Results for “natural intelligence” — Page 2

NASA NTRS2004

Intelligent Systems: Shaping the Future of Aeronautics and Space Exploration

Intelligent systems are nature-inspired, mathematically sound, computationally intensive problem solving tools and methodologies that have become important for NASA's future roles in Aeronautics and Space Exploration. Intelligent systems will enable safe, cost and mission-effective approaches to air& control, system design, spacecraft autonomy, robotic space exploration and human exploration of Moon, Mars, and beyond. In this talk, we will discuss intelligent system technologies and expand on the role of intelligent systems in NASA's missions. We will also present several examples of which some are highlighted m this extended abstract.

Krishnakumar, Kalmanje↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗

NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗

NASA NTRS1983

An overview of computer-based natural language processing

Computer based Natural Language Processing (NLP) is the key to enabling humans and their computer based creations to interact with machines in natural language (like English, Japanese, German, etc., in contrast to formal computer languages). The doors that such an achievement can open have made this a major research area in Artificial Intelligence and Computational Linguistics. Commercial natural language interfaces to computers have recently entered the market and future looks bright for other applications as well. This report reviews the basic approaches to such systems, the techniques utilized, applications, the state of the art of the technology, issues and research requirements, the major participants and finally, future trends and expectations. It is anticipated that this report will prove useful to engineering and research managers, potential users, and others who will be affected by this field as it unfolds.

Gevarter, W. B.↗

NASA NTRS1994

Learning procedures from interactive natural language instructions

Despite its ubiquity in human learning, very little work has been done in artificial intelligence on agents that learn from interactive natural language instructions. In this paper, the problem of learning procedures from interactive, situated instruction is examined in which the student is attempting to perform tasks within the instructional domain, and asks for instruction when it is needed. Presented is Instructo-Soar, a system that behaves and learns in response to interactive natural language instructions. Instructo-Soar learns completely new procedures from sequences of instruction, and also learns how to extend its knowledge of previously known procedures to new situations. These learning tasks require both inductive and analytic learning. Instructo-Soar exhibits a multiple execution learning process in which initial learning has a rote, episodic flavor, and later executions allow the initially learned knowledge to be generalized properly.

Huffman, Scott B.↗

NASA NTRS1987

The intelligent user interface for NASA's advanced information management systems

NASA has initiated the Intelligent Data Management Project to design and develop advanced information management systems. The project's primary goal is to formulate, design and develop advanced information systems that are capable of supporting the agency's future space research and operational information management needs. The first effort of the project was the development of a prototype Intelligent User Interface to an operational scientific database, using expert systems and natural language processing technologies. An overview of Intelligent User Interface formulation and development is given.

Campbell, William J.↗

NASA NTRSDate not supplied

Evaluating Machine Learning Approaches to Plume Tracking

On July 15, 2022, the Hunga Tonga-Hunga Ha’apai (HTHH) submarine volcano erupted, propelling trace gasses and ash through the troposphere and up into the stratosphere. Previous studies manually tracked the aerosol and trace gas plumes over time across different positions in the southern hemisphere. Using imagery from NASA’s Earth Observing System, including MODIS aerosol products and OMI sulfur dioxide products, this research demonstrates how open-source machine learning (ML) models, like Meta’s Segment Anything Model (SAM), can perform automatic plume tracking following the Hunga Tonga eruption. This extensible methodology, and modular data processing and modeling pipeline, establishes a framework for systematically and rapidly studying natural disasters, including additional volcanic eruptions and large-scale wildfires. By combining advanced machine learning techniques, such as SAM’s zero-shot learning, with large volumes of NASA’s Earth Observation and remote sensing data, this work shows how AI and open science can accelerate research and generate actionable results, even for unprecedented events. The tools and technologies presented here can help translate earth science to action from NASA’s current and future Earth observing satellite missions, and assist researchers and stakeholders in understanding, mapping, and responding to natural disasters in a changing world.

machine learning↗

NASA NTRS1990

Intelligent search and retrieval of a large multimedia knowledgebase for the Hubble Space Telescope

A document-retrieval assistant (DRA) in a microcomputer format is described which incorporates hypertext and natural language capabilities. Hypertext is used to introduce an intelligent search capability, and the natural-language interface permits access to specific data without the use of keywords. The DRA can be used to access and 'browse' the large multimedia database that is composed of project documentation from the HST.

