SEARCH · Engineering Papers

Results for “agent based model”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 451 records · Page 25

All sources NASA NTRS DOE OSTI

DOE OSTI2026

A transfer learning approach to energy-efficient control of small and medium-sized commercial buildings

Model-free reinforcement learning (RL) provides a data-driven and adaptive approach to optimize building energy use while satisfying occupant comfort. This powerful tool does not need any prior knowledge about the environment and system it is optimizing and can adapt its policy based on the changes in captures. Like any other data-driven tool, it faces high training costs due to the extensive agent-environment interactions required to capture long-term building dynamics and user comfort. Transfer learning, particularly policy distillation, offers a promising way to accelerate training by leveraging pretrained RL agents in different building and system types. Here, this study investigates online student distillation, in which the student model updates its neural network weights using outputs from teacher models. The work introduces a student distillation strategy designed for efficient knowledge transfer, along with a teacher selection method that ensures high-quality guidance. The approach is validated using a highly calibrated whole building energy model for a small/medium commercial building test facility. Results show substantial reductions in training time and data requirements while surpassing the performance of ASHRAE Guideline 36, an advanced rule-based control strategy. The distilled RL model required 45% less data and achieved 20% higher cumulative rewards than a state-of-the-art RL model, with faster convergence and lower energy consumption. These outcomes demonstrate that effective transfer learning enables a scalable and data-efficient energy management solution for commercial buildings.

ASHRAE guideline 36↗

NASA NTRS1996

An Open Computing Infrastructure that Facilitates Integrated Product and Process Development from a Decision-Based Perspective

Computer applications for design have evolved rapidly over the past several decades, and significant payoffs are being achieved by organizations through reductions in design cycle times. These applications are overwhelmed by the requirements imposed during complex, open engineering systems design. Organizations are faced with a number of different methodologies, numerous legacy disciplinary tools, and a very large amount of data. Yet they are also faced with few interdisciplinary tools for design collaboration or methods for achieving the revolutionary product designs required to maintain a competitive advantage in the future. These organizations are looking for a software infrastructure that integrates current corporate design practices with newer simulation and solution techniques. Such an infrastructure must be robust to changes in both corporate needs and enabling technologies. In addition, this infrastructure must be user-friendly, modular and scalable. This need is the motivation for the research described in this dissertation. The research is focused on the development of an open computing infrastructure that facilitates product and process design. In addition, this research explicitly deals with human interactions during design through a model that focuses on the role of a designer as that of decision-maker. The research perspective here is taken from that of design as a discipline with a focus on Decision-Based Design, Theory of Languages, Information Science, and Integration Technology. Given this background, a Model of IPPD is developed and implemented along the lines of a traditional experimental procedure: with the steps of establishing context, formalizing a theory, building an apparatus, conducting an experiment, reviewing results, and providing recommendations. Based on this Model, Design Processes and Specification can be explored in a structured and implementable architecture. An architecture for exploring design called DREAMS (Developing Robust Engineering Analysis Models and Specifications) has been developed which supports the activities of both meta-design and actual design execution. This is accomplished through a systematic process which is comprised of the stages of Formulation, Translation, and Evaluation. During this process, elements from a Design Specification are integrated into Design Processes. In addition, a software infrastructure was developed and is called IMAGE (Intelligent Multidisciplinary Aircraft Generation Environment). This represents a virtual apparatus in the Design Experiment conducted in this research. IMAGE is an innovative architecture because it explicitly supports design-related activities. This is accomplished through a GUI driven and Agent-based implementation of DREAMS. A HSCT design has been adopted from the Framework for Interdisciplinary Design Optimization (FIDO) and is implemented in IMAGE. This problem shows how Design Processes and Specification interact in a design system. In addition, the problem utilizes two different solution models concurrently: optimal and satisfying. The satisfying model allows for more design flexibility and allows a designer to maintain design freedom. As a result of following this experimental procedure, this infrastructure is an open system that it is robust to changes in both corporate needs and computer technologies. The development of this infrastructure leads to a number of significant intellectual contributions: 1) A new approach to implementing IPPD with the aid of a computer; 2) A formal Design Experiment; 3) A combined Process and Specification architecture that is language-based; 4) An infrastructure for exploring design; 5) An integration strategy for implementing computer resources; and 6) A seamless modeling language. The need for these contributions is emphasized by the demand by industry and government agencies for the development of these technologies.

