SEARCH · Search NASA

Results for “Natural language processing”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

NASA NTRS2024

Hierarchical Semantic Frames for Grounding Language in Robot Control Primitives

As robots become increasingly present in human environments, we need robots to be intuitively commanded by and effectively communicate with humans. In particular, non-expert users should be able to communicate task goals with robots. Language emerges as a logical mode of interaction due to its ubiquity in human environments and, more importantly, as the way humans naturally express tasks. Natural language commands present challenges in that robots must reason over ambiguous language probabilistically and reason over commands they may not be able to execute. We present hierarchical semantic frames , which ground commands in robot control primitives through hierarchies that construct high-level commands from lower-level commands. We demonstrate that hierarchical semantic frames allow robots to understand and execute a variety of commands, such as those involving multiple verb meanings, command variations, and compound nouns. The robot quickly processes hierarchical semantic frames and accurately grounds and executes the commanded tasks, demonstrating the power of hierarchical semantic frames for allowing users to intuitively interact with robots.

Emily Sheetz↗

NASA NTRS1990

A flight expert system for on-board fault monitoring and diagnosis

An architecture for a flight expert system (FLES) to assist pilots in monitoring, diagnosing, and recovering from inflight faults is described. A prototype was implemented and an attempt was made to automate the knowledge acquisition process by employing a learning by being told methodology. The scope of acquired knowledge ranges from domain knowledge, including the information about objects and their relationships, to the procedural knowledge associated with the functionality of the mechanisms. AKAS (automatic knowledge acquisition system) is the constructed prototype for demonstration proof of concept, in which the expert directly interfaces with the knowledge acquisition system to ultimately construct the knowledge base for the particular application. The expert talks directly to the system using a natural language restricted only by the extent of the definitions in an analyzer dictionary, i.e., the interface understands a subset of concepts related to a given domain. In this case, the domain is the electrical system of the Boeing 737. Efforts were made to define and employ heuristics as well as algorithmic rules to conceptualize data produced by normal and faulty jet engine behavior examples. These rules were employed in developing the machine learning system (MLS). The input to MLS is examples which contain data of normal and faulty engine behavior and which are obtained from an engine simulation program. MLS first transforms the data into discrete selectors. Partial descriptions formed by those selectors are then generalized or specialized to generate concept descriptions about faults. The concepts are represented in the form of characteristic and discriminant descriptions, which are stored in the knowledge base and are employed to diagnose faults. MLS was successfully tested on jet engine examples.

Ali, Moonis↗

NASA NTRS1991

ECLIPS: An extended CLIPS for backward chaining and goal-directed reasoning

Realistic production systems require an integrated combination of forward and backward reasoning to reflect appropriately the processes of natural human expert reasoning. A control mechanism that consists solely of forward reasoning is not an effective way to promptly focus the system's attention as calculation proceeds. Often, expert system programmers will attempt to compensate for this lack by using data to enforce the desired goal directed control structure. This approach is inherently flawed in that it is attempting to use data to fulfill the role of control. This paper will describe our implementation of backward chaining in C Language Integrated Production System (CLIPS), and show how this has shortened and simplified various CLIPS programs. This work was done at the Aerospace Corporation, and has general applicability.

Homeier, Peter V.↗

NASA NTRS2009

Policy-Based Management Natural Language Parser

The Policy-Based Management Natural Language Parser (PBEM) is a rules-based approach to enterprise management that can be used to automate certain management tasks. This parser simplifies the management of a given endeavor by establishing policies to deal with situations that are likely to occur. Policies are operating rules that can be referred to as a means of maintaining order, security, consistency, or other ways of successfully furthering a goal or mission. PBEM provides a way of managing configuration of network elements, applications, and processes via a set of high-level rules or business policies rather than managing individual elements, thus switching the control to a higher level. This software allows unique management rules (or commands) to be specified and applied to a cross-section of the Global Information Grid (GIG). This software embodies a parser that is capable of recognizing and understanding conversational English. Because all possible dialect variants cannot be anticipated, a unique capability was developed that parses passed on conversation intent rather than the exact way the words are used. This software can increase productivity by enabling a user to converse with the system in conversational English to define network policies. PBEM can be used in both manned and unmanned science-gathering programs. Because policy statements can be domain-independent, this software can be applied equally to a wide variety of applications.

