Incident Investigations of Composite Structures

During the past few decades, NASA Langley Research Center (LaRC) has supported several large-scale failure and incident investigations and numerous requests for engineering consultations. Although various extenuating circumstances contributed to each of these incidents, in all cases, the failure resulted from accumulation and/or propagation of damage that reduced the load carrying capability of the structure to a level below that which was needed to sustain structural loads. A brief overview of various failure and incident investigations supported by LaRC, including some of the computational and experimental methodologies that have been applied, is presented. An important outcome of many of these failure and incident investigations is the development of an improved understanding of not only the state-of-the-art in experimental and analytical methods but also the state-of-the-art in the design and manufacturing processes that may contribute to such failures. In order to provide insight into such large-scale investigations, a series of lessons learned were captured. Awareness of these lessons learned is highly beneficial to engineers involved in similar investigations. Therefore, it is prudent that the lessons learned are disseminated such that they can be built upon in other investigations and in ensuing research and development activities.

Ransom, J. B.↗

James Webb Space Telescope - Applying Lessons Learned to I&T

The James Webb Space Telescope (JWST) is part of a new generation of spacecraft acquiring large data volumes from remote regions in space. To support a mission such as the JWST, it is imperative that lessons learned from the development of previous missions such as the Hubble Space Telescope and the Earth Observing System mission set be applied throughout the development and operational lifecycles. One example of a key lesson that should be applied is that core components, such as the command and telemetry system and the project database, should be developed early, used throughout development and testing, and evolved into the operational system. The purpose of applying lessons learned is to reap benefits in programmatic or technical parameters such as risk reduction, end product quality, cost efficiency, and schedule optimization. In the cited example, the early development and use of the operational command and telemetry system as well as the establishment of the intended operational database will allow these components to be used by the developers of various spacecraft components such that development, testing, and operations will all use the same core components. This will reduce risk through the elimination of transitions between development and operational components and improve end product quality by extending the verification of those components through continual use. This paper will discuss key lessons learned that have been or are being applied to the JWST Ground Segment integration and test program.

Johns, Alan↗

Improving Grasp Skills Using Schema Structured Learning

Abstract In the control-based approach to robotics, complex behavior is created by sequencing and combining control primitives. While it is desirable for the robot to autonomously learn the correct control sequence, searching through the large number of potential solutions can be time consuming. This paper constrains this search to variations of a generalized solution encoded in a framework known as an action schema. A new algorithm, SCHEMA STRUCTURED LEARNING, is proposed that repeatedly executes variations of the generalized solution in search of instantiations that satisfy action schema objectives. This approach is tested in a grasping task where Dexter, the UMass humanoid robot, learns which reaching and grasping controllers maximize the probability of grasp success.

Platt, Robert↗

Inflatable Habitat Health Monitoring: Implementation, Lessons Learned, and Application to Lunar or Martian Habitat Health Monitoring

NASA's exploration mission is to send humans to the Moon and Mars, in which the purpose is to learn how to live and work safely in those harsh environments. A critical aspect of living in an extreme environment is habitation, and within that habitation element there are key systems which monitor the habitation environment to provide a safe and comfortable living and working space for humans. Expandable habitats are one of the options currently being considered due to their potential mass and volume efficiencies. This paper discusses a joint project between the National Science Foundation (NSF), ILC Dover, and NASA in which an expandable habitat was deployed in the extreme environment of Antarctica to better understand the performance and operations over a one-year period. This project was conducted through the Innovative Partnership Program (IPP) where the NSF provided the location at McMurdo Station in Antarctica and support at the location, ILC Dover provided the inflatable habitat, and NASA provided the instrumentation and data system for monitoring the habitat. The outcome of this project provided lessons learned in the implementation of an inflatable habitat and the systems that support that habitat. These lessons learned will be used to improve current habitation capabilities and systems to meet the objectives of exploration missions to the moon and Mars.

Rojdev, Kristina↗

Lessons Learned from Performance Testing of Humans in Spacesuits in Simulated Reduced Gravity

