Search NASA⌕ Search

SEARCH · Search NASA

Results for “agent architectures”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

A roadmap toward scaling, reasoning and self-evolving foundation models for nuclear and particle physics

Foundation models have revolutionized artificial intelligence, with Large Language Models demonstrating unprecedented capabilities in multimodal understanding, reasoning and tool use. Nuclear and particle physics stands at a critical juncture where similar transformative potential awaits realization. The field generates exabytes of experimental data, exascale simulations, and decades of theoretical insights — yet these remain largely disconnected from modern Artifical Intelligence (AI) capabilities, with most physics AI applications confined to narrow, task-specific models that suffer from domain shifting when applied to real experimental data. We present a roadmap for FM4NPP (Foundation Model for Nuclear and Particle Physics), systematically scaling from current proof-of-concept models to trillion-parameter architectures capable of autonomous discovery. Our approach advances three critical frontiers: unified data infrastructure integrating detector data, scientific knowledge and computational tools across global facilities; multi-facility foundation models enabling cross-experiment knowledge transfer and accelerated discovery; and agentic AI capabilities for reasoning and autonomous tool use. The resulting self-evolving FM4NPP will transform physics research by converting time-intensive data analysis, theory derivation and computational bottlenecks into rapid AI–human collaborative discovery. This paradigm shift promises to fundamentally accelerate scientific progress in nuclear and particle physics, enabling researchers to focus on high-level insights while AI handles routine analysis and explores vast parameter spaces beyond human capacity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

DOE Repository Metadata Profile (DRMP): A Metadata Framework for Advancing Interoperability and AI Readiness Across Scientific Repositories

The Department of Energy (DOE) funds a diverse and distributed ecosystem of repositories that steward scientific data, publications, and software across its research programs, user facilities, and national laboratories. While significant progress has been made in standardizing dataset-level metadata, the metadata describing repositories themselves (their identity, governance, access interfaces, policies, and technical capabilities) remains inconsistent and fragmented across DOE-funded systems. This variability limits discoverability, interoperability, automated validation, and AI-driven analysis, all of which are increasingly essential for modern scientific workflows. To address this gap, the DOE Data Curation Working Group (DCWG) developed the DOE Repository Metadata Profile (DRMP). The DRMP is a practical, community-driven framework that defines how repositories can describe themselves in a consistent, machine-actionable, and scalable manner. The DRMP is not a new metadata schema. Instead, it is a mapping profile and structured element set capturing the essential characteristics of DOE repositories. It harmonizes repository-level metadata across six widely adopted community schemas: RE3Data; DCAT-US v3; Schema.org; Dublin Core; DataCite 4.6; and PREMIS 3.0. This harmonization eliminates reinvention and enables interoperability within DOE and across the broader scientific ecosystem. A core objective of the DRMP is to reduce burden on repositories by allowing them to reuse their existing metadata through a Rosetta-style crosswalk rather than redesigning local implementations. The profile introduces a three-level conformance model that supports incremental adoption: • Level 1 – Minimum Viable Record (MVR): foundational identification elements required for workflows, project registration, and basic repository presence. • Level 2 – Interoperable: structured metadata enabling alignment with national and international discovery systems. • Level 3 – AI-Ready: enhanced provenance, policy transparency, fixity, semantic context, and capabilities that support automated reasoning, model training governance, and machine-assisted curation. To support implementation, the DRMP includes JSON Schema definitions, OpenAPI patterns, and MCP templates that allow repositories to publish machine-readable metadata directly within existing platforms. These resources are modular and lightweight, enabling adoption without major architectural change. Adopting the DRMP enables repositories to: • Enhance discoverability and interoperability by aligning identifiers, classifications, and descriptive elements across widely used schema standards. • Support federated discovery and cross-registration across DOE systems, Data.gov, and international catalogs. • Enable AI agents and workflow orchestration systems to interpret repository-level metadata within the American Science Cloud (AmSC) through Model Context Protocol (MCP)-based context publication. • Demonstrate alignment with DOE’s open science, stewardship, and FAIR data priorities. This guidance represents a community-driven step forward. Through voluntary adoption and continued feedback, the DRMP advances a cohesive, machine-actionable description of DOE repositories that supports FAIR data practices, preparing the infrastructure for AI-enabled research, and strengthening the discoverability and reuse of DOE’s scientific outputs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
NASA NTRS2007