James, Mark↗

NASA NTRS2012

Copilot: Monitoring Embedded Systems

Runtime verification (RV) is a natural fit for ultra-critical systems, where correctness is imperative. In ultra-critical systems, even if the software is fault-free, because of the inherent unreliability of commodity hardware and the adversity of operational environments, processing units (and their hosted software) are replicated, and fault-tolerant algorithms are used to compare the outputs. We investigate both software monitoring in distributed fault-tolerant systems, as well as implementing fault-tolerance mechanisms using RV techniques. We describe the Copilot language and compiler, specifically designed for generating monitors for distributed, hard real-time systems. We also describe two case-studies in which we generated Copilot monitors in avionics systems.

Pike, Lee↗

NASA NTRS1991

Debugging expert systems using a dynamically created hypertext network

The labor intensive nature of expert system writing and debugging motivated this study. The hypothesis is that a hypertext based debugging tool is easier and faster than one traditional tool, the graphical execution trace. HESDE (Hypertext Expert System Debugging Environment) uses Hypertext nodes and links to represent the objects and their relationships created during the execution of a rule based expert system. HESDE operates transparently on top of the CLIPS (C Language Integrated Production System) rule based system environment and is used during the knowledge base debugging process. During the execution process HESDE builds an execution trace. Use of facts, rules, and their values are automatically stored in a Hypertext network for each execution cycle. After the execution process, the knowledge engineer may access the Hypertext network and browse the network created. The network may be viewed in terms of rules, facts, and values. An experiment was conducted to compare HESDE with a graphical debugging environment. Subjects were given representative tasks. For speed and accuracy, in eight of the eleven tasks given to subjects, HESDE was significantly better.

Boyle, Craig D. B.↗

NASA NTRS1993

Review and analysis of dense linear system solver package for distributed memory machines

A dense linear system solver package recently developed at the University of Texas at Austin for distributed memory machine (e.g. Intel Paragon) has been reviewed and analyzed. The package contains about 45 software routines, some written in FORTRAN, and some in C-language, and forms the basis for parallel/distributed solutions of systems of linear equations encountered in many problems of scientific and engineering nature. The package, being studied by the Computer Applications Branch of the Analysis and Computation Division, may provide a significant computational resource for NASA scientists and engineers in parallel/distributed computing. Since the package is new and not well tested or documented, many of its underlying concepts and implementations were unclear; our task was to review, analyze, and critique the package as a step in the process that will enable scientists and engineers to apply it to the solution of their problems. All routines in the package were reviewed and analyzed. Underlying theory or concepts which exist in the form of published papers or technical reports, or memos, were either obtained from the author, or from the scientific literature; and general algorithms, explanations, examples, and critiques have been provided to explain the workings of these programs. Wherever the things were still unclear, communications were made with the developer (author), either by telephone or by electronic mail, to understand the workings of the routines. Whenever possible, tests were made to verify the concepts and logic employed in their implementations. A detailed report is being separately documented to explain the workings of these routines.

Narang, H. N.↗

DOE OSTI2026

Conservation laws and effective hadronization models

Hadronization models based on local string-breaking dynamics are typically Markovian by construction, yet the physical ensemble of final states is shaped by global constraints that couple the entire fragmentation trajectory. Recasting hadronization as a conditioned stochastic diffusion process provides a precise mathematical resolution to this tension. In particular, this language reveals explicitly that constraints stemming from conservation laws induce non-Markovian correlations between otherwise independent fragmentation steps, and that these correlations can be absorbed exactly into a renormalization of the local dynamics through a Doob $h$-transform. We develop this formalism for a $q\bar{q}$ string in the chiral limit, where the longitudinal-transverse factorization of the Lund kernel becomes exact, enabling systematic power counting and clean ultraviolet (UV)/infrared (IR) separation. The dynamics organize naturally into a tower of effective theories distinguished by the remaining string mass, spanning a UV fixed point with scale-invariant transport coefficients, an intermediate regime where transverse phase space induces controlled running, and an IR boundary layer where non-local effects enter at leading order. The tower exhibits genuine Wilsonian structure, including $β$-functions, anomalous dimensions, and systematic matching conditions. The resulting framework achieves a clean factorization of universal microscopic fragmentation dynamics from infrared constraint effects, and opens new directions for both the theoretical analysis and practical simulation of hadronization.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗

