Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Agent”

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 145 records · Page 8

Preliminary results of the autonomous sciencecraft experiment

The Autonomous Sciencecraft Experiment (ASE) will operate onboard the Earth Orbiter 1 mission 2004. The ASE software uses onboard continuous planning, robust task and goal-based execution, and onboard machine learning and patter recognition to radically increase science return by enabling intelligent downlink selection and autnomous retargeting. In this paper we will discuss how these AI technologies are synergistically integrated in multi-layer control architecture to enable a virtual spacecraft science agent.

Rabideau, Gregg↗

Gaming the beamlines—employing reinforcement learning to maximize scientific outcomes at large-scale user facilities

Abstract Beamline experiments at central facilities are increasingly demanding of remote, high-throughput, and adaptive operation conditions. To accommodate such needs, new approaches must be developed that enable on-the-fly decision making for data intensive challenges. Reinforcement learning (RL) is a domain of AI that holds the potential to enable autonomous operations in a feedback loop between beamline experiments and trained agents. Here, we outline the advanced data acquisition and control software of the Bluesky suite, and demonstrate its functionality with a canonical RL problem: cartpole. We then extend these methods to efficient use of beamline resources by using RL to develop an optimal measurement strategy for samples with different scattering characteristics. The RL agents converge on the empirically optimal policy when under-constrained with time. When resource limited, the agents outperform a naive or sequential measurement strategy, often by a factor of 100%. We interface these methods directly with the data storage and provenance technologies at the National Synchrotron Light Source II, thus demonstrating the potential for RL to increase the scientific output of beamlines, and layout the framework for how to achieve this impact.

36 MATERIALS SCIENCE↗

Secure API-Driven Research Automation to Accelerate Scientific Discovery

The Secure Scientific Service Mesh (S3M) provides API-driven infrastructure to accelerate scientific discovery through automated research workflows. By integrating near real-time streaming capabilities, intelligent workflow orchestration, and fine-grained authorization within a service mesh architecture, S3M enables secure and flexible programmatic access to high performance computing (HPC) resources. This framework allows intelligent agents and experimental facilities to dynamically provision resources and execute complex workflows, accelerating experimental lifecycles, and enabling AI-augmented autonomous science. S3M establishes a modern foundation for scientific computing infrastructure that significantly reduces traditional barriers between researchers, computational resources, and experimental facilities.

Skluzacek, Tyler [ORNL] (ORCID:0000000322424931)↗

Future applications of artificial intelligence to Mission Control Centers

Future applications of artificial intelligence to Mission Control Centers are presented in the form of the viewgraphs. The following subject areas are covered: basic objectives of the NASA-wide AI program; inhouse research program; constraint-based scheduling; learning and performance improvement for scheduling; GEMPLAN multi-agent planner; planning, scheduling, and control; Bayesian learning; efficient learning algorithms; ICARUS (an integrated architecture for learning); design knowledge acquisition and retention; computer-integrated documentation; and some speculation on future applications.

Friedland, Peter↗

Spacecraft autonomy using onboard processing for a SAR constellation mission

The Autonomous Sciencecraft Experiment (ASE) will fly onboard the Air Force TechSat 21 constellation of three spacecraft scheduled for launch in 2006. ASE uses onboard continuous planning, robust task and goal-based execution, model-based mode identification and reconfiguration, and onboard machine learning and pattern recognition to radically increase science return by enabling intelligent downlink selection and autonomous retargeting. In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecruft science agent. Demonstration of these capabilities in a flight environment will open up tremendous new opportunities in planetary science, space physics, and earth science that would be unreachable without this technology.

Autonomous Sciencecraft Experiment ASE virtual spa↗

Lessons Learned from Autonomous Sciencecraft Experiment

An Autonomous Science Agent has been flying onboard the Earth Observing One Spacecraft since 2003. This software enables the spacecraft to autonomously detect and responds to science events occurring on the Earth such as volcanoes, flooding, and snow melt. The package includes AI-based software systems that perform science data analysis, deliberative planning, and run-time robust execution. This software is in routine use to fly the EO-l mission. In this paper we briefly review the agent architecture and discuss lessons learned from this multi-year flight effort pertinent to deployment of software agents to critical applications.

