Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learned”

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 1,387 records · Page 77

Learning a trajectory using adjoint functions and teacher forcing

A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.

Toomarian, Nikzad B.↗

Sea ice classification using fast learning neural networks

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

Dawson, M. S.↗

Lift-fan aircraft: Lessons learned-the pilot's perspective

This paper is written from an engineering test pilot's point of view. Its purpose is to present lift-fan 'lessons learned' from the perspective of first-hand experience accumulated during the period 1962 through 1988 while flight testing vertical/short take-off and landing (V/STOL) experimental aircraft and evaluating piloted engineering simulations of promising V/STOL concepts. Specifically, the scope of the discussions to follow is primarily based upon a critical review of the writer's personal accounts of 30 hours of XV-5A/B and 2 hours of X-14A flight testing as well as a limited simulator evaluation of the Grumman Design 755 lift-fan aircraft. Opinions of other test pilots who flew these aircraft and the aircraft simulator are also included and supplement the writer's comments. Furthermore, the lessons learned are presented from the perspective of the writer's flying experience: 10,000 hours in 100 fixed- and rotary-wing aircraft including 330 hours in 5 experimental V/STOL research aircraft. The paper is organized to present to the reader a clear picture of lift-fan lessons learned from three distinct points of view in order to facilitate application of the lesson principles to future designs. Lessons learned are first discussed with respect to case histories of specific flight and simulator investigations. These principles are then organized and restated with respect to four selected design criteria categories in Appendix I. Lastly, Appendix Il is a discussion of the design of a hypothetical supersonic short take-off vertical landing (STOVL) fighter/attack aircraft.

Gerdes, Ronald M.↗

Establishing a Distance Learning Plan for International Space Station (ISS) Interactive Video Education Events (IVEE)

Educational outreach is an integral part of the International Space Station (ISS) mandate. In a few scant years, the International Space Station has already established a tradition of successful, general outreach activities. However, as the number of outreach events increased and began to reach school classrooms, those events came under greater scrutiny by the education community. Some of the ISS electronic field trips, while informative and helpful, did not meet the generally accepted criteria for education events, especially within the context of the classroom. To make classroom outreach events more acceptable to educators, the ISS outreach program must differentiate between communication events (meant to disseminate information to the general public) and education events (designed to facilitate student learning). In contrast to communication events, education events: are directed toward a relatively homogeneous audience who are gathered together for the purpose of learning, have specific performance objectives which the students are expected to master, include a method of assessing student performance, and include a series of structured activities that will help the students to master the desired skill(s). The core of the ISS education events is an interactive videoconference between students and ISS representatives. This interactive videoconference is to be preceded by and followed by classroom activities which help the students aftain the specified learning objectives. Using the interactive videoconference as the centerpiece of the education event lends a special excitement and allows students to ask questions about what they are learning and about the International Space Station and NASA. Whenever possible, the ISS outreach education events should be congruent with national guidelines for student achievement. ISS outreach staff should recognize that there are a number of different groups that will review the events, and that each group has different criteria for acceptance. For example, school administrators are more likely to be concerned about an event meeting national standards and the cost of the event. In contrast, a teacher's acceptance of an education event may be directly related to the amount of extra work the event imposes upon that teacher. ISS education events must be marketed differently to the different groups of educators, and must never increase the workload of the average teacher.

Wallington, Clint↗

Reinforcement Learning in a Nonstationary Environment: The El Farol Problem

This paper examines the performance of simple learning rules in a complex adaptive system based on a coordination problem modeled on the El Farol problem. The key features of the El Farol problem are that it typically involves a medium number of agents and that agents' pay-off functions have a discontinuous response to increased congestion. First we consider a single adaptive agent facing a stationary environment. We demonstrate that the simple learning rules proposed by Roth and Er'ev can be extremely sensitive to small changes in the initial conditions and that events early in a simulation can affect the performance of the rule over a relatively long time horizon. In contrast, a reinforcement learning rule based on standard practice in the computer science literature converges rapidly and robustly. The situation is reversed when multiple adaptive agents interact: the RE algorithms often converge rapidly to a stable average aggregate attendance despite the slow and erratic behavior of individual learners, while the CS based learners frequently over-attend in the early and intermediate terms. The symmetric mixed strategy equilibria is unstable: all three learning rules ultimately tend towards pure strategies or stabilize in the medium term at non-equilibrium probabilities of attendance. The brittleness of the algorithms in different contexts emphasize the importance of thorough and thoughtful examination of simulation-based results.

