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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS2005

Situation Awareness of Onboard System Autonomy

We have developed intelligent agent software for onboard system autonomy. Our approach is to provide control agents that automate crew and vehicle systems, and operations assistants that aid humans in working with these autonomous systems. We use the 3 Tier control architecture to develop the control agent software that automates system reconfiguration and routine fault management. We use the Distributed Collaboration and Interaction (DCI) System to develop the operations assistants that provide human services, including situation summarization, event notification, activity management, and support for manual commanding of autonomous system. In this paper we describe how the operations assistants aid situation awareness of the autonomous control agents. We also describe our evaluation of the DCI System to support control engineers during a ground test at Johnson Space Center (JSC) of the Post Processing System (PPS) for regenerative water recovery.

Schreckenghost, Debra↗
NASA NTRS2004

Agent Technology, Complex Adaptive Systems, and Autonomic Systems: Their Relationships

To reduce the cost of future spaceflight missions and to perform new science, NASA has been investigating autonomous ground and space flight systems. These goals of cost reduction have been further complicated by nanosatellites for future science data-gathering which will have large communications delays and at times be out of contact with ground control for extended periods of time. This paper describes two prototype agent-based systems, the Lights-out Ground Operations System (LOGOS) and the Agent Concept Testbed (ACT), and their autonomic properties that were developed at NASA Goddard Space Flight Center (GSFC) to demonstrate autonomous operations of future space flight missions. The paper discusses the architecture of the two agent-based systems, operational scenarios of both, and the two systems autonomic properties.

Truszkowski, Walt↗
NASA NTRS2006

Adjustably Autonomous Multi-agent Plan Execution with an Internal Spacecraft Free-Flying Robot Prototype

We present an multi-agent model-based autonomy architecture with monitoring, planning, diagnosis, and execution elements. We discuss an internal spacecraft free-flying robot prototype controlled by an implementation of this architecture and a ground test facility used for development. In addition, we discuss a simplified environment control life support system for the spacecraft domain also controlled by an implementation of this architecture. We discuss adjustable autonomy and how it applies to this architecture. We describe an interface that provides the user situation awareness of both autonomous systems and enables the user to dynamically edit the plans prior to and during execution as well as control these agents at various levels of autonomy. This interface also permits the agents to query the user or request the user to perform tasks to help achieve the commanded goals. We conclude by describing a scenario where these two agents and a human interact to cooperatively detect, diagnose and recover from a simulated spacecraft fault.

Dorais, Gregory A.↗
NASA NTRS2004

Validating the autonomous EO-1 science agent

This paper describes the validation process for the Autonomous Science Agent, a software agent that is currently flying onboard NASA EO-1 spacecraft. The agent autonomously collects, analyzes, and reacts to onboard science data. The Autonomous Science Agent has been designed using a layered architectural approach with specific redundant safeguards to reduce the risk of an agent malfunction to the EO-1 spacecraft. This safe design has been thoroughly validated by informal validation methods supplemented by sub-system and system-level testing. This paper describes the analysis used to define agent safety, elements of the design that increase the safety of the agent, and the process used to validate agent safety.

software↗
NASA NTRSDate not supplied

An Ontological Approach to Integrate Commercial Space Operations with an In-time Aviation Safety Management System (IASMS)

The emergence of commercial space operations (CSO) is one of many Advanced Air Mobility domains that pose major challenges to in-time safety assurance because of the different architectures used by the operators and other agents. The National Academies recognized the need to improve integration of disparate architectures and recommended that an In-time Aviation Safety Management System(IASMS) be developed to provide seamless connectivity across interacting architectures and enable in-time safety assurance. An ontological approach to integrating CSO with IASMS involves in-time Services, Functions, and Capabilities design to manage operational risks and inform changes to design. The resulting integrated architecture provides a common basis for risk management and in-time safety assurance.

K Ellis↗
DOE OSTI2026

Agentic Diagrammatica: Towards Autonomous Symbolic Computation in High Energy Physics

We present Diagrammatica, a symbolic computation extension to the HEPTAPOD agentic framework, which enables LLM agents to plan and execute multi-step theoretical calculations. Symbolic computation poses a distinctive reliability challenge for LLM agents, as correctness is governed by implicit mathematical conventions that are not encoded in a form that can be easily checked in the computational backend. We identify two complementary remedies, tool-constrained computation and targeted knowledge grounding, and pursue the first as the primary architecture. Concretely, we concentrate the agent's action distribution onto tool calls with convention-fixing semantics, in which the agent specifies a compact, human-auditable diagram specification and a trusted backend performs the symbolic or numerical manipulations exactly. The toolkit provides two complementary calculation paths consuming a shared diagram specification: Naive Dimensional Analysis (NDA) for order-of-magnitude rate estimates and Exact Diagrammatic Analysis (EDA) for tree-level symbolic calculations via automatic FeynCalc code generation, both supplemented by automatic Feynman diagram enumeration and a navigable theory knowledge base. The architecture is validated on two benchmarks: (1) an exhaustive catalog of all tree-level, single-vertex $1\to 2$ partial decay widths across scalar, fermion, and vector parents, with complete massless and threshold limits and Standard Model validation; and (2) an NDA sensitivity study of the muon decay multiplicity $μ^+ \to ν_μ\barν_e + n(e^+e^-) + e^-$, determining the maximum observable $n$ at current and planned muon experiments.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2025