Introduction: The overarching objective of the Integrated Suit Test (IST) series is to evaluate suited human performance using reduced-gravity analogs and learn what aspects of an EVA suit system affect human performance. For this objective to be successfully achieved, the testing methodology should be valid and reproducible, and the partial-gravity simulations must be as accurate and realistic as possible. Objectives: To highlight some of the key lessons learned about partial-gravity analogs and testing methodology, and to suggest considerations for optimizing the effectiveness and quality of results of future tests. Methods: Performance testing of suited and unsuited subjects was undertaken in different reduced-gravity analogs including the Space Vehicle Mockup Facility s Partial Gravity Simulator (POGO), parabolic flight on the C-9 aircraft, underwater environments including NASA s Extreme Environment Mission Operations (NEEMO) and the Neutral Buoyancy Lab (NBL), and in field analogs including Desert Research and Technology Studies (RATS), the Haughton Mars Project (HMP), and the JSC Rock Pile. Subjects performed level walking, incline/decline walking, running, shoveling, picking up and transferring rocks, kneeling/standing, and task boards. Lessons Learned Analogs: No single analog will properly simulate all aspects of the true partial-gravity environment. The POGO is an ideal environment from the standpoint that there are no time limits or significant volumetric constraints, but it does have several limitations. It allows only 2 translational degrees of freedom (DOF) and applies true partial-gravity offload only through the subject s center of gravity (CG). Also, when a subject is doing non-stationary tasks, significant overhead inertia from the lift column seems to have a negative impact on performance. Parabolic flight allows full translational and rotational DOF and applies offload to all parts of the body, but the simulation lasts less than 30 seconds. When this is coupled with the volumetric constraints of the plane, both task selection and data collection options are significantly limited. The underwater environments also allow all 6 DOF and allow off-loading to be applied throughout the body, but the data collection capabilities are limited to little more than subjective ratings. In addition, water drag negatively affects performance of tasks requiring dynamic motion. Field analogs provide the ability to simulate lunar terrain and more realistic mission-like objectives, but all of them operate at 1-g, so suited human performance testing generally must utilize a reduced-mass or "mockup" suit, depending on study objectives. In general, the ground-based overhead-suspension partial-gravity analogs like POGO allow the most diverse data collection methods possible while still simulating partial gravity. However, as currently designed, the POGO has significant limitations. Design of the Active Response Gravity Offload System (ARGOS) has begun and is focusing on adding full x,y,z translational DOF, improved offload accuracy, increased lift capacity, and active control of the x and y axes to minimize offload system inertia. Additionally, a new gimbal is being designed to reduce mass and inertia and to be able to work with different suits, as the current gimbal only supports suited testing with the Mark III Technology Demonstrator Suit (MKIII).

Norcross, Jason R.↗

Lessons Learned from the Node 1 Atmosphere Control and Storage and Water Recovery and Management Subsystem Design

Node 1 flew to the International Space Station (ISS) on Flight 2A during December 1998. To date the National Aeronautics and Space Administration (NASA) has learned a lot of lessons from this module based on its history of approximately two years of acceptance testing on the ground and currently its twelve years on-orbit. This paper will provide an overview of the ISS Environmental Control and Life Support (ECLS) design of the Node 1 Atmosphere Control and Storage (ACS) and Water Recovery and Management (WRM) subsystems and it will document some of the lessons that have been learned to date for these subsystems based on problems prelaunch, problems encountered on-orbit, and operational problems/concerns. It is hoped that documenting these lessons learned from ISS will help in preventing them in future Programs.

Williams, David E.↗

Lessons Learned from Mir - A Payload Perspective

Among the principal objectives of the Phase 1 NASA/Mir program were for the United States to gain experience working with an international partner, to gain working experience in long-duration space flight, and to gain working experience in planning for and executing research on a long-duration space platform. The Phase 1 program was to provide to the US early experience prior to the construction and operation of the International Space Station (Phase 2 and 3). While it can be argued that Mir and ISS are different platforms and that programmatically Phase 1 and ISS are organized differently, it is also clear that many aspects of operating a long-duration research program are platform independent. This can be demonstrated by a review of lessons learned from Skylab, a US space station program of the mid-1970's, many of which were again "learned" on Mir and are being "learned" on ISS. Among these are optimum crew training strategies, on-orbit crew operations, ground support, medical operations and crew psychological support, and safety certification processes

Uri, John J.↗

Imbalanced Learning for Functional State Assessment

This paper presents results of several imbalanced learning techniques applied to operator functional state assessment where the data is highly imbalanced, i.e., some function states (majority classes) have much more training samples than other states (minority classes). Conventional machine learning techniques usually tend to classify all data samples into majority classes and perform poorly for minority classes. In this study, we implemented five imbalanced learning techniques, including random undersampling, random over-sampling, synthetic minority over-sampling technique (SMOTE), borderline-SMOTE and adaptive synthetic sampling (ADASYN) to solve this problem. Experimental results on a benchmark driving lest dataset show thai accuracies for minority classes could be improved dramatically with a cost of slight performance degradations for majority classes,

Li, Feng↗

Lessons Learned from the Node 1 Atmosphere Control and Storage and Water Recovery and Management Subsystem Design

Node 1 flew to the International Space Station (ISS) on Flight 2A during December 1998. To date the National Aeronautics and Space Administration (NASA) has learned a lot of lessons from this module based on its history of approximately two years of acceptance testing on the ground and currently its twelve years on-orbit. This paper will provide an overview of the ISS Environmental Control and Life Support (ECLS) design of the Node 1 Atmosphere Control and Storage (ACS) and Water Recovery and Management (WRM) subsystems and it will document some of the lessons that have been learned to date for these subsystems based on problems prelaunch, problems encountered on-orbit, and operational problems/concerns. It is hoped that documenting these lessons learned from ISS will help in preventing them in future Programs.