Clapis, Paul J.↗

NASA NTRS1981

The demography of extraterrestrial civilizations

Studies carried out within the last ten years on the nature and distribution of extraterrestrial intelligent life are reviewed. Arguments for the absence of intelligent life in the Galaxy based on the assumption that at least some of these would have engaged in colonization and for the presence of colonies of extraterrestrials in some undiscovered location in the solar system are presented, and it is noted that both these views rest on the notion that interstellar travel can be achieved at high velocities in very large vehicles, which has been questioned. Alternative suggestions concerning interstellar exploration by automated probes and the possible extended time scale and motivation for galactic colonization are pointed out. Attention is then given to arguments for the extreme smallness of one of the factors in the Drake equation used to estimate the number of communicative extraterrestrial civilizations in the Galaxy, including the frequency of single stars, the likelihood that planets with the correct initial composition and conditions for life are at the proper distance from their stars, the probability of the formation of DNA and the origin of life, and the time for the evolution of intelligence. It is concluded that it seems likely that other civilizations exist in the Galaxy, although the number and distribution of such civilizations may only be determined by the detection of one or more examples.

Billingham, J.↗

NASA NTRSDate not supplied

GeoAI advances in specific landform mapping

Landform mapping (also referred to as geomorphology or geomorphometry) can be divided into two domains: general and specific (Evans 2012). Whereas general landform mapping categorizes all elements of the study area into landform classes, such as ridges, valleys, peaks, and depressions, the mapping of specific landforms requires the delineation (even if fuzzy) of individual landforms. The former is mainly driven by physical properties such as elevation, slope, and curvature. The latter, however, must consider the cognitive (human) reasoning that discriminates individual landforms in addition to these physical properties (Arundel and Sinha 2018). Both mapping forms are important. General geomorphometry is needed to understand geological and ecological processes and as boundary layer input to climate and environmental models. Specific geomorphometry supports such activities as disaster management and recovery, emergency response, transportation, and navigation. In the United States, individual landforms of interest are named in the U.S. Geological Survey (USGS) Geographic Names Information System, a point dataset captured specifically to digitize geographic names from the USGS Historical Topographic Map Collection (HTMC). Named landform extent is represented only by the name placement in the HTMC. Recent work has investigated CNN-based deep learning methods to capture these extents in machine-readable form. These studies first relied on physical properties (Arundel et al. 2020) and then included the HTMC as a band in RGB images in limited testing (Arundel et al. 2023). Results from the HTMC dataset surpassed those using just physical properties and using the HTMC alone performed best due to the hillshading and elevation (contour) data incorporated into the topographic maps. However, results fell short of an operational capacity to map all named landforms in the United States. Thus, our current work expands upon past research by focusing on the HTMC and physical information as inputs and the named landform label extents. Specifically, we propose to leverage pre-trained foundation models for segmentation and optical character recognition (OCR) models to jointly map landforms in the United States. Our approach aims to bridge the disparities among the independent information sources to facilitate informed decision-making. The modeling pipeline performs (1) segmentation using the physical information and (2) information extraction using OCR, in parallel. Then a computer vision approach merges the two branches into a labeled segmentation. References: Arundel, Samantha T., Wenwen Li, and Sizhe Wang. 2020. “GeoNat v1.0: A Dataset for Natural Feature Mapping with Artificial Intelligence and Supervised Learning.” Transactions in GIS 24 (3): 556–72. https://doi.org/10.1111/tgis.12633. Arundel, Samantha T, and Gaurav Sinha. 2018. “Validating GEOBIA Based Terrain Segmentation and Classification for Automated Delineation of Cognitively Salient Landforms BT - Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017).” In Proceedings of Workshops and Posters at the 13th International Conference on Spatial Information Theory (COSIT 2017), Lecture Notes in Geoinformation and Cartography, edited by Paolo Fogliaroni, Andrea Ballatore, and Eliseo Clementini, 9–14. Cham: Springer International Publishing. Arundel, Samantha T., Gaurav Sinha, Wenwen Li, David P. Martin, Kevin G. McKeehan, and Philip T. Thiem. 2023. “Historical Maps Inform Landform Cognition in Machine Learning.” Abstracts of the ICA 6 (August): 1–2. https://doi.org/10.5194/ica-abs-6-10-2023. Evans, Ian S. 2012. “Geomorphometry and Landform Mapping: What Is a Landform?” Geomorphology 137 (1): 94–106. https://doi.org/10.1016/j.geomorph.2010.09.029.

machine learning↗

NASA NTRS2022

Virtual Assistant for First Responders Using Natural Language Understanding and Optical Character Recognition

Commercial deep learning capabilities are available for many applications such as computer vision processing and intelligent chat bots. The Google Cloud Platform product Google Dialogflow provides lifelike conversational artificial intelligence (AI) using machine learning (ML) to generate natural conversations between computers and humans. This ML utilizes natural language understanding (NLU) to recognize a user’s intent and extracts key information into a form of entities. We have developed a user-friendly application through understanding the hazardous material database, first aid safety guidelines and observing the process of first responders who access this information in the field. We created the Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL) virtual assistant using Dialogflow1 and TensorFlow2 paired with EasyOCR.3 The chatbot supports first responders by providing voice interaction which helps limit additional steps such as browsing through multiple categories when searching for information. Using feedback from our field interviews, the voice interface has been developed to enable the first responder to focus on the immediate emergency. With less distractions, the first responder is able to engage the incident more effectively. The partial hands-free TruePAL chatbot assistant improves the accessibility to the correct guidance by an average of 1.9 seconds compared to the widely used application, NIH WISER, which requires full attention to operate. We combined this intelligent chatbot with a separate visual processing capability to produce hazardous signage analysis and generate the proper guidance for first responders. With the evolving functionality of AI tools, the use of virtual assistants in first responder technology will be an advancement, benefiting the safety of both first responders and civilians.