Surrogate modeling of Cellular-Potts agent-based models as a segmentation task using the U-Net neural network architecture

The Cellular-Potts model is a powerful and ubiquitous framework for developing computational models for simulating complex multicellular biological systems. Cellular-Potts models (CPMs) are often computationally expensive due to the explicit modeling of interactions among large numbers of individual model agents and diffusive fields described by partial differential equations (PDEs). In this work, we develop a convolutional neural network (CNN) surrogate model using a U-Net architecture that accounts for periodic boundary conditions. We use this model to accelerate the evaluation of a mechanistic CPM previously used to investigate in vitro vasculogenesis. The surrogate model was trained to predict 100 computational steps ahead (Monte-Carlo steps, MCS), accelerating simulation evaluations by a factor of 562 times compared to single-core CPM code execution on CPU. Over short timescales of up to 3 recursive evaluations, or 300 MCS, our model captures the emergent behaviors demonstrated by the original Cellular-Potts model such as vessel sprouting, extension and anastomosis, and contraction of vascular lacunae. This approach demonstrates the potential for deep learning to serve as a step toward efficient surrogate models for CPM simulations, enabling faster evaluation of computationally expensive CPM simulations of biological processes.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2003

The Mobile Agents Integrated Field Test: Mars Desert Research Station April 2003

The Mobile Agents model-based, distributed architecture, which integrates diverse components in a system for lunar and planetary surface operations, was extensively tested in a two-week field "technology retreat" at the Mars Society s Desert Research Station (MDRS) during April 2003. More than twenty scientists and engineers from three NASA centers and two universities refined and tested the system through a series of incremental scenarios. Agent software, implemented in runtime Brahms, processed GPS, health data, and voice commands-monitoring, controlling and logging science data throughout simulated EVAs with two geologists. Predefined EVA plans, modified on the fly by voice command, enabled the Mobile Agents system to provide navigation and timing advice. Communications were maintained over five wireless nodes distributed over hills and into canyons for 5 km; data, including photographs and status was transmitted automatically to the desktop at mission control in Houston. This paper describes the system configurations, communication protocols, scenarios, and test results.

Clancey, William J.↗
NASA NTRS2002

The Techsat-21 autonomous space science agent

In this paper we discuss how these AI technologies are synergistically integrated in a hybrid multi-layer control architecture to enable a virtual spacecraft science agent.

autonomy software agents onboard decision-making↗
NASA NTRS2005

Recent Developments in Hardware-in-the-Loop Formation Navigation and Control

The Formation Flying Test-Bed (FFTB) at NASA Goddard Space Flight Center (GSFC) provides a hardware-in-the-loop test environment for formation navigation and control. The facility is evolving as a modular, hybrid, dynamic simulation facility for end-tc-end guidance, navigation, and control (GN&C) design and analysis of formation flying spacecraft. The core capabilities of the FFTB, as a platform for testing critical hardware and software algorithms in-the-loop, are reviewed with a focus on many recent improvements. Two significant upgrades to the FFTB are a message-oriented middleware (MOM) architecture, and a software crosslink for inter-spacecraft ranging. The MOM architecture provides a common messaging bus for software agents, easing integration, arid supporting the GSFC Mission Services Evolution Center (GMSEC) architecture via software bridge. Additionally, the FFTB s hardware capabilities are expanding. Recently, two Low-Power Transceivers (LPTs) with ranging capability have been introduced into the FFTB. The LPT crosslinks will be connected to a modified Crosslink Channel Simulator (CCS), which applies realistic space-environment effects to the Radio Frequency (RF) signals produced by the LPTs.

Mitchell, Jason W.↗
DOE OSTI2026

Wolf

The Workflow Orchestration Language Framework (WOLF) is an agentic framework grounded in natural language with an architecture inspired by reinforcement learning (RL)—designed to orchestrate, scale, and accelerate complex workflows. The concept of WOLF was born out of the very successful ASC Tri-lab Multi-Agent Design Assistant (MADA) project, but extends beyond its domain-specific design agents to provide a more general and extensible architecture. WOLF capitalizes on the lessons learned from MADA and is fully aligned with Sutton’s The Bitter Lesson—that the most enduring progress in AI comes from general-purpose methods that scale with computation, rather than narrow techniques built on domain-specific human knowledge. In this spirit, WOLF enables agents to autonomously learn workflows, capture strategies as reusable playbooks, and build a growing corpus of interpretable, auditable “wisdom artifacts.” These artifacts, expressed in natural language, bridge human and machine understanding while preserving adaptability and scalability as computational power continues to expand.

