Search NASA⌕ Search

SEARCH · Search NASA

Results for “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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

Abstract-Reasoning Software for Coordinating Multiple Agents

A computer program for scheduling the activities of multiple agents that share limited resources has been incorporated into the Automated Scheduling and Planning Environment (ASPEN) software system, aspects of which have been reported in several previous NASA Tech Briefs articles. In the original intended application, the agents would be multiple spacecraft and/or robotic vehicles engaged in scientific exploration of distant planets. The program could also be used on Earth in such diverse settings as production lines and military maneuvers. This program includes a planning/scheduling subprogram of the iterative repair type that reasons about the activities of multiple agents at abstract levels in order to greatly improve the scheduling of their use of shared resources. The program summarizes the information about the constraints on, and resource requirements of, abstract activities on the basis of the constraints and requirements that pertain to their potential refinements (decomposition into less-abstract and ultimately to primitive activities). The advantage of reasoning about summary information is that time needed to find consistent schedules is exponentially smaller than the time that would be needed for reasoning about the same tasks at the primitive level.

Clement, Bradley↗
NASA NTRS2012

An Agent-Based Model of New Venture Creation: Conceptual Design for Simulating Entrepreneurship

There is a growing debate over the means by which regions can foster the growth of entrepreneurial activity in order to stimulate recovery and growth of their economies. On one side, agglomeration theory suggests the regions grow because of strong clusters that foster knowledge spillover locally; on the other side, the entrepreneurial action camp argues that innovative business models are generated by entrepreneurs with unique market perspectives who draw on knowledge from more distant domains. We will show you the design for a novel agent-based model of new venture creation that will demonstrate the relationship between agglomeration and action. The primary focus of this model is information exchange as the medium for these agent interactions. Our modeling and simulation study proposes to reveal interesting relationships in these perspectives, offer a foundation on which these disparate theories from economics and sociology can find common ground, and expand the use of agent-based modeling into entrepreneurship research.

Provance, Mike↗
NASA NTRS2013

Autonomous Formations of Multi-Agent Systems

Autonomous formation control of multi-agent dynamic systems has a number of applications that include ground-based and aerial robots and satellite formations. For air vehicles, formation flight ("flocking") has the potential to significantly increase airspace utilization as well as fuel efficiency. This presentation addresses two main problems in multi-agent formations: optimal role assignment to minimize the total cost (e.g., combined distance traveled by all agents); and maintaining formation geometry during flock motion. The Kuhn-Munkres ("Hungarian") algorithm is used for optimal assignment, and consensus-based leader-follower type control architecture is used to maintain formation shape despite the leader s independent movements. The methods are demonstrated by animated simulations.

Dhali, Sanjana↗
NASA NTRS2014

Evolutionary Agent-Based Simulation of the Introduction of New Technologies in Air Traffic Management

Accurate simulation of the effects of integrating new technologies into a complex system is critical to the modernization of our antiquated air traffic system, where there exist many layers of interacting procedures, controls, and automation all designed to cooperate with human operators. Additions of even simple new technologies may result in unexpected emergent behavior due to complex human/ machine interactions. One approach is to create high-fidelity human models coming from the field of human factors that can simulate a rich set of behaviors. However, such models are difficult to produce, especially to show unexpected emergent behavior coming from many human operators interacting simultaneously within a complex system. Instead of engineering complex human models, we directly model the emergent behavior by evolving goal directed agents, representing human users. Using evolution we can predict how the agent representing the human user reacts given his/her goals. In this paradigm, each autonomous agent in a system pursues individual goals, and the behavior of the system emerges from the interactions, foreseen or unforeseen, between the agents/actors. We show that this method reflects the integration of new technologies in a historical case, and apply the same methodology for a possible future technology.