A Distributed Trajectory-Oriented Approach to Managing Traffic Complexity

In order to handle the expected increase in air traffic volume, the next generation air transportation system is moving towards a distributed control architecture, in which ground-based service providers such as controllers and traffic managers and air-based users such as pilots share responsibility for aircraft trajectory generation and management. While its architecture becomes more distributed, the goal of the Air Traffic Management (ATM) system remains to achieve objectives such as maintaining safety and efficiency. It is, therefore, critical to design appropriate control elements to ensure that aircraft and groundbased actions result in achieving these objectives without unduly restricting user-preferred trajectories. This paper presents a trajectory-oriented approach containing two such elements. One is a trajectory flexibility preservation function, by which aircraft plan their trajectories to preserve flexibility to accommodate unforeseen events. And the other is a trajectory constraint minimization function by which ground-based agents, in collaboration with air-based agents, impose just-enough restrictions on trajectories to achieve ATM objectives, such as separation assurance and flow management. The underlying hypothesis is that preserving trajectory flexibility of each individual aircraft naturally achieves the aggregate objective of avoiding excessive traffic complexity, and that trajectory flexibility is increased by minimizing constraints without jeopardizing the intended ATM objectives. The paper presents conceptually how the two functions operate in a distributed control architecture that includes self separation. The paper illustrates the concept through hypothetical scenarios involving conflict resolution and flow management. It presents a functional analysis of the interaction and information flow between the functions. It also presents an analytical framework for defining metrics and developing methods to preserve trajectory flexibility and minimize its constraints. In this framework flexibility is defined in terms of robustness and adaptability to disturbances and the impact of constraints is illustrated through analysis of a trajectory solution space with limited degrees of freedom and in simple constraint situations involving meeting multiple times of arrival and resolving a conflict.

Idris, Husni↗
DOE OSTI2025

From clutter to clarity: Emergent neural operators via questionnaire metrics

Real-world datasets in chemical engineering and bioengineering processes—such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials—can often be unlabeled or disorganized, rendering the training of existing supervised learning models ineffective at learning the underlying dynamics. To salvage these datasets for decision-making, we first seek to obtain clarity from the cluttered data. Here, we present a framework for developing “structural” generative models, discovering emergent equations, and constructing efficient emulators from scrambled datasets by integrating unsupervised organizational learning techniques (Questionnaires) with advanced deep learning architectures (Deep Hidden Physics Models and Deep Operator Networks). Our approach is demonstrated on two illustrative model systems: (a) a 1D advection–diffusion partial differential equation representing a winding underground pipe and (b) an ensemble of Stuart–Landau oscillators, an agent-based system of coupled ordinary differential equations. In both cases, we successfully reconstruct meaningful spatial, temporal, and parameter embeddings from scrambled data, enabling good predictions of system dynamics. As a result, we highlight the framework’s potential for broader applications, enabling data-driven system identification in fields with inherently disorganized or hidden parameter spaces.

42 ENGINEERING↗
NASA NTRS2001

Self-assembly of mesoscopically ordered chromatic polydiacetylene/silica nanocomposites

Nature abounds with intricate composite architectures composed of hard and soft materials synergistically intertwined to provide both useful functionality and mechanical integrity. Recent synthetic efforts to mimic such natural designs have focused on nanocomposites, prepared mainly by slow procedures like monomer or polymer infiltration of inorganic nanostructures or sequential deposition. Here we report the self-assembly of conjugated polymer/silica nanocomposite films with hexagonal, cubic or lamellar mesoscopic order using polymerizable amphiphilic diacetylene molecules as both structure-directing agents and monomers. The self-assembly procedure is rapid and incorporates the organic monomers uniformly within a highly ordered, inorganic environment. Polymerization results in polydiacetylene/silica nanocomposites that are optically transparent and mechanically robust. Compared to ordered diacetylene-containing films prepared as Langmuir monolayers or by Langmuir-Blodgett deposition, the nanostructured inorganic host alters the diacetylene polymerization behaviour, and the resulting nanocomposite exhibits unusual chromatic changes in response to thermal, mechanical and chemical stimuli. The inorganic framework serves to protect, stabilize, and orient the polymer, and to mediate its function. The nanocomposite architecture also provides sufficient mechanical integrity to enable integration into devices and microsystems.

