Search NASA⌕ Search

SEARCH · Search NASA

Results for “Agent based modeling”

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
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

Formal Assurance for Cognitive Architecture Based Autonomous Agent

Autonomous systems are designed and deployed in different modeling paradigms. These environments focus on specific concepts in designing the system. We focus our effort in the use of cognitive architectures to design autonomous agents to collaborate with humans to accomplish tasks in a mission. Our research focuses on introducing formal assurance methods to verify the behavior of agents designed in Soar, by translating the agent to the formal verification environment Uppaal.

Bhattacharyya, Siddhartha↗
NASA NTRSDate not supplied

A Framework for Sense and Follow Convoys for Collective Autonomous Mobility

Convoys are collections of vehicles that share similar velocity profiles. In the sense-and follow convoy construct, a vehicle can follow a member of an existing convoy resulting in convoy chaining. We prove conditions under which this can occur such that the resulting convoy chain is bounded and the velocities of all members converge to the leader velocity through locally distributed control algorithms. To assess the approach, we utilize a six degree-of-freedom rigid body vehicle dynamics model for each agent. A dynamic inversion based control law is used to track the desired trajectory generated by the convoy algorithms. To simulate the system, we utilize Unity, a cross-platform game engine, where 3-dimensional terrain, building, and vehicle data can be visualized. Numerous simulations are presented to illustrate the concept.

convoys↗
NASA NTRSDate not supplied

A Framework for Sense and Follow Convoys for Collective Autonomous Mobility

Convoys are collections of vehicles that share similar velocity profiles. In the sense-and follow convoy construct, a vehicle can follow a member of an existing convoy resulting in convoy chaining. We prove conditions under which this can occur such that the resulting convoy chain is bounded and the velocities of all members converge to the leader velocity through locally distributed control algorithms. To assess the approach, we utilize a six degree-of-freedom rigid body vehicle dynamics model for each agent. A dynamic inversion based control law is used to track the desired trajectory generated by the convoy algorithms. To simulate the system, we utilize Unity, a cross-platform game engine, where 3-dimensional terrain, building, and vehicle data can be visualized. Numerous simulations are presented to illustrate the concept. Link to video file below:

convoys↗
NASA NTRS1998

Integration of the Remote Agent for the NASA Deep Space One Autonomy Experiment

This paper describes the integration of the Remote Agent (RA), a spacecraft autonomy system which is scheduled to control the Deep Space 1 spacecraft during a flight experiment in 1999. The RA is a reusable, model-based autonomy system that is quite different from software typically used to control an aerospace system. We describe the integration challenges we faced, how we addressed them, and the lessons learned. We focus on those aspects of integrating the RA that were either easier or more difficult than integrating a more traditional large software application because the RA is a model-based autonomous system. A number of characteristics of the RA made integration process easier. One example is the model-based nature of RA. Since the RA is model-based, most of its behavior is not hard coded into procedural program code. Instead, engineers specify high level models of the spacecraft's components from which the Remote Agent automatically derives correct system-wide behavior on the fly. This high level, modular, and declarative software description allowed some interfaces between RA components and between RA and the flight software to be automatically generated and tested for completeness against the Remote Agent's models. In addition, the Remote Agent's model-based diagnosis system automatically diagnoses when the RA models are not consistent with the behavior of the spacecraft. In flight, this feature is used to diagnose failures in the spacecraft hardware. During integration, it proved valuable in finding problems in the spacecraft simulator or flight software. In addition, when modifications are made to the spacecraft hardware or flight software, the RA models are easily changed because they only capture a description of the spacecraft. one does not have to maintain procedural code that implements the correct behavior for every expected situation. On the other hand, several features of the RA made it more difficult to integrate than typical flight software. For example, the definition of correct behavior is more difficult to specify for a system that is expected to reason about and flexibly react to its environment than for a traditional flight software system. Consequently, whenever a change is made to the RA it is more time consuming to determine if the resulting behavior is correct. We conclude the paper with a discussion of future work on the Remote Agent as well as recommendations to ease integration of similar autonomy projects.