Bell, Ann Maria↗

A Computer Learning Center for Environmental Sciences

In the fall of 1998, MacMillan Hall opened at Brown University to students. In MacMillan Hall was the new Computer Learning Center, since named the EarthLab which was outfitted with high-end workstations and peripherals primarily focused on the use of remotely sensed and other spatial data in the environmental sciences. The NASA grant we received as part of the "Centers of Excellence in Applications of Remote Sensing to Regional and Global Integrated Environmental Assessments" was the primary source of funds to outfit this learning and research center. Since opening, we have expanded the range of learning and research opportunities and integrated a cross-campus network of disciplines who have come together to learn and use spatial data of all kinds. The EarthLab also forms a core of undergraduate, graduate, and faculty research on environmental problems that draw upon the unique perspective of remotely sensed data. Over the last two years, the Earthlab has been a center for research on the environmental impact of water resource use in and regions, impact of the green revolution on forest cover in India, the design of forest preserves in Vietnam, and detailed assessments of the utility of thermal and hyperspectral data for water quality analysis. It has also been used extensively for local environmental activities, in particular studies on the impact of lead on the health of urban children in Rhode Island. Finally, the EarthLab has also served as a key educational and analysis center for activities related to the Brown University Affiliated Research Center that is devoted to transferring university research to the private sector.

Mustard, John F.↗

On-Line, Self-Learning, Predictive Tool for Determining Payload Thermal Response

This paper will present the results of a joint ManTech / Goddard R&D effort, currently under way, to develop and test a computer based, on-line, predictive simulation model for use by facility operators to predict the thermal response of a payload during thermal vacuum testing. Thermal response was identified as an area that could benefit from the algorithms developed by Dr. Jeri for complex computer simulations. Most thermal vacuum test setups are unique since no two payloads have the same thermal properties. This requires that the operators depend on their past experiences to conduct the test which requires time for them to learn how the payload responds while at the same time limiting any risk of exceeding hot or cold temperature limits. The predictive tool being developed is intended to be used with the new Thermal Vacuum Data System (TVDS) developed at Goddard for the Thermal Vacuum Test Operations group. This model can learn the thermal response of the payload by reading a few data points from the TVDS, accepting the payload's current temperature as the initial condition for prediction. The model can then be used as a predictive tool to estimate the future payload temperatures according to a predetermined shroud temperature profile. If the error of prediction is too big, the model can be asked to re-learn the new situation on-line in real-time and give a new prediction. Based on some preliminary tests, we feel this predictive model can forecast the payload temperature of the entire test cycle within 5 degrees Celsius after it has learned 3 times during the beginning of the test. The tool will allow the operator to play "what-if' experiments to decide what is his best shroud temperature set-point control strategy. This tool will save money by minimizing guess work and optimizing transitions as well as making the testing process safer and easier to conduct.

Jen, Chian-Li↗

Quality Training and Learning in Aviation: Problems of Alignment

The challenge of producing training programs that lead to quality learning outcomes is ever present in aviation, especially when economic and regulatory pressures are brought into the equation. Previous research by Telfer & Moore (1997) indicates the importance of appropriate alignment of beliefs about learning across all levels of an organization from the managerial level, through the instructor/check and training level, to the pilots and other crew. This paper argues for a central focus on approaches to learning and training that encourage understanding, problem solving and application. Recent research in the area is emphasized as are methods and techniques for enhancing deeper learning.

Moore, Phillip J.↗

Representing Learning With Graphical Models

Probabilistic graphical models are being used widely in artificial intelligence, for instance, in diagnosis and expert systems, as a unified qualitative and quantitative framework for representing and reasoning with probabilities and independencies. Their development and use spans several fields including artificial intelligence, decision theory and statistics, and provides an important bridge between these communities. This paper shows by way of example that these models can be extended to machine learning, neural networks and knowledge discovery by representing the notion of a sample on the graphical model. Not only does this allow a flexible variety of learning problems to be represented, it also provides the means for representing the goal of learning and opens the way for the automatic development of learning algorithms from specifications.