Autonomous Sciencecraft Experiment (ASE)↗

Making the Grid "Smart" Through "Smart" Microgrids: Real-Time Power Management of Microgrids with Multiple Distributed Generation Sources Using Intelligent Control

In this Project we collaborated with two DOE National Laboratories, Pacific Northwest National Lab (PNNL) and Lawrence Berkeley National Lab (LBL). Dr. Hammerstrom of PNNL initially supported our project and was on the graduate committee of one of the Ph.D. students (graduated in 2014) who was supported by this project. He is also a committee member of a current graduate student of the PI who was supported by this project in the last two years (August 2014-July 2016). The graduate student is now supported be the Electrical and Computer Engineering (ECE) Department at Montana State University (MSU). Dr. Chris Marney of LBL provided actual load data, and the software WEBOPT developed at LBL for microgrid (MG) design for our project. NEC-Labs America, a private industry, also supported our project, providing expert support and modest financial support. We also used the software “HOMER,” originally developed at the National Renewable Energy Laboratory (NREL) and the most recent version made available to us by HOMER Energy, Inc., for MG (hybrid energy system) unit sizing. We compared the findings from WebOpt and HOMER and designed appropriately sized hybrid systems for our case studies. The objective of the project was to investigate real-time power management strategies for MGs using intelligent control, considering maximum feasible energy sustainability, reliability and efficiency while, minimizing cost and undesired environmental impact (emissions). Through analytic and simulation studies, we evaluated the suitability of several heuristic and artificial-intelligence (AI)-based optimization techniques that had potential for real-time MG power management, including genetic algorithms (GA), ant colony optimization (ACO), particle swarm optimization (PSO), and multi-agent systems (MAS), which is based on the negotiation of smart software-based agents. We found that PSO and MAS, in particular, distributed MAS, were more efficient and better suited for our work. We investigated the following: • Intelligent load control - demand response (DR) - for frequency stabilization in islanded MGs (partially supported by PNNL). • The impact of high penetration of solar photovoltaic (PV)-generated power at the distribution level (partially supported by PNNL). • The application of AI approaches to renewable (wind, PV) power forecasting (proposed by the reviewers of our proposal). • Application of AI approaches and DR for real-time MG power management (partially supported by NEC Labs-America) • Application of DR in dealing with the variability of wind power • Real-time MG power management using DR and storage (partially supported by NEC Labs-America) • Application of DR in enhancing the performance of load-frequency controller • MAS-based whole-sale and retail power market design for smart grid A

24 POWER TRANSMISSION AND DISTRIBUTION↗

The AI Bus architecture for distributed knowledge-based systems

The AI Bus architecture is layered, distributed object oriented framework developed to support the requirements of advanced technology programs for an order of magnitude improvement in software costs. The consequent need for highly autonomous computer systems, adaptable to new technology advances over a long lifespan, led to the design of an open architecture and toolbox for building large scale, robust, production quality systems. The AI Bus accommodates a mix of knowledge based and conventional components, running on heterogeneous, distributed real world and testbed environment. The concepts and design is described of the AI Bus architecture and its current implementation status as a Unix C++ library or reusable objects. Each high level semiautonomous agent process consists of a number of knowledge sources together with interagent communication mechanisms based on shared blackboards and message passing acquaintances. Standard interfaces and protocols are followed for combining and validating subsystems. Dynamic probes or demons provide an event driven means for providing active objects with shared access to resources, and each other, while not violating their security.