NASA Discipline Life Support Systems↗
NASA NTRS2004

Design of Hybrid Mobile Communication Networks for Planetary Exploration

The Mobile Exploration System Project (MEX) at NASA Ames Research Center has been conducting studies into hybrid communication networks for future planetary missions. These networks consist of space-based communication assets connected to ground-based Internets and planetary surface-based mobile wireless networks. These hybrid mobile networks have been deployed in rugged field locations in the American desert and the Canadian arctic for support of science and simulation activities on at least six occasions. This work has been conducted over the past five years resulting in evolving architectural complexity, improved component characteristics and better analysis and test methods. A rich set of data and techniques have resulted from the development and field testing of the communication network during field expeditions such as the Haughton Mars Project and NASA Mobile Agents Project.

Alena, Richard L.↗
DOE OSTI2025

Tunable structure and reinforcement of polyvinyl alcohol (PVA) hydrogels using fungal chitin particles

Polysaccharides, including chitin, are one of the most abundant biopolymers in nature and are increasingly recognized as a sustainable alternative to petroleum-derived plastics and synthetic fillers in polymer composites. Traditionally sourced from crustacean shells, chitin offers mechanical strength and biocompatibility with limitations also in processability and functionality. Fungal-derived chitin material represents a promising alternative, with advantages including scalable fermentation on low-cost substrates, absence of shellfish allergens, and tunable molecular architectures that vary by species, developmental stage, and growth environment. Here, in this study, we systematically examined chitinous materials obtained from taxonomically and functionally distinct fungi, Laccaria bicolor, Trichoderma reesei and Rhizopus oryzae, to assess their structural, chemical, and morphological properties as reinforcement agents in polymer composites. Mild alkaline pretreatment was employed to obtain mycelium chitin particles, thereby improving accessibility to chitin and co-occurring β-D-glucans while maintaining microparticle integrity. Comprehensive FTIR and solid-state NMR analyses revealed species-specific differences in chemical composition and microstructure, with R. oryzae exhibiting a unique spectral signature. These fungal-derived chitin were then incorporated into poly(vinyl alcohol) (PVA) hydrogels, where they acted as reinforcing fillers without the need for additional chemical crosslinkers. Comparative evaluation of hydrogel properties demonstrated that fungal chitin significantly enhanced mechanical performance, with all mycelium fillers mitigating the water weakening in PVA hydrogels. R. oryzae-derived composites tripled the hydrogel tensile strength while the submicron fibrous morphology in L. bicolor contributes to over 45 % tensile improvement in dry PVA composites. Our findings highlight the potential of fungal biomass as a tunable, sustainable platform for producing chitin-based reinforcing agents.

Chitin↗
NASA NTRS2013

The Space Microbe Invasion: To Eat or Not to Eat

Objective: To investigate how different cleaning agents sanitize an assortment of vegetables and fruits for ~nsumption on board the International Space Station (ISS). -Description: This laboratory investigation will have students testing different cleaning agents on a variety of vegetables and fruits that can be grown on board the ISS. Students will determine which cleaning agent most effectively lowers the number of bacteria on a variety of vegetables and fruits. This lab will also lend itself to investigations dealing with pH and its' role in lowering bacterial counts. In addition, students will figure out the correct balance between plant architecture and effectiveness of sanitizing these surfaces to achieve lower bacteria counts. This will be determined based on swabbed bacteria samples later grown on a Petri dish.