Boureima, Ismaeal↗
DOE OSTI2025

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2006

Model-Unified Planning and Execution for Distributed Autonomous System Control

The Intelligent Distributed Execution Architecture (IDEA) is a real-time architecture that exploits artificial intelligence planning as the core reasoning engine for interacting autonomous agents. Rather than enforcing separate deliberation and execution layers, IDEA unifies them under a single planning technology. Deliberative and reactive planners reason about and act according to a single representation of the past, present and future domain state. The domain state behaves the rules dictated by a declarative model of the subsystem to be controlled, internal processes of the IDEA controller, and interactions with other agents. We present IDEA concepts - modeling, the IDEA core architecture, the unification of deliberation and reaction under planning - and illustrate its use in a simple example. Finally, we present several real-world applications of IDEA, and compare IDEA to other high-level control approaches.

Aschwanden, Pascal↗
NASA NTRS2019

Impacts of In-Space Assembly as Applied to Human Exploration Architectures

Human missions to Mars present several major challenges that must be overcome, including delivering multiple large mass and volume elements, keeping the crew safe and productive, meeting cost constraints, and ensuring a sustainable campaign. Traditional methods for executing human Mars missions minimize or eliminate in-space assembly (iSA), which provides a narrow range of options for addressing these challenges and limits the types of missions that can be performed. This paper discusses recent work to evaluate how the inclusion of in-space assembly in space mission architectural concepts could provide novel solutions to address these challenges by increasing operational flexibility, robustness, risk reduction, crew health and safety, and sustainability. Several assembly focus areas identified through previous work were developed and evaluated to identify high-potential iSA applications that can have meaningful impacts on the challenges facing Mars missions. Architecture trade options were developed and assessed through sensitivity analyses, resulting in identification of six iSA-based architecture solutions that could be incorporated into Mars mission architectures with moderate levels of assembly. Assembly agent and infrastructure concepts were also developed that would be necessary to enable or facilitate the iSA operations. Several observations developed through the study are presented to inform future human mission architecture and campaign developments.

Jefferies, Sharon A.↗
NASA NTRS2020

Projection-Based Inter-Agent Collision Avoidance in Dual Agent Systems

Inter-agent collisions can occur in otherwise dynamically-stable (i.e., Lyapunov stable) dual-agent leaderfollower systems. These inter-agent collisions between the leader and the follower happen during the transient phase of the system’s evolution, although the steady-state behavior of the system is asymptotically/exponentially stable. Therefore, to avoid such inter-agent collisions, it is essential to control the relative error trajectory between the leader and the follower during the transient phase of the system’s evolution. In this paper, we introduce a novel projection operator based modelreference control architecture that can mitigate impending inter-agent collisions by modifying the transient dynamics of relative trajectories. This controller augments the follower’s baseline controller and consists of two essential components: a collision-free reference model based on the projection operator and a model reference tracking controller to guide the follower to follow the reference-model. This paper defines the concept of transient-instability in leader-follower systems, introduces collision mitigation controller architecture, and presents an illustrative example demonstrating its effectiveness.

Bayard, David S.↗
NASA NTRS2007

Human Activity Behavior and Gesture Generation in Virtual Worlds for Long- Duration Space Missions

A virtual worlds presentation technique with embodied, intelligent agents is being developed as an instructional medium suitable to present in situ training on long term space flight. The system combines a behavioral element based on finite state automata, a behavior based reactive architecture also described as subsumption architecture, and a belief-desire-intention agent structure. These three features are being integrated to describe a Brahms virtual environment model of extravehicular crew activity which could become a basis for procedure training during extended space flight.

Sierhuis, Maarten↗
DOE OSTI2026

Optimization-based approaches to control of connected and automated vehicles: Principles, complexities, applications, challenges, and outlook

Safe and optimal motion control for connected and automated vehicles (CAVs) poses a fundamental optimization challenge at the intersection of system complexity, environmental uncertainty, and stringent real-time constraints. Existing surveys address this challenge in isolation – focusing either on specific control techniques or individual uncertainty sources – without providing a unified framework that characterizes the trade-offs among computational tractability, performance verifiability, and adaptive generalization across paradigms. This review addresses that gap by presenting a cohesive analytical framework concentrated on the decision-making and trajectory optimization layers of the CAV autonomy stack. We systematically analyze three major optimization paradigms – first-principles model-based optimization, data-driven methods, and hybrid synergistic architectures – evaluating each against four core complexity axes: problem formulation, constraint handling, optimality guarantees, and robustness. Key applications including platooning, trajectory planning, collision avoidance, and cooperative control are examined to reveal recurring methodological patterns and critical operational constraints that limit real-world performance. Our synthesis identifies verifiable hybrid architectures, incentive-aligned multi-agent cooperation, and hardware-algorithm co-design as the defining research frontiers, and distills a targeted agenda for developing CAV control systems that are simultaneously safe, computationally efficient, and deployable in the full complexity of real-world traffic environments.

Muzahid, Abu Jafar Md [University of Tennessee, Kn↗
NASA NTRS2002

Autonomous planning and scheduling on the TechSat 21 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.

AI architectures applications intelligent agents m↗