DOE OSTI2024

Unsupervised multimodal fusion of in-process sensor data for advanced manufacturing process monitoring

Effective monitoring of manufacturing processes is crucial for maintaining product quality and operational efficiency. Modern manufacturing environments often generate vast amounts of complementary multimodal data, including visual imagery from various perspectives and resolutions, hyperspectral data, and machine health monitoring information such as actuator positions, accelerometer readings, and temperature measurements. However, fusing and interpreting this complex, high-dimensional data presents significant challenges, particularly when labeled datasets are unavailable or impractical to obtain. This paper presents a novel approach to multimodal sensor data fusion in manufacturing processes, inspired by the Contrastive Language-Image Pre-training (CLIP) model. We leverage contrastive learning techniques to correlate different data modalities without the need for labeled data, overcoming limitations of traditional supervised machine learning methods in manufacturing contexts. Our proposed method demonstrates the ability to handle and learn encoders for five distinct modalities: visual imagery, audio signals, laser position (x and y coordinates), and laser power measurements. By compressing these high-dimensional datasets into low-dimensional representational spaces, our approach facilitates downstream tasks such as process control, anomaly detection, and quality assurance. The unsupervised nature of our method makes it broadly applicable across various manufacturing domains, where large volumes of unlabeled sensor data are common. We evaluate the effectiveness of our approach through a series of experiments, demonstrating its potential to enhance process monitoring capabilities in advanced manufacturing systems. This research contributes to the field of smart manufacturing by providing a flexible, scalable framework for multimodal data fusion that can adapt to diverse manufacturing environments and sensor configurations. The proposed method paves the way for more robust, data-driven decision-making in complex manufacturing processes.

Contrastive Learning↗

NASA NTRS1993

Tensoral: A system for post-processing turbulence simulation data

Many computer simulations in engineering and science -- and especially in computational fluid dynamics (CFD) -- produce huge quantities of numerical data. These data are often so large as to make even relatively simple post-processing of this data unwieldy. The data, once computed and quality-assured, is most likely analyzed by only a few people. As a result, much useful numerical data is under-utilized. Since future state-of-the-art simulations will produce even larger datasets, will use more complex flow geometries, and will be performed on more complex supercomputers, data management issues will become increasingly cumbersome. My goal is to provide software which will automate the present and future task of managing and post-processing large turbulence datasets. My research has focused on the development of these software tools -- specifically, through the development of a very high-level language called 'Tensoral'. The ultimate goal of Tensoral is to convert high-level mathematical expressions (tensor algebra, calculus, and statistics) into efficient low-level programs which numerically calculate these expressions given simulation datasets. This approach to the database and post-processing problem has several advantages. Using Tensoral the numerical and data management details of a simulation are shielded from the concerns of the end user. This shielding is carried out without sacrificing post-processor efficiency and robustness. Another advantage of Tensoral is that its very high-level nature lends itself to portability across a wide variety of computing (and supercomputing) platforms. This is especially important considering the rapidity of changes in supercomputing hardware.

Dresselhaus, Eliot↗

NASA NTRS1988

An intelligent multi-media human-computer dialogue system

Sophisticated computer systems are being developed to assist in the human decision-making process for very complex tasks performed under stressful conditions. The human-computer interface is a critical factor in these systems. The human-computer interface should be simple and natural to use, require a minimal learning period, assist the user in accomplishing his task(s) with a minimum of distraction, present output in a form that best conveys information to the user, and reduce cognitive load for the user. In pursuit of this ideal, the Intelligent Multi-Media Interfaces project is devoted to the development of interface technology that integrates speech, natural language text, graphics, and pointing gestures for human-computer dialogues. The objective of the project is to develop interface technology that uses the media/modalities intelligently in a flexible, context-sensitive, and highly integrated manner modelled after the manner in which humans converse in simultaneous coordinated multiple modalities. As part of the project, a knowledge-based interface system, called CUBRICON (CUBRC Intelligent CONversationalist) is being developed as a research prototype. The application domain being used to drive the research is that of military tactical air control.