Buntine, Wray L.↗

Learning Sequences of Actions in Collectives of Autonomous Agents

In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. We are particularly interested in instances of this problem where centralized control is either impossible or impractical. For single agent systems in similar domains, machine learning methods (e.g., reinforcement learners) have been successfully used. However, applying such solutions directly to multi-agent systems often proves problematic, as agents may work at cross-purposes, or have difficulty in evaluating their contribution to achievement of the global objective, or both. Accordingly, the crucial design step in multiagent systems centers on determining the private objectives of each agent so that as the agents strive for those objectives, the system reaches a good global solution. In this work we consider a version of this problem involving multiple autonomous agents in a grid world. We use concepts from collective intelligence to design goals for the agents that are 'aligned' with the global goal, and are 'learnable' in that agents can readily see how their behavior affects their utility. We show that reinforcement learning agents using those goals outperform both 'natural' extensions of single agent algorithms and global reinforcement, learning solutions based on 'team games'.

Turner, Kagan↗

NASA Materials Related Lessons Learned

Lessons Learned have been the basis for our accomplishments throughout the ages. They have been passed down from father to son, mother to daughter, teacher to pupil, and older to younger worker. Lessons Learned have also been the basis for the nation's accomplishments for more than 200 years. Both government and industry have long recognized the need to systematically document and utilize the knowledge gained from past experiences in order to avoid the repetition of failures and mishaps. Through the knowledge captured and recorded in Lessons Learned from more than 80 years of flight in the Earth's atmosphere, NASA's materials researchers are constantly working to develop stronger, lighter, and more durable materials that can withstand the challenges of space. The Agency's talented materials engineers and scientists continue to build on that rich tradition by using the knowledge and wisdom gained from past experiences to create futurist materials and technologies that will be used in the next generation of advanced spacecraft and satellites that may one day enable mankind to land men on another planet or explore our nearest star. These same materials may also have application here on Earth to make commercial aircraft more economical to build and fly. With the explosion in technical accomplishments over the last decade, the ability to capture knowledge and have the capability to rapidly communicate this knowledge at lightning speed throughout an organization like NASA has become critical. Use of Lessons Learned is a principal component of an organizational culture committed to continuous improvement.

Garcia, Danny↗

Reinforcement Learning for Weakly-Coupled MDPs and an Application to Planetary Rover Control

Weakly-coupled Markov decision processes can be decomposed into subprocesses that interact only through a small set of bottleneck states. We study a hierarchical reinforcement learning algorithm designed to take advantage of this particular type of decomposability. To test our algorithm, we use a decision-making problem faced by autonomous planetary rovers. In this problem, a Mars rover must decide which activities to perform and when to traverse between science sites in order to make the best use of its limited resources. In our experiments, the hierarchical algorithm performs better than Q-learning in the early stages of learning, but unlike Q-learning it converges to a suboptimal policy. This suggests that it may be advantageous to use the hierarchical algorithm when training time is limited.

Bernstein, Daniel S.↗

Lessons Learned (3 Years of H2O2 Propulsion System Testing Efforts at NASA's John C. Stennis Space Center)

John C. Stennis Space Center continues to support the Propulsion community in an effort to validate High-Test Peroxide as an alternative to existing/future oxidizers. This continued volume of peroxide test/handling activity at Stennis Space Center (SSC) provides numerous opportunities for the SSC team to build upon previously documented 'lessons learned'. SSC shall continue to strive to document their experience and findings as H2O2 issues surface. This paper is intended to capture all significant peroxide issues that we have learned over the last three years. This data (lessons learned) has been formulated from practical handling, usage, storage, operations, and initial development/design of our systems/facility viewpoint. The paper is intended to be an information type tool and limited in technical rational; therefore, presenting the peroxide community with some issues to think about as the continued interest in peroxide evolves and more facilities/hardware are built. These lessons learned are intended to assist industry in mitigating problems and identifying potential pitfalls when dealing with the requirements for handling high-test peroxide.

Taylor, Gary O.↗

DASL-Data and Activities for Solar Learning

DASL-Data and Activities for Solar Learning Data and Activities for Solar Learning (DASL) provides a classroom learning environment based on a twenty-five year record of solar magnetograms from the National Solar Observatory (NSO) at Kitt Peak, AZ. The data, together with image processing software for Macs or PCs, can be used to learn basic facts about the Sun and astronomy at the middle school level. At the high school level, students can study properties of the Sun's magnetic cycle with classroom exercises emphasizing data and error analysis and can participate in a new scientific study, Research in Active Solar Longitudes (RASL), in collaboration with classrooms throughout the country and scientists at NSO and NASA. We present a half-day course to train teachers in the scientific content of the project and its classroom use. We will provide a compact disc with the data and software and will demonstrate software installation and use, classroom exercises, and participation in RASL with computer projection.