Simulation↗
NASA NTRS2014

Agent Based Modeling of Air Carrier Behavior for Evaluation of Technology Equipage and Adoption

As part of ongoing research, the National Aeronautics and Space Administration (NASA) and LMI developed a research framework to assist policymakers in identifying impacts on the U.S. air transportation system (ATS) of potential policies and technology related to the implementation of the Next Generation Air Transportation System (NextGen). This framework, called the Air Transportation System Evolutionary Simulation (ATS-EVOS), integrates multiple models into a single process flow to best simulate responses by U.S. commercial airlines and other ATS stakeholders to NextGen-related policies, and in turn, how those responses impact the ATS. Development of this framework required NASA and LMI to create an agent-based model of airline and passenger behavior. This Airline Evolutionary Simulation (AIRLINE-EVOS) models airline decisions about tactical airfare and schedule adjustments, and strategic decisions related to fleet assignments, market prices, and equipage. AIRLINE-EVOS models its own heterogeneous population of passenger agents that interact with airlines; this interaction allows the model to simulate the cycle of action-reaction as airlines compete with each other and engage passengers. We validated a baseline configuration of AIRLINE-EVOS against Airline Origin and Destination Survey (DB1B) data and subject matter expert opinion, and we verified the ATS-EVOS framework and agent behavior logic through scenario-based experiments. These experiments demonstrated AIRLINE-EVOS's capabilities in responding to an input price shock in fuel prices, and to equipage challenges in a series of analyses based on potential incentive policies for best equipped best served, optimal-wind routing, and traffic management initiative exemption concepts..

Horio, Brant M.↗
NASA NTRS2015

Collaborating with Autonomous Agents

With the anticipated increase of small unmanned aircraft systems (sUAS) entering into the National Airspace System, it is highly likely that vehicle operators will be teaming with fleets of small autonomous vehicles. The small vehicles may consist of sUAS, which are 55 pounds or less that typically will y at altitudes 400 feet and below, and small ground vehicles typically operating in buildings or defined small campuses. Typically, the vehicle operators are not concerned with manual control of the vehicle; instead they are concerned with the overall mission. In order for this vision of high-level mission operators working with fleets of vehicles to come to fruition, many human factors related challenges must be investigated and solved. First, the interface between the human operator and the autonomous agent must be at a level that the operator needs and the agents can understand. This paper details the natural language human factors e orts that NASA Langley's Autonomy Incubator is focusing on. In particular these e orts focus on allowing the operator to interact with the system using speech and gestures rather than a mouse and keyboard. With this ability of the system to understand both speech and gestures, operators not familiar with the vehicle dynamics will be able to easily plan, initiate, and change missions using a language familiar to them rather than having to learn and converse in the vehicle's language. This will foster better teaming between the operator and the autonomous agent which will help lower workload, increase situation awareness, and improve performance of the system as a whole.

Trujillo, Anna C.↗
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 NTRS2018

Multistage Delivery of Active Agents

Multistage delivery vehicles are disclosed which include a first stage particle and a second stage particle. The first stage particle is a micro or nanoparticle that contains the second stage particle. The second stage particle includes an active agent, such as a therapeutic agent or an imaging agent. The multistage delivery vehicle allows sequential overcoming or bypassing of biological barriers. The multistage delivery vehicle is administered as a part of a composition that includes a plurality of the vehicles. Methods of making the multistage delivery vehicles are also provided.

Ferrari, Mauro↗
NASA NTRS2018

The Mid-IR Spectral Effects of Darkening Agents and Porosity on the Silicate Surface Features of Airless Bodies

We systematically measured the mid-IR spectra of different mixtures of three silicates (antigorite, lizardite, and pure silica) with varying effective porosities and amounts of darkening agent (iron oxide and carbon). These spectra have broad implications for interpretation of current and future mission data for airless bodies, as well as for testing the capabilities of new instruments. Serpentines, such as antigorite and lizardite, are common to airless surfaces, and their mid-IR spectra in the presence of darkening agents and different surface porosities would be typical for those measured by spacecraft. Silica has only been measured in the plumes of Enceladus and presents exciting possibilities for other Saturn-system surfaces due to long range transport of E-ring material. Results show that the addition of the IR-transparent salt, KBr, to simulate surface porosity affected silicate spectra in ways that were not predictable from linear mixing models. The strengthening of silicate bands with increasing pore space, even when only trace amounts of KBr were added, indicates that spectral features of porous surfaces are more detectable in the mid-IR. Combining iron oxide with the pure silicates seemed to flatten most of the silicate features, but strengthened the reststrahlen band of the silica. Incorporating carbon with the silicates weakened all silicate features, but the silica bands were more resistant to being diminished, indicating silica may be more detectable in the mid-IR than the serpentines. We show how incorporating darkening agents and porosity provides a more complete explanation of the mid-IR spectral features previously reported on worlds such as Iapetus.