Dorais, Gregory A.↗
DOE OSTI2025

Automatic building energy model development and debugging using large language models agentic workflow

Building energy modeling (BEM) is a complex process that demands significant time and expertise, limiting its broader application in building design and operations. While Large Language Models (LLMs) agentic workflow have facilitated complex engineering processes, their application in BEM has not been specifically explored. This paper investigates the feasibility of automating BEM using LLM agentic workflow. Here, we developed a generic LLM-planning-based workflow that takes a building description as input and generates an error-free EnergyPlus building energy model. Our robust workflow includes four core agents: 1) Building Description Pre-Processing, 2) IDF Object Information Extraction, 3) Single IDF Object Generator Suite, and 4) IDF Debugging Agent. These agents divide the complex tasks into manageable sub-steps, enabling LLMs to generate accurate and reliable results at each stage. The case study demonstrates the successful translation of a building description into an error-free EnergyPlus model for the iUnit modular building at the National Renewable Energy Laboratory. The effectiveness of our workflow surpasses: 1) naive prompt engineering, 2) other LLM-based workflows, and 3) manual modeling, in terms of accuracy, reliability, and time efficiency. The paper concludes with a discussion on the interplay between foundational models and LLM agent planning design, advocating for the use of fine-tuned, specialized models to advance this field.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2013

Aviation Safety: Modeling and Analyzing Complex Interactions between Humans and Automated Systems

The on-going transformation from the current US Air Traffic System (ATS) to the Next Generation Air Traffic System (NextGen) will force the introduction of new automated systems and most likely will cause automation to migrate from ground to air. This will yield new function allocations between humans and automation and therefore change the roles and responsibilities in the ATS. Yet, safety in NextGen is required to be at least as good as in the current system. We therefore need techniques to evaluate the safety of the interactions between humans and automation. We think that current human factor studies and simulation-based techniques will fall short in front of the ATS complexity, and that we need to add more automated techniques to simulations, such as model checking, which offers exhaustive coverage of the non-deterministic behaviors in nominal and off-nominal scenarios. In this work, we present a verification approach based both on simulations and on model checking for evaluating the roles and responsibilities of humans and automation. Models are created using Brahms (a multi-agent framework) and we show that the traditional Brahms simulations can be integrated with automated exploration techniques based on model checking, thus offering a complete exploration of the behavioral space of the scenario. Our formal analysis supports the notion of beliefs and probabilities to reason about human behavior. We demonstrate the technique with the Ueberligen accident since it exemplifies authority problems when receiving conflicting advices from human and automated systems.

Muti-agent System↗
DOE OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗
NASA NTRS1990

Dual redundant arm system operational quality measures and their applications - Dynamic measures

Dual-arm dynamic operation quality measures are presented which quantify the efficiency and capability of generating Cartesian accelerations by two cooperative arms based on the analysis of dual-arm dynamic interactions. Dual-arm dynamic manipulability is defined as the efficiency of generating Cartesian accelerations under the dynamic and kinematic interactions between individual arms and an object under manipulation. The analysis of dual-arm dynamic interactions is based on the so-called Cartesian space agent model of an arm, which represents an individual arm as a force source acting upon a point mass with the effective Cartesian space arm dynamics and an environment or an object under manipulation. The Cartesian space agent model of an arm makes it possible to derive the dynamic and kinematic constraints involved in the transport, assembly and grasping modes of dual-arm cooperation. A task-oriented operational quality measure, (TOQd) is defined by evaluating dual-arm dynamic manipulability in terms of given task requirements. TOQd is used in dual-arm joint configuration optimization. Simulation results are shown. A complete set of forward dynamic equations for a dual-arm system is derived, and dual-arm dynamic operational quality measures for various modes of dual-arm cooperation allowing sliding contacts are established.