Munoz, Angela↗
NASA NTRSDate not supplied

Firmware Architecture of the ARMADAS Bolting Robot

The Automated Reconfigurable Mission Adaptive Digital Assembly Systems (ARMADAS) project, under development at NASA Ames Research Center, has demonstrated on-ground autonomous robotic assembly of extensive digital structures, and it is now moving forward towards in-space demonstration. The ARMADAS system comprises of the operation software, the operation user interface (opsUI), and a swarm of robots. The robotic system consists of a multitude of collaborative agents specifically designed to transport, place and bolt the building blocks, called voxels (volumetric pixels). This paper focuses on the bolting robot, referred to as Mobile Metamaterial Internal Co-Integrator (MMIC-I). MMIC-I is a battery-powered crawling robot. It navigates the structure through extension, contraction and gripping. Two distinct controller boards operate the robot's two symmetric modules, referred to as module A and B. Board A is the master board: it coordinates motion planning and motion primitives execution, hosts the WiFi client, performs periodic self-assessment and system idle check and triggers faults if anomalies are detected. Board B periodically sends a heartbeat to board A, through a wired communication channel that uses the Serial protocol. Additionally, board A's WiFi client receives heartbeat packet requests or motion/bolting commands from a dedicated server board, and acknowledges reception sending back a response heartbeat packet containing information about the overall robot status, e. g. electrical current and voltage values, target and actual angles, operating mode, fault status. Whenever a motion command is sent, the motion planning section of the firmware determines the current robot configuration, using Inertial Measurement Unit readings and the motors Pulse Width Modulation values. Afterwards, it calculates the list of primitives needed to reach the target state, and controls their execution in the proper order. MMIC-I can receive and execute motion and bolting commands only when it is in operational mode. MMIC-I has three operating modes: standby, operational and safed. Standby mode is automatically entered upon startup. While in standby mode, all motors are powered off, and the only accepted commands are the ones relative to a change of mode and heartbeat packet request. Fault detection causes the robot to automatically enter safed or standby mode. Whenever the detected fault occurs within a motion and requires immediate intervention, e. g. an over-current situation, the robot enters safed mode. Safed mode powers off all motors except for the locomotion module, thus preventing the robot from collapsing. Conversely, when the detected fault doesn't require immediate intervention (low battery warning, for instance), the robot enters standby mode after completing the ongoing motion. This paper provides a detailed discussion of MMIC-I's firmware architecture. It accurately describes the implementation approach for each module: sensor data reading, motor control and actuation, WiFi server-client communication, intra-boards Serial communication, operating modes and autonomous fault detection, motion planning, coordination and execution, etc. Moreover, in support of the software description, this paper includes a thorough characterization of MMIC-I's hardware and avionics.

In-space assembly↗
DOE OSTI2026

Adaptive Reinforcement Learning Control for Power Distribution in Multi-Output Resonant Converters

This paper presents an adaptive reinforcement learning (ARL)-based control framework for efficient power distribution in a multi-output resonant converter for UAV applications. The proposed system is based on a high-frequency isolated resonant architecture, where a single energy source supplies multiple propulsion loads through independently controlled output rectifiers, addressing the need for coordinated multi-motor power management. The ARL framework dynamically allocates output power by learning optimal phase-shift control actions under varying load demands and operating conditions. The agent autonomously determines control parameters that maximize conversion efficiency while ensuring accurate power sharing among multiple outputs. In addition, the proposed approach enables adaptive operation without requiring detailed system modeling or manual tuning. Experimental results demonstrate stable and efficient performance over a wide range of operating conditions, confirming the effectiveness and robustness of the learning-based control strategy for multi-output resonant converter system.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗
NASA NTRS2019

Quantum Technologies for UAS (QTech)

Recent advances in small Unmanned Aerial System (sUAS) technologies lower the barriers for use by both private and commercial entities. However, these advances are also likely to lead to greater vehicle densities, a more heterogenous mix of vehicles and equipment and greater levels of vehicle autonomy, which can increase the chance for communications disruptions. For the safe and secure operation of these vehicles, it is essential to have a robust communications network. This work is focused on harnessing the power of quantum technologies to enable this robust communications network by: (1) utilizing quantum optimization algorithms to design robust network with routing redundancy that can respond adaptively to dynamically changing real-time environment and disruptions, (2) utilize quantum optimization algorithms resource allocation for detection, localization, and tracking of mobile communication disruption agents and (3) utilize quantum key distribution (QKD) to execute secure key sharing in anti-jamming protocols for secure radio frequency (RF) communication. Efforts to map these quantum optimization algorithms to commercially available quantum annealers and soon to be available general-purpose gate-model quantum hardware architectures will be reviewed, and plans for testing the solutions to these algorithms through indoor sUAS flight tests will be discussed. Lastly, efforts to miniaturize and practically deploy Quantum Key Distribution (QKD) hardware, which could ultimately be used to securely exchange encryption keys, in sUAS networks will be reviewed.