Chow, Edward↗

NASA NTRS2000

The Biological Relevance of Artificial Life: Lessons from Artificial Intelligence

There is no fundamental reason why A-life couldn't simply be a branch of computer science that deals with algorithms that are inspired by, or emulate biological phenomena. However, if these are the limits we place on this field, we miss the opportunity to help advance Theoretical Biology and to contribute to a deeper understanding of the nature of life. The history of Artificial Intelligence provides a good example, in that early interest in the nature of cognition quickly was lost to the process of building tools, such as "expert systems" that, were certainly useful, but provided little insight in the nature of cognition. Based on this lesson, I will discuss criteria for increasing the biological relevance of A-life and the probability that this field may provide a theoretical foundation for Biology.

Colombano, Silvano↗

NASA NTRS1987

Space Station Mission Planning System (MPS) development study. Volume 2

The process and existing software used for Spacelab payload mission planning were studied. A complete baseline definition of the Spacelab payload mission planning process was established, along with a definition of existing software capabilities for potential extrapolation to the Space Station. This information was used as a basis for defining system requirements to support Space Station mission planning. The Space Station mission planning concept was reviewed for the purpose of identifying areas where artificial intelligence concepts might offer substantially improved capability. Three specific artificial intelligence concepts were to be investigated for applicability: natural language interfaces; expert systems; and automatic programming. The advantages and disadvantages of interfacing an artificial intelligence language with existing FORTRAN programs or of converting totally to a new programming language were identified.

Klus, W. J.↗

NASA NTRS1994

High-speed data search

The high-speed data search system developed for KSC incorporates existing and emerging information retrieval technology to help a user intelligently and rapidly locate information found in large textual databases. This technology includes: natural language input; statistical ranking of retrieved information; an artificial intelligence concept called semantics, where 'surface level' knowledge found in text is used to improve the ranking of retrieved information; and relevance feedback, where user judgements about viewed information are used to automatically modify the search for further information. Semantics and relevance feedback are features of the system which are not available commercially. The system further demonstrates focus on paragraphs of information to decide relevance; and it can be used (without modification) to intelligently search all kinds of document collections, such as collections of legal documents medical documents, news stories, patents, and so forth. The purpose of this paper is to demonstrate the usefulness of statistical ranking, our semantic improvement, and relevance feedback.

Driscoll, James N.↗

NASA NTRS1995

Computer-Assisted Search Of Large Textual Data Bases

"QA" denotes high-speed computer system for searching diverse collections of documents including (but not limited to) technical reference manuals, legal documents, medical documents, news releases, and patents. Incorporates previously available and emerging information-retrieval technology to help user intelligently and rapidly locate information found in large textual data bases. Technology includes provision for inquiries in natural language; statistical ranking of retrieved information; artificial-intelligence implementation of semantics, in which "surface level" knowledge found in text used to improve ranking of retrieved information; and relevance feedback, in which user's judgements of relevance of some retrieved documents used automatically to modify search for further information.

Driscoll, James R.↗

NASA NTRS1985

Our Future in the Cosmos: Computers

The future of computers and the computerization of society are discussed. Speculation regarding the nature and appropriate application of computer intelligence and human intelligence is given.

Asimov, I.↗

NASA NTRS1987

A space systems perspective of graphics simulation integration

Creation of an interactive display environment can expose issues in system design and operation not apparent from nongraphics development approaches. Large amounts of information can be presented in a short period of time. Processes can be simulated and observed before committing resources. In addition, changes in the economics of computing have enabled broader graphics usage beyond traditional engineering and design into integrated telerobotics and Artificial Intelligence (AI) applications. The highly integrated nature of space operations often tend to rely upon visually intensive man-machine communication to ensure success. Graphics simulation activities at the Mission Planning and Analysis Division (MPAD) of NASA's Johnson Space Center are focusing on the evaluation of a wide variety of graphical analysis within the context of present and future space operations. Several telerobotics and AI applications studies utilizing graphical simulation are described. The presentation includes portions of videotape illustrating technology developments involving: (1) coordinated manned maneuvering unit and remote manipulator system operations, (2) a helmet mounted display system, and (3) an automated rendezous application utilizing expert system and voice input/output technology.

Brown, R.↗