Lee, Sukhan↗
NASA NTRS2002

CATS-based Air Traffic Controller Agents

This report describes intelligent agents that function as air traffic controllers. Each agent controls traffic in a single sector in real time; agents controlling traffic in adjoining sectors can coordinate to manage an arrival flow across a given meter fix. The purpose of this research is threefold. First, it seeks to study the design of agents for controlling complex systems. In particular, it investigates agent planning and reactive control functionality in a dynamic environment in which a variety perceptual and decision making skills play a central role. It examines how heuristic rules can be applied to model planning and decision making skills, rather than attempting to apply optimization methods. Thus, the research attempts to develop intelligent agents that provide an approximation of human air traffic controller behavior that, while not based on an explicit cognitive model, does produce task performance consistent with the way human air traffic controllers operate. Second, this research sought to extend previous research on using the Crew Activity Tracking System (CATS) as the basis for intelligent agents. The agents use a high-level model of air traffic controller activities to structure the control task. To execute an activity in the CATS model, according to the current task context, the agents reference a 'skill library' and 'control rules' that in turn execute the pattern recognition, planning, and decision-making required to perform the activity. Applying the skills enables the agents to modify their representation of the current control situation (i.e., the 'flick' or 'picture'). The updated representation supports the next activity in a cycle of action that, taken as a whole, simulates air traffic controller behavior. A third, practical motivation for this research is to use intelligent agents to support evaluation of new air traffic control (ATC) methods to support new Air Traffic Management (ATM) concepts. Current approaches that use large, human-in-the-loop simulations are unquestionably valuable for this purpose, but pose considerable logistical, fiscal, and experimental control problems. First, data analysis is extremely complicated, owing simply to the large number of participants and data sources in such simulations. In addition, experienced human air traffic controllers working adjacent sectors tend to flexibly adapt to the evolving control problem - potentially shifting to other strategies than those under investigation. In addition, their performance is tightly coupled to the control interface, which in the development phase may support some concepts and supporting strategies better than others. A simple shift in strategy by one controller can change the character of a particular traffic scenario dramatically, which makes experimental comparison of ATC performance under different traffic scenarios difficult. Training a given team of controllers on operations under a new ATM concept for a sufficient period of time could avert such difficulties, but instituting an adequate training program is expensive and logistically difficult.

Callantine, Todd J.↗
NASA NTRS2005

Studies of Particle Acceleration, Transport and Radiation in Impulsive Phase of Solar Flares

Solar activity and its most prominent aspect, the solar flares, have considerable influence on terrestrial and space weather. Solar flares also provide a suitable laboratory for the investigation of many plasma and high energy processes important in the magnetosphere of the Earth and many other space and astrophysical situations. Hence, progress in understanding of flares will have considerable scientific and societal impact. The primary goal of this grant is the understanding of two of the most important problems of solar flare physics, namely the determination of the energy release mechanism and how this energy accelerates particles. This is done through comparison of the observations with theoretical models, starting from observations and gradually proceeding to theoretically more complex situations as the lower foundations of our understanding are secured. It is generally agreed that the source of the flare energy is the annihilation of magnetic fields by the reconnection process. Exactly how this energy is released or how it is dissipated remains controversial. Moreover, the exact mechanism of the acceleration of the particles is still a matter of debate. Data from many spacecrafts and ground based instruments obtained over the past decades have given us some clues. Theoretical analyses of these data have led to the standard thick target model (STT) where most of the released energy goes into an (assumed) power law spectrum of accelerated particles, and where all the observed radiations are the consequence of the interaction of these particles with the flare plasma. However, some theoretical arguments, and more importantly some new observations, have led us to believe that the above picture is not complete. It appears that plasma turbulence plays a more prominent role than suspected previously, and that it is the most likely agent for accelerating particles. The model we have developed is based on production of a high level of plasma waves and turbulence in the reconnection region above a flare loop. This turbulence accelerates particles stochastically which radiate some of their energy in this region but carry most of their energy to the footpoints of the loop, where they lose all their energy and radiate bulk of the observed radiation as in the traditional thick target model. In the past we have worked on various aspects of this model. We have evaluated the interaction rates of the plasma waves with electrons and ions, developed theoretical frameworks for the acceleration, transport and radiative processes, and produced numerical codes for the investigation of these processes. The goal of this grant has been further development and testing of this new paradigm, with emphases on the relative acceleration of electrons and ions and on a comprehensive investigation of the turbulence generation, cascade, and damping processes. We review several pieces of important evidence that we have uncovered indicating the crucial roles of turbulence, in and we describe accomplishments during the past two years of this grant.