Neal, J. G.↗

NASA NTRS1993

Design issues for a reinforcement-based self-learning fuzzy controller

Fuzzy logic controllers have some often cited advantages over conventional techniques such as PID control: easy implementation, its accommodation to natural language, the ability to cover wider range of operating conditions and others. One major obstacle that hinders its broader application is the lack of a systematic way to develop and modify its rules and as result the creation and modification of fuzzy rules often depends on try-error or pure experimentation. One of the proposed approaches to address this issue is self-learning fuzzy logic controllers (SFLC) that use reinforcement learning techniques to learn the desirability of states and to adjust the consequent part of fuzzy control rules accordingly. Due to the different dynamics of the controlled processes, the performance of self-learning fuzzy controller is highly contingent on the design. The design issue has not received sufficient attention. The issues related to the design of a SFLC for the application to chemical process are discussed and its performance is compared with that of PID and self-tuning fuzzy logic controller.

Yen, John↗

NASA NTRS2014

Earth Science Data Analysis in the Era of Big Data

Anyone with even a cursory interest in information technology cannot help but recognize that "Big Data" is one of the most fashionable catchphrases of late. From accurate voice and facial recognition, language translation, and airfare prediction and comparison, to monitoring the real-time spread of flu, Big Data techniques have been applied to many seemingly intractable problems with spectacular successes. They appear to be a rewarding way to approach many currently unsolved problems. Few fields of research can claim a longer history with problems involving voluminous data than Earth science. The problems we are facing today with our Earth's future are more complex and carry potentially graver consequences than the examples given above. How has our climate changed? Beside natural variations, what is causing these changes? What are the processes involved and through what mechanisms are these connected? How will they impact life as we know it? In attempts to answer these questions, we have resorted to observations and numerical simulations with ever-finer resolutions, which continue to feed the "data deluge." Plausibly, many Earth scientists are wondering: How will Big Data technologies benefit Earth science research? As an example from the global water cycle, one subdomain among many in Earth science, how would these technologies accelerate the analysis of decades of global precipitation to ascertain the changes in its characteristics, to validate these changes in predictive climate models, and to infer the implications of these changes to ecosystems, economies, and public health? Earth science researchers need a viable way to harness the power of Big Data technologies to analyze large volumes and varieties of data with velocity and veracity. Beyond providing speedy data analysis capabilities, Big Data technologies can also play a crucial, albeit indirect, role in boosting scientific productivity by facilitating effective collaboration within an analysis environment. To illustrate the effects of combining a Big Data technology with an effective means of collaboration, we relate the (fictitious) experience of an early-career Earth science researcher a few years beyond the present, interlaced and contrasted with reminiscences of its recent past (i.e., the present).

Kuo, K.-S.↗

NASA NTRS2012

LogScope

LogScope is a software package for analyzing log files. The intended use is for offline post-processing of such logs, after the execution of the system under test. LogScope can, however, in principle, also be used to monitor systems online during their execution. Logs are checked against requirements formulated as monitors expressed in a rule-based specification language. This language has similarities to a state machine language, but is more expressive, for example, in its handling of data parameters. The specification language is user friendly, simple, and yet expressive enough for many practical scenarios. The LogScope software was initially developed to specifically assist in testing JPL s Mars Science Laboratory (MSL) flight software, but it is very generic in nature and can be applied to any application that produces some form of logging information (which almost any software does).