Quantum Computing↗
NASA NTRS2004

Asteroid Exploration with Autonomic Systems

NASA is studying advanced technologies for a future robotic exploration mission to the asteroid belt. The prospective ANTS (Autonomous Nano Technology Swarm) mission comprises autonomous agents including worker agents (small spacecra3) designed to cooperate in asteroid exploration under the overall authoriq of at least one ruler agent (a larger spacecraft) whose goal is to cause science data to be returned to Earth. The ANTS team (ruler plus workers and messenger agents), but not necessarily any individual on the team, will exhibit behaviors that qualify it as an autonomic system, where an autonomic system is defined as a system that self-reconfigures, self-optimizes, self-heals, and self-protects. Autonomic system concepts lead naturally to realistic, scalable architectures rich in capabilities and behaviors. In-depth consideration of a major mission like ANTS in terms of autonomic systems brings new insights into alternative definitions of autonomic behavior. This paper gives an overview of the ANTS mission and discusses the autonomic properties of the mission.

Truszkowski, Walt↗
NASA NTRS2016

A Cognitive Systems Engineering Approach to Developing HMI Requirements for New Technologies

This document examines the challenges inherent in designing and regulating to support human-automation interaction for new technologies that will deployed into complex systems. A key question for new technologies, is how work will be accomplished by the human and machine agents. This question has traditionally been framed as how functions should be allocated between humans and machines. Such framing misses the coordination and synchronization that is needed for the different human and machine roles in the system to accomplish their goals. Coordination and synchronization demands are driven by the underlying human-automation architecture of the new technology, which are typically not specified explicitly by the designers. The human machine interface (HMI) which is intended to facilitate human-machine interaction and cooperation, however, typically is defined explicitly and therefore serves as a proxy for human-automation cooperation requirements with respect to technical standards for technologies. Unfortunately, mismatches between the HMI and the coordination and synchronization demands of the underlying human-automation architecture, can lead to system breakdowns. A methodology is needed that both designers and regulators can utilize to evaluate the expected performance of a new technology given potential human-automation architectures. Three experiments were conducted to inform the minimum HMI requirements a detect and avoid system for unmanned aircraft systems (UAS). The results of the experiments provided empirical input to specific minimum operational performance standards that UAS manufacturers will have to meet in order to operate UAS in the National Airspace System (NAS). These studies represent a success story for how to objectively and systematically evaluate prototype technologies as part of the process for developing regulatory requirements. They also provide an opportunity to reflect on the lessons learned from a recent research effort in order to improve the methodology for defining technology requirements for regulators in the future. The biggest shortcoming of the presented research program was the absence of the explicit definition, generation and analysis of potential human-automation architectures. Failure to execute this step in the research process resulted in less efficient evaluation of the candidate prototypes technologies in addition to the complete absence of different approaches to human-automation cooperation. For example, all of the prototype technologies that were evaluated in the research program assumed a human-automation architecture that relied on serial processing from the automation to the human. While this type of human-automation architecture is typical across many different technologies and in many different domains, it ignores different architectures where humans and automation work in parallel. Defining potential human-automation architectures a priori also allows regulators to develop scenarios that will stress the performance boundaries of the technology during the evaluation phase. The importance of adding this step of generating and evaluating candidate human-automation architectures prior to formal empirical evaluation is discussed.

human systems integration↗
NASA NTRS1989

A prototype autonomous agent for crew and equipment retrieval in space

The ground-based demonstration of Extra Vehicular Activity (EVA) Retriever, a voice-supervised, intelligent, free-flying robot, is designed to evaluate the capability to retrieve objects (astronauts, equipment, and tools) which have accidentally separated from the Space Station. The EVA Retriever software is required to autonomously plan and execute a target rendezvous, grapple, and return to base while avoiding stationary and moving obstacles. The software architecture incorporates a hierarchical decomposition of the control system that is horizontally partitioned into five major functional subsystems: perception, world model, reasoning, sensing, and acting. The design provides for supervised autonomy as the primary mode of operation with teleoperation as the backup mode. It is intended to be an evolutionary system improving in capability over time and as it earns crew trust through reliable operation.

Erickson, J. D.↗
NASA NTRS1994

Prevent and cure disuse bone loss

Anabolic agents like parathyroid hormone and postagladin E-like substances were studied in dogs and rats to determine their effectiveness in the prevention and cure of bone loss due to immobilization. It was determined that postagladin E2 administration prevented immobilization while at the same time it added extra bone in a dose responsive manner. Although bone mass returns, poor trabecular architecture remains after normal ambulation recovery from immobilization. Disuse related bone loss and poor trabecular architecture were cured by post-immobilization postagladin E2 treatment.

Jee, Webster S. S.↗