Schultz, Roger D.↗

Modeling the Information Age Combat Model: An Agent-Based Simulation of Network Centric Operations

The Information Age Combat Model (IACM) was introduced by Cares in 2005 to contribute to the development of an understanding of the influence of connectivity on force effectiveness that can eventually lead to quantitative prediction and guidelines for design and employment. The structure of the IACM makes it clear that the Perron-Frobenius Eigenvalue is a quantifiable metric with which to measure the organization of a networked force. The results of recent experiments presented in Deller, et aI., (2009) indicate that the value of the Perron-Frobenius Eigenvalue is a significant measurement of the performance of an Information Age combat force. This was accomplished through the innovative use of an agent-based simulation to model the IACM and represents an initial contribution towards a new generation of combat models that are net-centric instead of using the current platform-centric approach. This paper describes the intent, challenges, design, and initial results of this agent-based simulation model.

Deller, Sean↗

CHEMREASONER: Heuristic Search over a Large Language Model’s Knowledge Space using Quantum-Chemical Feedback

The discovery of new catalysts is essential for the design of new and more efficient chemical processes in order to transition to a sustainable future. We introduce an AI-guided computational screening framework unifying linguistic reasoning with quantum-chemistry based feedback from 3D atomistic representations. Our approach formulates catalyst discovery as an uncertain environment where an agent actively searches for highly effective catalysts via the iterative combination of large language model (LLM)-derived hypotheses and atomistic graph neural network (GNN)-derived feedback. Identified catalysts in intermediate search steps undergo structural evaluation based on spatial orientation, reaction pathways, and stability. Scoring functions based on adsorption energies and barriers steer the exploration in the LLM's knowledge space toward energetically favorable, high-efficiency catalysts. We introduce planning methods that automatically guide the exploration without human input, providing competitive performance against expert-enumerated chemical descriptor-based implementations. By integrating language-guided reasoning with computational chemistry feedback, our work pioneers AI-accelerated, trustworthy catalyst discovery.

artificial intelligence↗

Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We demonstrate that hierarchical agentic large language model reasoning can efficiently drive simulation and scientific exploration. Across two chemical applications, CO adsorption on Cu surface transition metal adatoms and on M–N–C catalysts, reasoning-guided exploration reduces required atomistic simulations by up to 90% relative to heuristic or random selection. Comparisons across single-agent, multi-agent, and stochastic baselines show that hierarchical strategies yield more coherent and information-efficient search trajectories. Reasoning traces reveal chemically grounded decisions that cannot be explained by semantic bias or stochastic sampling. We realize these agentic reasoning strategies in Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), a multimodal system that translates natural language into density functional theory workflows. Altogether, multi-agent collaboration accelerates heterogeneous catalyst discovery and marks a step toward more autonomous, reasoning-guided scientific exploration.

30 DIRECT ENERGY CONVERSION↗

Reinforcement learning for block decomposition of planar CAD models

Abstract The problem of hexahedral mesh generation of general CAD models has vexed researchers for over 3 decades and analysts often spend more than 50% of the design-analysis cycle time decomposing complex models into simpler blocks meshable by existing techniques. The decomposed blocks are required for generating good quality meshes (tilings of quadrilaterals or hexahedra) suitable for numerical simulations of physical systems governed by conservation laws. We present a novel AI-assisted method for decomposing (segmenting) planar CAD (computer-aided design) models into well shaped rectangular blocks. Even though the simple examples presented here can also be meshed using many conventional methods, we believe this work is proof-of-principle of a AI-based decomposition method that can eventually be generalized to complex 2D and 3D CAD models. Our method uses reinforcement learning to train an agent to perform a series of optimal cuts on the CAD model that result in a good quality block decomposition. We show that the agent quickly learns an effective strategy for picking the location and direction of the cuts and maximizing its rewards. This paper is the first successful demonstration of an agent autonomously learning how to perform this block decomposition task effectively, thereby holding the promise of a viable method to automate this challenging process for more complex cases.

