Search NASA⌕ Search

SEARCH · Search NASA

Results for “Adaptive 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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
NASA NTRS2004

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

Williams-Hayes, Peggy S.↗
NASA NTRS1996

Effects of altered loading states on muscle plasticity: what have we learned from rodents?

This paper summarizes the key findings concerning the adaptive properties of rodent muscle in response to altered loading states. When the mechanical stress on the muscle is chronically increased, the muscle adapts by hypertrophying its fibers. This response is regulated by processes resulting in contractile protein expression reflecting slower phenotypes, thereby enabling the muscle to better support load-hearing activity. In contrast, reducing the load-bearing activity induces an opposite response whereby muscles used for both antigravity function and locomotion atrophy while transforming some of the slow fibers into faster contractile phenotypes. Accompanying the atrophy is both a reduced power generating and activity sustaining capability. These adaptive processes are regulated by both transcriptional and translational processes. Available evidence further suggests that the interaction of heavy resistance activity and hormonal/growth factors (insulin-like growth factor, growth hormone, glucocorticoids, etc.) are critical in the maintenance of muscle mass and function. Also resistance training, in contrast to other activities such as endurance running, provides a more economical form of stress because less mechanical activity is required to maintain muscle homeostasis in the context of chronic states of weightlessness.

Non-NASA Center↗
NASA NTRS2004

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

The NASA F-15 Intelligent Flight Control System project team has developed a series of flight control concepts designed to demonstrate the benefits of a neural network-based adaptive controller. The objective of the team is to develop and flight-test control systems that use neural network technology to optimize the performance of the aircraft under nominal conditions as well as stabilize the aircraft under failure conditions. Failure conditions include locked or failed control surfaces as well as unforeseen damage that might occur to the aircraft in flight. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to the baseline aerodynamic derivatives in flight. This set of open-loop flight tests was performed in preparation for a future phase of flights in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed a pitch frequency sweep and an automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. An examination of flight data shows that addition of the flight-identified aerodynamic derivative increments into the simulation improved the pitch handling qualities of the aircraft.

Williams, Peggy S.↗
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 NTRS2019

Everybody Needs Somebody Sometimes: Validation of Adaptive Recovery in Robotic Space Operations

This work assesses an adaptive approach to fault recovery in autonomous robotic space operations, which uses indicators of opportunity, such as physiological state measurements and observations of past human assistant performance, to inform future selections. We validated our reinforcement learning approach using data we collected from humans executing simulated mission scenarios. We present a method of structuring human-factors experiments that permits collection of relevant indicator of opportunity and assigned assistance task performance data, as well as evaluation of our adaptive approach, without requiring large numbers of test subjects. Application of our reinforcement learning algorithm to our experimental data shows that our adaptive assistant selection approach can achieve lower cumulative regret compared to existing non-adaptive baseline approaches when using real human data. Our work has applications beyond space robotics to any application where autonomy failures may occur that require external intervention.

Human-centered robotics↗
NASA NTRS2019

High-Performance Computing Optimization for Aladyn – Adaptive Neural Network Molecular Dynamics Mini-Application

This report provides a description and performance evaluation of the optimization techniques for high performance computing (HPC) implementation of the open source Computational Materials mini-application Aladyn (https://github.com/nasa/aladyn). Aladyn is a basic molecular dynamics code written in FORTRAN 2003, which is designed to demonstrate the use of adaptive neural networks (ANNs) in atomistic simulations. The role of ANNs is to efficiently reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of the more expensive quantum mechanics-based calculations. The ANN is trained on a large set of atomic structures calculated using the density functional theory (DFT) method. While achieving orders of magnitude faster computational performance than DFT, the ANN-based approach was still very computationally demanding compared to the conventional approach of using empirically fitted energy functions. After its initial development, Aladyn was evaluated and optimized by experts at the NASA Advanced Supercomputing (NAS) division to exploit modern supercomputer architectures. The code has been optimized for execution on multicore central processing units (CPUs), including Intel® Skylake microarchitecture, and on graphic accelerators, such as Nvidia® V100 graphic processing units (GPUs), using Open Multi-Processing (OpenMP) and Open Accelerators (OpenACC) programming interfaces. The optimization achieved a speedup of 4.7 times the baseline version on CPU performance and an additional 2.4 times on CPU+GPU performance. Atomistic computer simulations are a fundamental tool in materials research to model material properties form physics-based first principles. Atomic interaction, governed by Quantum Mechanics (QM) require sophisticated and highly computationally demanding mathematical models to calculate [1]. Classical methods use approximate functional forms, empirically fitted through a set of variable parameters to emulate atomic energies as direct functions of atomic coordinates [2]. While empirical potentials are computationally much simpler, allowing simulations of large-scale systems of up to a trillion (1012) atoms [3], they are substantially less accurate compared to quantum calculations and applicable only to very specific atomic configurations or predefined crystallographic phases. A recently suggested approach is to use heuristic machine learning methods [4], such as those based on Adaptive Neural Networks (ANNs) to predict atomic energies, after being trained on a sufficiently large database of QM-calculated structures [5,6]. This approach reduces significantly the computational complexity, allowing for simulations of orders of magnitude larger systems compared to QM-based methods without compromising accuracy. Still, compared to classical methods using empirical energy functions, ANN methods remain two- to three orders of magnitude more computationally demanding. Hence, the computational cost of simulations, together with the need for extensive training of ANNs, still makes the practical implementation of ANN-based methods quite challenging. The purpose of the Aladyn mini-application software [7], available as open source at https://github.com/nasa/aladyn, is to be a testbed for exploring possible optimization strategies to develop highly scalable parallel algorithms for ANN-based atomistic simulations. Aladyn is aimed at utilizing the architecture of the high-end modern highperformance computing (HPC) hardware based on multicore central processing units (CPUs) equipped with graphic processing unit (GPU) accelerators. Specifically, the goal is to optimize the performance on a single HPC compute node, before implementing scaling to multi-node parallelization using message passing interface (MPI). At the same time, the open source code of Aladyn can serve as a training model for students and professors in academia.