Havelund, Klaus↗

NASA NTRS1989

User's guide: Programs for processing altimeter data over inland seas

The programs described were developed to process GEODYN-formatted satellite altimeter data, and to apply the processed results to predict geoid undulations and gravity anomalies of inland sea areas. These programs are written in standard FORTRAN 77 and are designed to run on the NSESCC IBM 3081(MVS) computer. Because of the experimental nature of these programs they are tailored to the geographical area analyzed. The attached program listings are customized for processing the altimeter data over the Black Sea. Users interested in the Caspian Sea data are expected to modify each program, although the required modifications are generally minor. Program control parameters are defined in the programs via PARAMETER statements and/or DATA statements. Other auxiliary parameters, such as labels, are hard-wired into the programs. Large data files are read in or written out through different input or output units. The program listings of these programs are accompanied by sample IBM job control language (JCL) images. Familiarity with IBM JCL and the TEMPLATE graphic package is assumed.

Au, A. Y.↗

NASA NTRS1990

Integration of object-oriented knowledge representation with the CLIPS rule based system

The paper describes a portion of the work aimed at developing an integrated, knowledge based environment for the development of engineering-oriented applications. An Object Representation Language (ORL) was implemented in C++ which is used to build and modify an object-oriented knowledge base. The ORL was designed in such a way so as to be easily integrated with other representation schemes that could effectively reason with the object base. Specifically, the integration of the ORL with the rule based system C Language Production Systems (CLIPS), developed at the NASA Johnson Space Center, will be discussed. The object-oriented knowledge representation provides a natural means of representing problem data as a collection of related objects. Objects are comprised of descriptive properties and interrelationships. The object-oriented model promotes efficient handling of the problem data by allowing knowledge to be encapsulated in objects. Data is inherited through an object network via the relationship links. Together, the two schemes complement each other in that the object-oriented approach efficiently handles problem data while the rule based knowledge is used to simulate the reasoning process. Alone, the object based knowledge is little more than an object-oriented data storage scheme; however, the CLIPS inference engine adds the mechanism to directly and automatically reason with that knowledge. In this hybrid scheme, the expert system dynamically queries for data and can modify the object base with complete access to all the functionality of the ORL from rules.

Logie, David S.↗

NASA NTRS1994

Language in Comparative Perspective

The twentieth century will be noted for a wide variety of scientific and technological advancements, including powered flight, antibiotics, space travel, and the breaking of the genetic code. It also should be noted as the century in which major psychological, as well as biological, continuities between animal and human have been defined. Charles Darwin (1859) was quite right when he anticipated continuity in mental processes, some of which provide for language. Though none will argue that any animal has the full capacity of humans for language, none should deny that at least some animals have quite impressive competencies for language skills, including speech comprehension. The finding that the language skills in the bonobo and the chimpanzee are likely more fully and efficiently developed as a result of early rearing than by formal training at a later age declares a continuity even stronger than that defined by the language acquisition potential of the ape. To clarify, because early rearing facilitates the emergence of language in ape as well as in child, a naturalness to the familiar course of language acquisition, whereby comprehension precedes production, is also corroborated. In turn, the continuity and the shared naturalness of language acquisition serve jointly to define an advanced and critical point of linkage between the genera Pan and Homo - and, as concluded by Domjan (1993), one worthy of contributing to the series of reconceptions of ourselves as anticipated by Ploog and Melnechuk (1971).

Rumbaugh, Duane M.↗

NASA NTRS2017

Improving the Plasticity of LIMS Implementation: LIMS Extension through Microsoft Excel

A Laboratory Information Management System (LIMS) is a databasing software with many built-in tools ideal for handling and documenting most laboratory processes in an accurate and consistent manner, making it an indispensable tool for the modern laboratory. However, a lot of LIMS end users will find that in the performance of analyses that have unique considerations such as standard curves, multiple stages incubations, or logical considerations, a base LIMS distribution may not ideally suit their needs. These considerations bring about the need for extension languages, which can extend the functionality of a LIMS. While these languages do provide the implementation team the functionality required to accommodate these special laboratory analyses, they are usually too complex for the end user to modify to compensate for natural changes in laboratory operations. The LIMS utilized by our laboratory offers a unique and easy-to-use choice for an extension language, one that is already heavily relied upon not only in science but also in most academic and business pursuits: Microsoft Excel. The validity of Microsoft Excel as a pseudo programming language and its usability and versatility as a LIMS extension language will be discussed. The NELAC implications and overall drawbacks of this LIMS configuration will also be discussed.

LIMS↗