Search NASA⌕ Search

SEARCH · Search NASA

Results for “Artificial intelligence (AI)”

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.

422 records · Page 24
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

A Knowledge-Based Representation Scheme for Environmental Science Models

One of the primary methods available for studying environmental phenomena is the construction and analysis of computational models. We have been studying how artificial intelligence techniques can be applied to assist in the development and use of environmental science models within the context of NASA-sponsored activities. We have identified several high-utility areas as potential targets for research and development: model development; data visualization, analysis, and interpretation; model publishing and reuse, training and education; and framing, posing, and answering questions. Central to progress on any of the above areas is a representation for environmental models that contains a great deal more information than is present in a traditional software implementation. In particular, a traditional software implementation is devoid of any semantic information that connects the code with the environmental context that forms the background for the modeling activity. Before we can build AI systems to assist in model development and usage, we must develop a representation for environmental models that adequately describes a model's semantics and explicitly represents the relationship between the code and the modeling task at hand. We have developed one such representation in conjunction with our work on the SIGMA (Scientists' Intelligent Graphical Modeling Assistant) environment. The key feature of the representation is that it provides a semantic grounding for the symbols in a set of modeling equations by linking those symbols to an explicit representation of the underlying environmental scenario.

Keller, Richard M.↗
NASA NTRS1987

Geometric reasoning

Cognitive robot systems are ones in which sensing and representation occur, from which task plans and tactics are determined. Such a robot system accomplishes a task after being told what to do, but determines for itself how to do it. Cognition is required when the work environment is uncontrolled, when contingencies are prevalent, or when task complexity is large; it is useful in any robotic mission. A number of distinguishing features can be associated with cognitive robotics, and one emphasized here is the role of artificial intelligence in knowledge representation and in planning. While space telerobotics may elude some of the problems driving cognitive robotics, it shares many of the same demands, and it can be assumed that capabilities developed for cognitive robotics can be employed advantageously for telerobotics in general. The top level problem is task planning, and it is appropriate to introduce a hierarchical view of control. Presented with certain mission objectives, the system must generate plans (typically) at the strategic, tactical, and reflexive levels. The structure by which knowledge is used to construct and update these plans endows the system with its cognitive attributes, and with the ability to deal with contingencies, changes, unknowns, and so on. Issues of representation and reasoning which are absolutely fundamental to robot manipulation, decisions based upon geometry, are discussed here, not AI task planning per se.

Woodbury, R. F.↗
NASA NTRS1986

An artificial intelligence approach to onboard fault monitoring and diagnosis for aircraft applications

Real-time onboard fault monitoring and diagnosis for aircraft applications, whether performed by the human pilot or by automation, presents many difficult problems. Quick response to failures may be critical, the pilot often must compensate for the failure while diagnosing it, his information about the state of the aircraft is often incomplete, and the behavior of the aircraft changes as the effect of the failure propagates through the system. A research effort was initiated to identify guidelines for automation of onboard fault monitoring and diagnosis and associated crew interfaces. The effort began by determining the flight crew's information requirements for fault monitoring and diagnosis and the various reasoning strategies they use. Based on this information, a conceptual architecture was developed for the fault monitoring and diagnosis process. This architecture represents an approach and a framework which, once incorporated with the necessary detail and knowledge, can be a fully operational fault monitoring and diagnosis system, as well as providing the basis for comparison of this approach to other fault monitoring and diagnosis concepts. The architecture encompasses all aspects of the aircraft's operation, including navigation, guidance and controls, and subsystem status. The portion of the architecture that encompasses subsystem monitoring and diagnosis was implemented for an aircraft turbofan engine to explore and demonstrate the AI concepts involved. This paper describes the architecture and the implementation for the engine subsystem.

Schutte, P. C.↗
NASA NTRS1990

Compiling knowledge-based systems from KEE to Ada

The dominant technology for developing AI applications is to work in a multi-mechanism, integrated, knowledge-based system (KBS) development environment. Unfortunately, systems developed in such environments are inappropriate for delivering many applications - most importantly, they carry the baggage of the entire Lisp environment and are not written in conventional languages. One resolution of this problem would be to compile applications from complex environments to conventional languages. Here the first efforts to develop a system for compiling KBS developed in KEE to Ada (trademark). This system is called KATYDID, for KEE/Ada Translation Yields Development Into Delivery. KATYDID includes early prototypes of a run-time KEE core (object-structure) library module for Ada, and translation mechanisms for knowledge structures, rules, and Lisp code to Ada. Using these tools, part of a simple expert system was compiled (not quite automatically) to run in a purely Ada environment. This experience has given us various insights on Ada as an artificial intelligence programming language, potential solutions of some of the engineering difficulties encountered in early work, and inspiration on future system development.