Young, Cindy L.↗
NASA NTRS2020

Multi-Agent Motion Planning using Deep Learning for Space Applications

State-of-the-art motion planners cannot scale to a large number of systems. Motion planning for multiple agents is an NP (non-deterministic polynomial-time) hard problem, so the computation time increases exponentially with each addition of agents. This computational demand is a major stumbling block to the motion planner's application to future NASA missions involving the swarm of space vehicles. We applied a deep neural network to transform computationally demanding mathematical motion planning problems into deep learning-based numerical problems. We showed optimal motion trajectories can be accurately replicated using deep learning-based numerical models in several 2D and 3D systems with multiple agents. The deep learning-based numerical model demonstrates superior computational efficiency with plans generated 1000 times faster than the mathematical model counterpart.

Madani, Ramtin↗
NASA NTRSDate not supplied

Intelligent Change Detection System: Autonomous Intelligent Machine Agent Model Development

NASA’s significant role in facilitating the harmonious integration of unmanned aircraft systems (UAS), with other aerial vehicles operating in the National Airspace System (NAS), has revealed a need for more advanced technological tools than are being utilized currently. This technology would lend itself to significantly assisting Direct-Action Aviation Personnel (DAAP) with the ingress and egress of UAS operations within the NAS. Providing research findings that would reduce technical barriers, associated with UAS-NAS integration, has been a persistent effort by both NASA and the FAA. One such research effort, pursued by NASA’s Transformative Tools and Technologies – Revolutionary Aviation Mobility (T3-RAM) project, is the development of an autonomous intelligent machine (AIM) agent that would aid DAAP functioning as implemented in remote ground control stations (RGCS). This evolution of the “human-machine” symbiosis, within the aviation environment, is necessary for many reasons. For example, there are projections of large increases to the 864,000 registered UAS and 45,000 aviation operations taking place in the NAS each day. With a data output range from 1 to 20 terabytes per flight or each aerial vehicle, which is projected to have proportional rate increase to that of registered UASs. It is evident, that due to the projected increase of UASs and their generated data, the human-agent’s data managing capabilities will be quickly overwhelmed by the enormous amounts of data emanating in the NAS. The research efforts presented in this paper puts forward results from the development, assessment, and verification of a previously conceptualized AIM-Agent that combats actionable-data (information) errors resulting from the visual perception phenomenon known as “change blindness” (CB). CB has been identified as one of the main culprits of information erroring encountered within the ground control station operator (GCSO) community.

Change Blindness↗
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]↗
DOE OSTI2026

Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential information leakage associated with machine learning systems. Designing effective MIAs is a challenging task that usually requires extensive manual exploration of model behaviors to identify potential vulnerabilities. In this paper, we introduce AutoMIA -- a novel framework that leverages large language model (LLM) agents to automate the design and implementation of new MIA signal computations. By utilizing LLM agents, we can systematically explore a vast space of potential attack strategies, enabling the discovery of novel strategies. Our experiments demonstrate AutoMIA can successfully discover new MIAs that are specifically tailored to user-configured target model and dataset, resulting in improvements of up to 0.18 in absolute AUC over existing MIAs. This work provides the first demonstration that LLM agents can serve as an effective and scalable paradigm for designing and implementing MIAs with SOTA performance, opening up new avenues for future exploration.