Petrosian, Vahe↗
DOE OSTI2024

Graph-Based Modeling for the Detection and Tracking of Sarin-Surrogate-Induced Neurotoxicity Using a Human-Relevant, In-Vitro Brain Model

Organophosphorus (OP) nerve agents are a chemical threat to the United States, to the civilian population (e.g., pesticides) and historically weaponized (e.g., sarin) as chemical warfare agents. The unprecedented, accelerated process from “bench-to-bedside” during the SARSCov2 pandemic has made it clear that technology and tools need to be readily available for immediate response. Advances in human organ tissue mimetic systems are a promising technology to evaluate the human-relevant response in vitro for basic and applied research and drug screening. In particular, current brain microphysiological systems (MPS) have the capability to monitor and detect changes in engineered human neural circuit activity. However, current data analytics approaches for these systems lack the granularity to functionally detect and distinguish the different mechanisms that occur in the brain following neurotoxicity, injury, and disease. The goal of this project was to advance the computational analytical capabilities of the brain MPS to detect functional changes in neural circuit structure at different stages of Sarin surrogate-induced neurotoxicity. We developed graph-based models to (1) identify the composition of the neural circuit structure; (2) detect and monitor how this structure changes following sarin-induced neurotoxicity; and (3) evaluate the analytical pipeline using known/promising oxime reactivators. Through experiments on the bMPS where in vitro neuronal cultures were exposed to a sarin surrogate, we demonstrated the capabilities of our computational pipeline to identify different responses in the functional networks of brain cells exposed to low and high concentrations of the nerve agent. We identified a biphasic response of human neural network activity following exposure to a sarin-surrogate that had not been reported in the literature before. The graph-based models and software developed in this project can be used for future studies that leverage the brain MPS technology, such as treatment efficacy assessment.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2003

Mobile Agents: A Distributed Voice-Commanded Sensory and Robotic System for Surface EVA Assistance

A model-based, distributed architecture integrates diverse components in a system designed for lunar and planetary surface operations: spacesuit biosensors, cameras, GPS, and a robotic assistant. The system transmits data and assists communication between the extra-vehicular activity (EVA) astronauts, the crew in a local habitat, and a remote mission support team. Software processes ("agents"), implemented in a system called Brahms, run on multiple, mobile platforms, including the spacesuit backpacks, all-terrain vehicles, and robot. These "mobile agents" interpret and transform available data to help people and robotic systems coordinate their actions to make operations more safe and efficient. Different types of agents relate platforms to each other ("proxy agents"), devices to software ("comm agents"), and people to the system ("personal agents"). A state-of-the-art spoken dialogue interface enables people to communicate with their personal agents, supporting a speech-driven navigation and scheduling tool, field observation record, and rover command system. An important aspect of the engineering methodology involves first simulating the entire hardware and software system in Brahms, and then configuring the agents into a runtime system. Design of mobile agent functionality has been based on ethnographic observation of scientists working in Mars analog settings in the High Canadian Arctic on Devon Island and the southeast Utah desert. The Mobile Agents system is developed iteratively in the context of use, with people doing authentic work. This paper provides a brief introduction to the architecture and emphasizes the method of empirical requirements analysis, through which observation, modeling, design, and testing are integrated in simulated EVA operations.