Filman, Robert E.↗
NASA NTRS1988

NESSUS (Numerical Evaluation of Stochastic Structures Under Stress)/EXPERT: Bridging the gap between artificial intelligence and FORTRAN

The development of a probabilistic structural analysis methodology (PSAM) is described. In the near-term, the methodology will be applied to designing critical components of the next generation space shuttle main engine. In the long-term, PSAM will be applied very broadly, providing designers with a new technology for more effective design of structures whose character and performance are significantly affected by random variables. The software under development to implement the ideas developed in PSAM resembles, in many ways, conventional deterministic structural analysis code. However, several additional capabilities regarding the probabilistic analysis makes the input data requirements and the resulting output even more complex. As a result, an intelligent front- and back-end to the code is being developed to assist the design engineer in providing the input data in a correct and appropriate manner. The type of knowledge that this entails is, in general, heuristically-based, allowing the fairly well-understood technology of production rules to apply with little difficulty. However, the PSAM code, called NESSUS, is written in FORTRAN-77 and runs on a DEC VAX. Thus, the associated expert system, called NESSUS/EXPERT, must run on a DEC VAX as well, and integrate effectively and efficiently with the existing FORTRAN code. This paper discusses the process undergone to select a suitable tool, identify an appropriate division between the functions that should be performed in FORTRAN and those that should be performed by production rules, and how integration of the conventional and AI technologies was achieved.

Fink, Pamela K.↗
NASA NTRSDate not supplied

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗
NASA NTRS1993

Adaptive laser link reconfiguration using constraint propagation

This paper describes Harris AI research performed on the Adaptive Link Reconfiguration (ALR) study for Rome Lab, and focuses on the application of constraint propagation to the problem of link reconfiguration for the proposed space based Strategic Defense System (SDS) Brilliant Pebbles (BP) communications system. According to the concept of operations at the time of the study, laser communications will exist between BP's and to ground entry points. Long-term links typical of RF transmission will not exist. This study addressed an initial implementation of BP's based on the Global Protection Against Limited Strikes (GPALS) SDI mission. The number of satellites and rings studied was representative of this problem. An orbital dynamics program was used to generate line-of-site data for the modeled architecture. This was input into a discrete event simulation implemented in the Harris developed COnstraint Propagation Expert System (COPES) Shell, developed initially on the Rome Lab BM/C3 study. Using a model of the network and several heuristics, the COPES shell was used to develop the Heuristic Adaptive Link Ordering (HALO) Algorithm to rank and order potential laser links according to probability of communication. A reduced set of links based on this ranking would then be used by a routing algorithm to select the next hop. This paper includes an overview of Constraint Propagation as an Artificial Intelligence technique and its embodiment in the COPES shell. It describes the design and implementation of both the simulation of the GPALS BP network and the HALO algorithm in COPES. This is described using a 59 Data Flow Diagram, State Transition Diagrams, and Structured English PDL. It describes a laser communications model and the heuristics involved in rank-ordering the potential communication links. The generation of simulation data is described along with its interface via COPES to the Harris developed View Net graphical tool for visual analysis of communications networks. Conclusions are presented, including a graphical analysis of results depicting the ordered set of links versus the set of all possible links based on the computed Bit Error Rate (BER). Finally, future research is discussed which includes enhancements to the HALO algorithm, network simulation, and the addition of an intelligent routing algorithm for BP.

Crone, M. S.↗
NASA NTRSDate not supplied

Atlas: Navigating NASA’s Knowledge Universe with AI-Powered Natural Language Queries

NASA has a vast archive of engineering guidelines, standards, and best practices collected over decades. This encompasses a breadth of topics from rocketry and engineering standards to risk management and space-related health issues. This wealth of information, while invaluable to NASA engineers, staff, and the public, is too extensive for any individual to fully comprehend. To address this challenge, we have developed Atlas, a tool within NASA's Mission Cloud Platform that enables users to query these diverse sources effectively. Atlas allows users to ask natural language questions and receive answers grounded in factual information from source documents. The tool provides responses with direct quotations and links to original documents, ensuring transparency and accuracy. It can address a wide range of queries, from specific technical details like safe distances for rocket launches from lightning to broader topics such as crew health requirements for long-duration space missions, corrosion protection in low Earth orbit, and NASA's agreements with various entities. In developing Atlas, we encountered and overcame several technical challenges. Large Language Models often struggle with consistently providing accurate information, especially for highly specialized topics. We implemented strategies to prevent hallucinations and ensure the reliability of responses, even for complex questions on topics ranging from NASA Mission Classes to intricate rocket science concepts. Additionally, we addressed the challenges of delivering quick responses while maintaining cost-effectiveness. Our presentation will detail the innovative approaches we employed to optimize performance and efficiency, making Atlas a powerful and practical tool for accessing NASA's extensive knowledge base.

Artificial Intelligence↗