Hale, Mark A.↗

NASA NTRS2003

Targeted Help for Spoken Dialogue Systems: Intelligent Feedback Improves Naive Users' Performance

We present experimental evidence that providing naive users of a spoken dialogue system with immediate help messages related to their out-of-coverage utterances improves their success in using the system. A grammar-based recognizer and a Statistical Language Model (SLM) recognizer are run simultaneously. If the grammar-based recognizer suceeds, the less accurate SLM recognizer hypothesis is not used. When the grammar-based recognizer fails and the SLM recognizer produces a recognition hypothesis, this result is used by the Targeted Help agent to give the user feed-back on what was recognized, a diagnosis of what was problematic about the utterance, and a related in-coverage example. The in-coverage example is intended to encourage alignment between user inputs and the language model of the system. We report on controlled experiments on a spoken dialogue system for command and control of a simulated robotic helicopter.

Hockey, Beth Ann↗

DOE OSTI2022

Structure-based discovery of potent WD repeat domain 5 inhibitors that demonstrate efficacy and safety in preclinical animal models

WD repeat domain 5 (WDR5) is a core scaffolding component of many multiprotein complexes that perform a variety of critical chromatin-centric processes in the nucleus. WDR5 is a component of the mixed lineage leukemia MLL/SET complex and localizes MYC to chromatin at tumor-critical target genes. As a part of these complexes, WDR5 plays a role in sustaining oncogenesis in a variety of human cancers that are often associated with poor prognoses. Thus, WDR5 has been recognized as an attractive therapeutic target for treating both solid and hematological tumors. Previously, small-molecule inhibitors of the WDR5-interaction (WIN) site and WDR5 degraders have demonstrated robust in vitro cellular efficacy in cancer cell lines and established the therapeutic potential of WDR5. However, these agents have not demonstrated significant in vivo efficacy at pharmacologically relevant doses by oral administration in animal disease models. We have discovered WDR5 WIN-site inhibitors that feature bicyclic heteroaryl P 7 units through structure-based design and address the limitations of our previous series of small-molecule inhibitors. Importantly, our lead compounds exhibit enhanced on-target potency, excellent oral pharmacokinetic (PK) profiles, and potent dose-dependent in vivo efficacy in a mouse MV4:11 subcutaneous xenograft model by oral dosing. Furthermore, these in vivo probes show excellent tolerability under a repeated high-dose regimen in rodents to demonstrate the safety of the WDR5 WIN-site inhibition mechanism. Collectively, our results provide strong support for WDR5 WIN-site inhibitors to be utilized as potential anticancer therapeutics.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

DEMographic MicrOSimulation (DEMOS) v2.0

DEMOS is an agent-based simulation framework used to evolve population demographic characteristics or lifecycle events such as education, marital status etc. DEMOS modules are designed to capture the interdependencies of short-term and long-term lifecycle events often influential in downstream transportation and land use modeling. An important facet of DEMOS is that it is dynamic, meaning it captures the impact of an agent's demographic characteristics in year 't' on their demographic status in year 't+1'. This has important consequences on medium- and long-term downstream modeling in different domains, such as transportation where decisions such as household vehicle transactions (i.e., buying, selling, or replacing a vehicle) depend current or past household vehicle holdings as well as household transitions. Other downstream modeling that can be enabled by DEMOS include building technology adoption or retrofit decisions, and more. DEMOS modules include: individual age progression year by year, individual mortality events, household restructuring events including marriage match-making; household birth events; individual education participation; individual labor force participation; child leaving household; household in-migration and out-migration for the region; household residence location choice and household mandatory destination choice (work and school). This version of DEMOS is tailored to be integrated with the land use simulation software UrbanSim.