Jones, Harrison P.↗

Robot Behavior Acquisition Superposition and Composting of Behaviors Learned through Teleoperation

Superposition of a small set of behaviors, learned via teleoperation, can lead to robust completion of a simple articulated reach-and-grasp task. Results support the hypothesis that a set of learned behaviors can be combined to generate new behaviors of a similar type. This supports the hypothesis that a robot can learn to interact purposefully with its environment through a developmental acquisition of sensory-motor coordination. Teleoperation bootstraps the process by enabling the robot to observe its own sensory responses to actions that lead to specific outcomes. A reach-and-grasp task, learned by an articulated robot through a small number of teleoperated trials, can be performed autonomously with success in the face of significant variations in the environment and perturbations of the goal. Superpositioning was performed using the Verbs and Adverbs algorithm that was developed originally for the graphical animation of articulated characters. Work was performed on Robonaut at NASA-JSC.

Peters, Richard Alan, II↗

NASA Materials Related Lessons Learned

Lessons Learned have been the basis for our accomplishments throughout the ages. They have been passed down from father to son, mother to daughter, teacher to pupil, and older to younger worker. Lessons Learned have also been the basis for the nation s accomplishments for more than 200 years. Both government and industry have long recognized the need to systematically document and utilize the knowledge gained from past experiences in order to avoid the repetition of failures and mishaps. Through the knowledge captured and recorded in Lessons Learned from more than 80 years of flight in the Earth s atmosphere, NASA s materials researchers are constantly working to develop stronger, lighter, and more durable materials that can withstand the challenges of space. The Agency s talented materials engineers and scientists continue to build on that rich tradition by using the knowledge and wisdom gained from past experiences to create futuristic materials and technologies that will be used in the next generation of advanced spacecraft and satellites that may one day enable mankind to land men on another planet or explore our nearest star. These same materials may also have application here on Earth to make commercial aircraft more economical to build and fly. With the explosion in technical accomplishments over the last decade, the ability to capture knowledge and have the capability to rapidly communicate this knowledge at lightning speed throughout an organization like NASA has become critical. Use of Lessons Learned is a principal component of an organizational culture committed to continuous improvement.

Garcia, Danny↗

Multi Agent Reward Analysis for Learning in Noisy Domains

In many multi agent learning problems, it is difficult to determine, a priori, the agent reward structure that will lead to good performance. This problem is particularly pronounced in continuous, noisy domains ill-suited to simple table backup schemes commonly used in TD(lambda)/Q-learning. In this paper, we present a new reward evaluation method that allows the tradeoff between coordination among the agents and the difficulty of the learning problem each agent faces to be visualized. This method is independent of the learning algorithm and is only a function of the problem domain and the agents reward structure. We then use this reward efficiency visualization method to determine an effective reward without performing extensive simulations. We test this method in both a static and a dynamic multi-rover learning domain where the agents have continuous state spaces and where their actions are noisy (e.g., the agents movement decisions are not always carried out properly). Our results show that in the more difficult dynamic domain, the reward efficiency visualization method provides a two order of magnitude speedup in selecting a good reward. Most importantly it allows one to quickly create and verify rewards tailored to the observational limitations of the domain.

Tumer, Kagan↗

Human Factors Lessons Learned on the International Space Station

Experience on International Space Station (ISS) provides many important lessons for future space flight. NASA human factors engineers have been systematically collecting lessons learned from crew debriefs, as well as working with ground support teams to continuously improve crew operations. This paper describes the methods for collecting data from debriefs, lessons learned through that process, and an example of a technology development task funded through the Space Human Factors Engineering (SHFE) program element in response to an identified operational need. Each ISS increment crew spends many hours after the flight answering questions from the various subsystem leads. The Flight Crew Integration subsystem lead asks questions specific to human factors and habitability issues. In addition, crew comments on many other subsystems provide insight into interface designs, operability and maintainability. The debrief comments are unique to each crew, and must be categorized to provide operational lessons learned. Personal identifiers are removed and comments aggregated to separate consistent issues from personal preferences. Examples will be given, and the procedure for incorporating the lessons into requirements and guidelines for the next human space vehicle will be described. In flight, very few astronauts are medical doctors. Written medical procedures during flight need to be easy to follow and quick to understand. The problem was analyzed as part of a SHFE task. Organization was analyzed and reorganizations were created and tested. Results will be reported. The ISS is a very important analog for planning future long-term missions. Collection of data from debriefs, studying the lessons learned and focusing on requirements for future missions are examples of the accomplishments through the SHFE program.

Woolford, Barbara↗