97 MATHEMATICS AND COMPUTING↗

Proto-Examples of Data Access and Visualization Components of a Potential Cloud-Based GEOSS-AI System

Once a research or application problem has been identified, one logical next step is to search for available relevant data products. Thus, an early component of a potential GEOSS-AI system, in the continuum between observations and end point research, applications, and decision making, would be one that enables transparent data discovery and access by users. Such a component might be effected via the systems data agents. Presumably, some kind of data cataloging has already been implemented, e.g., in the GEOSS Common Infrastructure (GCI). Both the agents and cataloging could also leverage existing resources external to the system. The system would have some means to accept and integrate user-contributed agents. The need or desirability for some data format internal to the system should be evaluated. Another early component would be one that facilitates browsing visualization of the data, as well as some basic analyses.Three ongoing projects at the NASA Goddard Earth Sciences Data and Information Services Center (GES DISC) provide possible proto-examples of potential data access and visualization components of a cloud-based GEOSS-AI system. 1. Reorganizing data archived as time-step arrays to point-time series (data rods), as well as leveraging the NASA Simple Subset Wizard (SSW), to significantly increase the number of data products available, at multiple NASA data centers, for production as on-the-fly (virtual) data rods. SSWs data discovery is based on OpenSearch. Both pre-generated and virtual data rods are accessible via Web services. 2. Developing Web Feature Services to publish the metadata, and expose the locations, of pre-generated and virtual data rods in the GEOSS Portal and enable direct access of the data via Web services. SSW is also leveraged to increase the availability of both NASA and non-NASA data.3.Federating NASA Giovanni (Geospatial Interactive Online Visualization and Analysis Interface), for multi-sensor data exploration, that would allow each cooperating data center, currently the NASA Distributed Active Archive Centers (DAACs), to configure its own Giovanni deployment, while also allowing all the deployments to incorporate each others data. A federated Giovanni comprises Giovanni Virtual Machines, which can be run on local servers or in the cloud.

access↗

AI-Ready Semantic Infrastructure for CEBAF: From CED to PALS Knowledge Graphs

JLab and PNNL are jointly developing an AI-ready data ecosystem that exposes the Continuous Electron Beam Acceleration Facility’s (CEBAF’s) operational configuration, lattice description, and control-system channels to agentic optimization frameworks through a standards-based semantic layer. The effort integrates the existing facility-specific CEBAF Element Database (CED) with extensions of the emerging facility-agnostic Particle Accelerator Lattice Standard (PALS) to produce a knowledge graph (KG) containing coherent, machine-interpretable views of devices, signals, and regions. With this KG, CEBAF’s setpoints, readbacks, and device hierarchies become queryable using a uniform declarative graph query language (e.g., Neo4j Cypher), providing intents and inspectable semantics suitable for agentic control. The resulting graph-backed interfaces will allow autonomous agents to retrieve authoritative machine configurations, reason over device- and signal-level relationships, and execute tuning and diagnostic workflows without bespoke CEBAF-specific logic, thereby delivering a scalable pathway from operational data to trustworthy agentic accelerator tuning frameworks.

Zhang, He [Thomas Jefferson National Accelerator F↗

Building distributed rule-based systems using the AI Bus

The AI Bus software architecture was designed to support the construction of large-scale, production-quality applications in areas of high technology flux, running heterogeneous distributed environments, utilizing a mix of knowledge-based and conventional components. These goals led to its current development as a layered, object-oriented library for cooperative systems. This paper describes the concepts and design of the AI Bus and its implementation status as a library of reusable and customizable objects, structured by layers from operating system interfaces up to high-level knowledge-based agents. Each agent is a semi-autonomous process with specialized expertise, and consists of a number of knowledge sources (a knowledge base and inference engine). Inter-agent communication mechanisms are based on blackboards and Actors-style acquaintances. As a conservative first implementation, we used C++ on top of Unix, and wrapped an embedded Clips with methods for the knowledge source class. This involved designing standard protocols for communication and functions which use these protocols in rules. Embedding several CLIPS objects within a single process was an unexpected problem because of global variables, whose solution involved constructing and recompiling a C++ version of CLIPS. We are currently working on a more radical approach to incorporating CLIPS, by separating out its pattern matcher, rule and fact representations and other components as true object oriented modules.