Clancey, William J.↗
NASA NTRS2004

Formalism Challenges of the Cougaar Model Driven Architecture

The Cognitive Agent Architecture (Cougaar) is one of the most sophisticated distributed agent architectures developed today. As part of its research and evolution, Cougaar is being studied for application to large, logistics-based applications for the Department of Defense (DoD). Anticipiting future complex applications of Cougaar, we are investigating the Model Driven Architecture (MDA) approach to understand how effective it would be for increasing productivity in Cougar-based development efforts. Recognizing the sophistication of the Cougaar development environment and the limitations of transformation technologies for agents, we have systematically developed an approach that combines component assembly in the large and transformation in the small. This paper describes some of the key elements that went into the Cougaar Model Driven Architecture approach and the characteristics that drove the approach.

Bohner, Shawn A.↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
DOE OSTI2025

Multi-scale, Multi-disciplinary, and Multi-agent Explainable AI with Koopman-Undergirded Learning, Prediction, and Analysis (M3EA KULPA) (Project Closeout Report)

The goal of this project was to develop and use domain-aware machine learning formulations, based on the Koopman Operator (KO), for modelling multi-scale, multi-disciplinary (e.g., multi-physics), and/or multi-agent systems. The project developed these formulations for the following cases: • Systems with dynamics at two separate time scales, • Systems with a bi-level hierarchical control structure, • Systems with bi-level hierarchical control and dynamics at two separate time scales (the lower level controls operating at the faster time scale), and • Systems with n separate but interacting agents/disciplines (with/without control, respectively); the controls for each agent could include bi-level hierarchical control and dynamics at two separate time scales as described above. The project then defined a set of dynamical systems consisting of different nonlinear oscillators that could be used to test these different formulations and then subsequently learned the KO models for those systems. With the KO models, we were able to do the following: • Quantify system stability, including both long-term and transient behavior, • Quantify the effects of feedbacks between the different time scales and agents/disciplines in terms of those feedbacks’ effects on system stability, • Replace a standard Proportional-Integral (PI) control in the hierarchical control structure with a KO-based Linear-Quadratic Regular (LQR), a form of optimal control, • Calculate optimal supervisory control policies a) with and without time scale separated dynamics at the lower level control levels and b) with both PI and KO-based LQR lower level control policies, and • Calculate dynamic Nash equilibria for multi-agent systems where each agent makes its own control decisions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers

Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainability. We present LC-Opt, a Sustainable Liquid Cooling (LC) benchmark environment, for reinforcement learning (RL) control strategies in energy-efficient liquid cooling of high-performance computing (HPC) systems. Built on the baseline of a high-fidelity digital twin of Oak Ridge National Lab's Frontier Supercomputer cooling system, LC-Opt provides detailed Modelica-based end-to-end models spanning site-level cooling towers to data center cabinets and server blade groups. RL agents optimize critical thermal controls like liquid supply temperature, flow rate, and granular valve actuation at the IT cabinet level, as well as cooling tower (CT) setpoints through a Gymnasium interface, with dynamic changes in workloads. This environment creates a multi-objective real-time optimization challenge balancing local thermal regulation and global energy efficiency, and also supports additional components like a heat recovery unit (HRU). We benchmark centralized and decentralized multi-agent RL approaches, demonstrate policy distillation into decision and regression trees for interpretable control, and explore LLM-based methods that explain control actions in natural language through an agentic mesh architecture designed to foster user trust and simplify system management. LC-Opt democratizes access to detailed, customizable liquid cooling models, enabling the ML community, operators, and vendors to develop sustainable data center liquid cooling control solutions.

Naug, Avisek [Hewlett Packard Enterprise]↗
NASA NTRSDate not supplied

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning↗