Yamakov, Vesselin I.↗
NASA NTRSDate not supplied

A New ML-Based Adaptive Thinning Methodology to Improve the Impact of AIRS and CrIS Assimilation on Global Tropical Cyclone Forecasts

This work builds on previous research performed by this team to improve the forecast of Tropical Cyclones (TCs) by assimilating AIRS and CrIS radiances into the NASA Global Earth Observing System (GEOS). Past published work demonstrated that the assimilation of radiances with variable density was beneficial to TC forecasting in the GEOS. In the previous setup, a fixed-size moving square named 'TC domain' was activated by the so-called TC-vitals, an international real-time message accessible to all NWP forecasting centers, that documents the existence of a TC, its estimated position, and its size. The information from TC-vitals activated a switch in the GEOS, which allowed to reduce the distance used for thinning AIRS and CrIS data inside a 15 degrees by 15 degrees moving TC domain centered on the storm, so that more data were assimilated in the vicinity of the TC during its lifetime. The methodology produced improved TC analyses and led to better forecasts, particularly related to intensity, without damaging the global forecast skill. In the new version, the adaptive thinning methodology is based on a machine-learning technique. The technique searches for TCs and creates TC masks by using cloud-top temperatures from all geostationary satellites without the need for additional information. It is being trained against the International Best Track Archive for Climate Stewardship (IBTrACS) data base. Once a TC mask is created, a switch identical to the one used in the previous adaptive thinning method is activated, allowing the GEOS to ingest more data in the TC-shaped size-changing domain that follows the storm. As of today, the team has been able to successfully assimilate data inside the ML-detected TC domains. Future work includes an improved capability of reducing false alarm rates (i.e., cloud systems that are erroneously labeled as TCs).

Oreste Reale↗
NASA NTRS2011

Adaptive System Modeling for Spacecraft Simulation

This invention introduces a methodology and associated software tools for automatically learning spacecraft system models without any assumptions regarding system behavior. Data stream mining techniques were used to learn models for critical portions of the International Space Station (ISS) Electrical Power System (EPS). Evaluation on historical ISS telemetry data shows that adaptive system modeling reduces simulation error anywhere from 50 to 90 percent over existing approaches. The purpose of the methodology is to outline how someone can create accurate system models from sensor (telemetry) data. The purpose of the software is to support the methodology. The software provides analysis tools to design the adaptive models. The software also provides the algorithms to initially build system models and continuously update them from the latest streaming sensor data. The main strengths are as follows: Creates accurate spacecraft system models without in-depth system knowledge or any assumptions about system behavior. Automatically updates/calibrates system models using the latest streaming sensor data. Creates device specific models that capture the exact behavior of devices of the same type. Adapts to evolving systems. Can reduce computational complexity (faster simulations).

Thomas, Justin↗
NASA NTRS1981

Parameter estimation of large flexible aerospace structures with application to the control of the Maypole Deployable Reflector

Systems such as the Maypole deployable reflector have a distributed parameter nature. The flexible column and hoop structure and the circular antenna of 30-100 meter diameter which it supports are described by partial, rather than ordinary, differential equations. Progress completed in reduced order modelling andd controller design and digital parameter estimation and control is summarized. Topics covered include depolyment and on-orbit operation; quasi-static (steady state) operation; dynamic distributed parameter system; autoregressive moving average identification; frequency domain procedures; direct or implicit active control; adaptive observers; parameter estimation using a linear reinforcement learning factor; feedback control; and reduced order modeling for nonlinear systems.

Balas, M. J.↗
NASA NTRS1991

Video data compression using artificial neural network differential vector quantization

An artificial neural network vector quantizer is developed for use in data compression applications such as Digital Video. Differential Vector Quantization is used to preserve edge features, and a new adaptive algorithm, known as Frequency-Sensitive Competitive Learning, is used to develop the vector quantizer codebook. To develop real time performance, a custom Very Large Scale Integration Application Specific Integrated Circuit (VLSI ASIC) is being developed to realize the associative memory functions needed in the vector quantization algorithm. By using vector quantization, the need for Huffman coding can be eliminated, resulting in superior performance against channel bit errors than methods that use variable length codes.