Schultz, Roger D.↗

Regulation of Yersina pestis Virulence by AI-2 Mediated Quorum Sensing

The proposed research was motivated by an interest in understanding Y. pestis virulence mechanisms and bacteria cell-cell communication. It is expected that a greater understanding of virulence mechanisms will ultimately lead to biothreat countermeasures and novel therapeutics. Y. pestis is the etiological agent of plague, the most devastating disease in human history. Y. pestis infection has a high mortality rate and a short incubation before mortality. There is no widely available and effective vaccine for Y. pestis and multi-drug resistant strains are emerging. Y. pestis is a recognized biothreat agent based on the wide distribution of the bacteria in research laboratories around the world and on the knowledge that methods exist to produce and aerosolize large amounts of bacteria. We hypothesized that cell-cell communication via signaling molecules, or quorum sensing, by Y. pestis is important for the regulation of virulence factor gene expression during host invasion, though a causative link had never been established. Quorum sensing is a mode of intercellular communication which enables orchestration of gene expression for many bacteria as a function of population density and available evidence suggests there may be a link between quorum sensing and regulation of Y. pesits virulence. Several pathogenic bacteria have been shown to regulate expression of virulence factor genes, including genes encoding type III secretion, via quorum sensing. The Y. pestis genome encodes several cell-cell signaling pathways and the interaction of at least three of these are thought to be involved in one or more modes of host invasion. Furthermore, Y. pestis gene expression array studies carried out at LLNL have established a correlation between expression of known virulence factors and genes involved in processing of the AI-2 quorum sensing signal. This was a basic research project that was intended to provide new insights into bacterial intercellular communication and how it is used to regulate virulence in Y. pestis. It is known that many bacteria use intercellular signaling molecules to orchestrate gene expression and cellular function. A fair amount is known about production and uptake of signaling molecules, but very little is known about how intercellular signaling regulates other pathways. Although several studies demonstrate that intercellular signaling plays a role in regulating virulence in other pathogens, the link between signaling and regulation of virulence has not been established. Very little work had been done directly with Y. pestis intercellular signaling apart from the work carried out at LLNL. The research we proposed was intended to both establish a causative link between AI-2 intercellular signaling and regulation of virulence in Y. pestis and elucidate the fate of the AI-2 signaling molecule after it is taken up and processed by Y. pestis. Elucidating the fate of AI-2 was expected to lead directly to the understanding of how AI-2 signal processing regulates other pathways as well as provide new insights in this direction.

59 BASIC BIOLOGICAL SCIENCES↗

Development and Implementation of a New AI-Based Tool to Support Fast Reactor Software Model Generation and Validation

This report summarizes FY26 work to develop Maggie, an artificial intelligence-based assistant designed to support software model generation and validation activities for fast reactor analysis codes. The project established a modular, code-agnostic software architecture that separates reusable agent capabilities from code-specific knowledge and tools, with initial implementation focused on the FRP-supported fast reactor safety analysis code SAS4A/SASSYS1 (SAS). A curated SAS-specific knowledge base was assembled from the code manual, training materials, historical analysis reports, and representative input files, and was integrated through retrieval-augmented generation to ground Maggie’s responses in authoritative sources. Maggie was deployed on the internal Argonne network, where it demonstrated practical user-facing capability as a chatbot for answering natural language questions about SAS and retrieving relevant technical information. Demonstration cases also showed that Maggie can generate useful snippets of SAS input for selected modeling tasks, while highlighting current limitations in reliability and consistency for more complex input generation tasks. Overall, the FY26 effort established the technical foundation for an AI-assisted capability intended to improve the efficiency, consistency, and accessibility of fast reactor software model development at Argonne and, with further improvements, to support eventual use by the broader fast reactor community, including industry users of FRP-supported analysis tools.

Thomas, Rachel [Argonne National Laboratory (ANL),↗