Williams, David E.↗

The Impact of Incentivizing the Use of Feedback on Learning and Performance in Educational Videogames

Educational videogames can be designed to provide instructional feedback responsive to specific actions. However, existing research indicates that students tend to ignore the feedback provided. That is, students often use ineffective help-seeking strategies. Research on the topic of help-seeking in learning environments have primarily focused on the role of cognitive factors, the nature of the help, or issues of timing and frequency. There is a noticeable gap in understanding how to motivate the use provided feedback. This study examined the relation between incentivizing the use of feedback and providing an explanation of the game's scoring rules on math learning in a pre-algebra videogame. A randomized-control design was used, comparing learning outcomes of students who received the incentive with those who did not. Results indicated that students given the incentive to use feedback had significantly higher normalized change scores on math items (d = .53), with stronger effects for students with low academic intrinsic motivation (d = .88 - 1.17).

Delacruz, Girlie C.↗

Defining Learning Space in a Serious Game in Terms of Operative and Resultant Actions

This paper explores the distinction between operative and resultant actions in games, and proposes that the learning space created by a serious game is a function of these actions. Further, it suggests a possible relationship between these actions and the forms of cognitive load imposed upon the game player. Association of specific types of cognitive load with respective forms of actions in game mechanics also presents some heuristics for integrating learning content into serious games. Research indicates that different balances of these types of actions are more suitable for novice or experienced learners. By examining these relationships, we can develop a few basic principles of game design which have an increased potential to promote positive learning outcomes.

Martin, Michael W.↗

Innovating Training through Immersive Environments: Generation Y, Exploratory Learning, and Serious Games

Over the next decade, those entering Service and Joint Staff positions within the military will come from a different generation than the current leadership. They will come from Generation Y and have differing preferences for learning. Immersive learning environments like serious games and virtual world initiatives can complement traditional training methods to provide a better overall training program for staffs. Generation Y members desire learning methods which are relevant and interactive, regardless of whether they are delivered over the internet or in person. This paper focuses on a project undertaken to assess alternative training methods to teach special operations staffs. It provides a summary of the needs analysis used to consider alternatives and to better posture the Department of Defense for future training development.

Gendron, Gerald↗

Active Learning for Directed Exploration of Complex Systems

Physics-based simulation codes are widely used in science and engineering to model complex systems that would be infeasible to study otherwise. Such codes provide the highest-fidelity representation of system behavior, but are often so slow to run that insight into the system is limited. For example, conducting an exhaustive sweep over a d-dimensional input parameter space with k-steps along each dimension requires k(sup d) simulation trials (translating into k(sup d) CPU-days for one of our current simulations). An alternative is directed exploration in which the next simulation trials are cleverly chosen at each step. Given the results of previous trials, supervised learning techniques (SVM, KDE, GP) are applied to build up simplified predictive models of system behavior. These models are then used within an active learning framework to identify the most valuable trials to run next. Several active learning strategies are examined including a recently-proposed information-theoretic approach. Performance is evaluated on a set of thirteen synthetic oracles, which serve as surrogates for the more expensive simulations and enable the experiments to be replicated by other researchers.

oracles↗

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

Tran, Loc↗

Real-Time Global Nonlinear Aerodynamic Modeling for Learn-To-Fly

Flight testing and modeling techniques were developed to accurately identify global nonlinear aerodynamic models for aircraft in real time. The techniques were developed and demonstrated during flight testing of a remotely-piloted subscale propeller-driven fixed-wing aircraft using flight test maneuvers designed to simulate a Learn-To-Fly scenario. Prediction testing was used to evaluate the quality of the global models identified in real time. The real-time global nonlinear aerodynamic modeling algorithm will be integrated and further tested with learning adaptive control and guidance for NASA Learn-To-Fly concept flight demonstrations.

Morelli, Eugene A.↗

A Learning Model for L/M Specificity in Ganglion Cells

An unsupervised learning model for developing LM specific wiring at the ganglion cell level would support the research indicating LM specific wiring at the ganglion cell level (Reid and Shapley, 2002). Removing the contributions to the surround from cells of the same cone type improves the signal-to-noise ratio of the chromatic signals. The unsupervised learning model used is Hebbian associative learning, which strengthens the surround input connections according to the correlation of the output with the input. Since the surround units of the same cone type as the center are redundant with the center, their weights end up disappearing. This process can be thought of as a general mechanism for eliminating unnecessary cells in the nervous system.

Ahumada, Albert J.↗