Tran, Toan Viet [Emory University]↗
DOE OSTI2025

Bayesian Calibration of Stochastic Agent Based Model via Random Forest

Agent-based models (ABM) provide an excellent framework for modeling outbreaks and interventions in epidemiology by explicitly accounting for diverse individual interactions and environments. However, these models are usually stochastic and highly parametrized, requiring precise calibration for predictive performance. When considering realistic numbers of agents and properly accounting for stochasticity, this high-dimensional calibration can be computationally prohibitive. This paper presents a random forest-based surrogate modeling technique to accelerate the evaluation of ABMs and demonstrates its use to calibrate an epidemiological ABM named CityCOVID via Markov chain Monte Carlo (MCMC). The technique is first outlined in the context of CityCOVID's quantities of interest, namely hospitalizations and deaths, by exploring dimensionality reduction via temporal decomposition with principal component analysis (PCA) and via sensitivity analysis. The calibration problem is then presented, and samples are generated to best match COVID-19 hospitalization and death numbers in Chicago from March to June in 2020. Further, these results are compared with previous approximate Bayesian calibration (IMABC) results, and their predictive performance is analyzed, showing improved performance with a reduction in computation.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Towards philosophical reasoning with agentic LLMs: Socratic method for scientific assistance

As large language models (LLMs) become central tools in science, improving their reasoning capabilities is critical for meaningful and trustworthy applications. We introduce a Socratic agent for scientific reasoning, implemented through a structured system prompt that guides LLMs via classical principles of inquiry. Unlike typical prompt engineering or retrieval-based methods, our approach leverages definition, analogy, hypothesis elimination, and other Socratic techniques to generate more coherent, critical, and domain-aware responses. We evaluate the agent across diverse scientific domains and benchmark it on the abstraction and reasoning corpus challenge dataset, achieving 97.15% under a fixed prompting protocol and without fine-tuning or external tools. Expert evaluation shows improved reasoning depth, clarity, and adaptability over conventional LLM outputs, suggesting that structured prompting rooted in philosophical reasoning can improve the scientific utility of language models.

LLM reasoning↗
DOE OSTI2024

Biphasic response of human iPSC-derived neural network activity following exposure to a sarin-surrogate nerve agent

Organophosphorus nerve agents (OPNA) are hazardous environmental exposures to the civilian population and have been historically weaponized as chemical warfare agents (CWA). OPNA exposure can lead to several neurological, sensory, and motor symptoms that can manifest into chronic neurological illnesses later in life. There is still a large need for technological advancement to better understand changes in brain function following OPNA exposure. The human-relevant in vitro multi-electrode array (MEA) system, which combines the MEA technology with human stem cell technology, has the potential to monitor the acute, sub-chronic, and chronic consequences of OPNA exposure on brain activity. However, the application of this system to assess OPNA hazards and risks to human brain function remains to be investigated. In a concentration-response study, we have employed a human-relevant MEA system to monitor and detect changes in the electrical activity of engineered neural networks to increasing concentrations of the sarin surrogate 4-nitrophenyl isopropyl methylphosphonate (NIMP). We report a biphasic response in the spiking (but not bursting) activity of neurons exposed to low (i.e., 0.4 and 4 μM) versus high concentrations (i.e., 40 and 100 μM) of NIMP, which was monitored during the exposure period and up to 6 days post-exposure. Regardless of the NIMP concentration, at a network level, communication or coordination of neuronal activity decreased as early as 60 min and persisted at 24 h of NIMP exposure. Once NIMP was removed, coordinated activity was no different than control (0 μM of NIMP). Interestingly, only in the high concentration of NIMP did coordination of activity at a network level begin to decrease again at 2 days post-exposure and persisted on day 6 post-exposure. Notably, cell viability was not affected during or after NIMP exposure. Also, while the catalytic activity of AChE decreased during NIMP exposure, its activity recovered once NIMP was removed. Gene expression analysis suggests that human iPSC-derived neurons and primary human astrocytes resulted in altered genes related to the cell’s interaction with the extracellular environment, its intracellular calcium signaling pathways, and inflammation, which could have contributed to how neurons communicated at a network level.

59 BASIC BIOLOGICAL SCIENCES↗