Krishnamurthy, Ashok K.↗
NASA NTRS1995

Geophysical phenomena classification by artificial neural networks

Space science information systems involve accessing vast data bases. There is a need for an automatic process by which properties of the whole data set can be assimilated and presented to the user. Where data are in the form of spectrograms, phenomena can be detected by pattern recognition techniques. Presented are the first results obtained by applying unsupervised Artificial Neural Networks (ANN's) to the classification of magnetospheric wave spectra. The networks used here were a simple unsupervised Hamming network run on a PC and a more sophisticated CALM network run on a Sparc workstation. The ANN's were compared in their geophysical data recognition performance. CALM networks offer such qualities as fast learning, superiority in generalizing, the ability to continuously adapt to changes in the pattern set, and the possibility to modularize the network to allow the inter-relation between phenomena and data sets. This work is the first step toward an information system interface being developed at Sussex, the Whole Information System Expert (WISE). Phenomena in the data are automatically identified and provided to the user in the form of a data occurrence morphology, the Whole Information System Data Occurrence Morphology (WISDOM), along with relationships to other parameters and phenomena.

Gough, M. P.↗
NASA NTRS2003

Decision-Theoretic Control of Planetary Rovers

Planetary rovers are small unmanned vehicles equipped with cameras and a variety of sensors used for scientific experiments. They must operate under tight constraints over such resources as operation time, power, storage capacity, and communication bandwidth. Moreover, the limited computational resources of the rover limit the complexity of on-line planning and scheduling. We describe two decision-theoretic approaches to maximize the productivity of planetary rovers: one based on adaptive planning and the other on hierarchical reinforcement learning. Both approaches map the problem into a Markov decision problem and attempt to solve a large part of the problem off-line, exploiting the structure of the plan and independence between plan components. We examine the advantages and limitations of these techniques and their scalability.

Zilberstein, Shlomo↗
NASA NTRS2003

Atmospheric and ocean sensing with GNSS

The 1980s and 1990s saw the Global Positioning System (GPS) transform space geodesy from an elite national enterprise to one open to the individual researcher. By adapting the tools from that endeavor we are learning to probe the atmosphere and the ocean surface in novel ways, including ground-based sensing of atmospheric moisture; space-based profiling of atmospheric refractivity by active limb sounding; and global ocean altimetry with reflected signals.

reflectometry↗
NASA NTRS2004

Execution of the Spitzer In-orbit Checkout and Science Verification Plan

The Spitzer Space Telescope is an 85-cm telescope with three cryogenically cooled instruments. Following launch, the observatory was initialized and commissioned for science operations during the in-orbit checkout (IOC) and science verification (SV) phases, carried out over a total of 98.3 days. The execution of the IOC/SV mission plan progressively established Spitzer capabilities taking into consideration thermal, cryogenic, optical, pointing, communications, and operational designs and constraints. The plan was carried out with high efficiency, making effective use of cryogen-limited flight time. One key component to the success of the plan was the pre-launch allocation of schedule reserve in the timeline of IOC/SV activities, and how it was used in flight both to cover activity redesign and growth due to continually improving spacecraft and instrument knowledge, and to recover from anomalies. This paper describes the adaptive system design and evolution, implementation, and lessons learned from IOC/SV operations. It is hoped that this information will provide guidance to future missions with similar engineering challenges

operations↗
NASA NTRS2018

Online Self-Supervised Long-Range Scene Segmentation for MAVs

Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles (MAVs). As these robots aspire for high-speed autonomous flights in complex dynamic environments, robust scene understanding at long-range becomes critical. The problem is heavily characterized by either the limitations imposed by sensor capabilities for geometry-based methods, or the need for large-amounts of manually annotated training data required by data-driven methods. This motivates the need to build systems that have the capability to alleviate these problems by exploiting the complimentary strengths of both geometry and data-driven methods. In this paper, we take a step in this direction and propose a generic framework for adaptive scene segmentation using self-supervised online learning. We present this in the context of vision-based autonomous MAV flight, and demonstrate the efficacy of our proposed system through extensive experiments on benchmark datasets and real world field tests.

Matthies, Larry↗
NASA NTRS1990

Functional description of a command and control language tutor

The status of an ongoing project to explore the application of Intelligent Tutoring System (ITS) technology to NASA command and control languages is described. The primary objective of the current phase of the project is to develop a user interface for an ITS to assist NASA control center personnel in learning Systems Test and Operations Language (STOL). Although this ITS will be developed for Gamma Ray Observatory operators, it will be designed with sufficient flexibility so that its modules may serve as an ITS for other control languages such as the User Interface Language (UIL). The focus of this phase is to develop at least one other form of STOL representation to complement the operational STOL interface. Such an alternative representation would be adaptively employed during the tutoring session to facilitate the learning process. This is a key feature of this ITS which distinguishes it from a simulator that is only capable of representing the operational environment.

Elke, David R.↗