Caicedo, Juan [UrbanSim, Inc.]↗

NASA NTRS2005

Validation Of The Airspace Concept Evaluation System Using Real World Data

This paper discusses the process of performing a validation of the Airspace Concept Evaluation System (ACES) using real world historical flight operational data. ACES inputs are generated from select real world data and processed to create a realistic reproduction of a single day of operations within the National Airspace System (NAS). ACES outputs are then compared to real world operational metrics and delay statistics for the reproduced day. Preliminary results indicate that ACES produces delays and airport operational metrics similar to the real world with minor variations of delay by phase of flight. ACES is a nation-wide fast-time simulation tool developed at NASA Ames Research Center. ACES models and simulates the NAS using interacting agents representing center control, terminal flow management, airports, individual flights, and other NAS elements. These agents pass messages between one another similar to real world communications. This distributed agent based system is designed to emulate the highly unpredictable nature of the NAS, making it a suitable tool to evaluate current and envisioned airspace concepts. To ensure that ACES produces the most realistic results, the system must be validated. There is no way to validate future concepts scenarios using real world historical data, but current day scenario validations increase confidence in the validity of future scenario results. Each operational day has unique weather and traffic demand schedules. The more a simulation utilizes the unique characteristic of a specific day, the more realistic the results should be. ACES is able to simulate the full scale demand traffic necessary to perform a validation using real world data. Through direct comparison with the real world, models may continuee to be improved and unusual trends and biases may be filtered out of the system or used to normalize the results of future concept simulations.

Zelinski, Shannon↗

DOE OSTI2026

ORCHID: Orchestrated Retrieval-Augmented Classification of High-Risk Property with Intelligent Decision-Making

High-Risk Property (HRP) classification is critical at U.S. Department of Energy (DOE) sites, where inventories include sensitive and often dual-use equipment. Compliance must track evolving rules designated by various export control policies to make transparent and auditable decisions. Traditional expert-only workflows are time-consuming, backlog-prone, and struggle to keep pace with shifting regulatory boundaries. We propose ORCHID, a modular agentic framework for HRP classification that pairs retrieval-augmented generation (RAG) with human oversight to produce policy based outputs that can be audited. Small cooperating agents—retrieval, description refiner, classifier, validator, and feedback logger—coordinate via agent-to-agent messaging and invoke tools through the Model Context Protocol (MCP) for model-agnostic on-premise operation. The interface follows an "Item to Evidence to Decision" loop with step-by-step reasoning, on-policy citations, and append-only audit bundles (run-cards, prompts, evidence). In preliminary tests on real HRP cases, ORCHID improves accuracy and traceability over a non-agentic baseline while deferring uncertain items to Subject Matter Experts (SMEs). The demonstration shows single item submission, grounded citations, SME feedback capture, and exportable audit artifacts—illustrating a practical path to trustworthy LLM assistance in sensitive DOE compliance workflows.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗

DOE OSTI2025

Multi-agent AI collaboration for digital twin development and assessment

Developing a digital twin (DT) model involves different steps that encompass formulating requirements, model development, implementation, and assessment with respect to real applications. Human expertise is required to coordinate and implement different steps in the DT development and assessment process. However, certain parts of this process can be automated using artificial intelligence (AI) agents for efficient workflow development. In this work, we test and analyze a multiagent AI collaboration with humans in the loop to automate different elements of the DT development and assessment process. To implement the workflow for multiagent AI DT development and assessment, we use Autogen, a multiagent framework developed by Microsoft. Autogen offers a modular and flexible framework for configuring and designing task-specific multiagent workflows. In this framework, large language models (LLMs) form the core intelligence of the AI agents where the quality and performance of the automated element is governed by the inherent capabilities and knowledge base of the LLM. We use retrieval augmented generation to supplement the LLM with relevant domain-specific information for DT requirement formulation. We illustrate this multiagent workflow using a case study on a thermal energy storage system, focusing on how AI agents can collaborate with humans to expedite and optimize different elements of DT development and assessment process.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS2006

Haughton-Mars Project Expedition 2005

The 2005 expedition to the Haughton-Mars Project (HMP) research station on Devon Island was part of a NASA-funded project on Space Logistics. A team of nine r&searchers from MIT went to the Canadian Arctic to participate in the annual I-IMP field campaign from July 8 to August 12, 2005. We investigated the applicability of the HMP research station as an analogue for planetary macro- and micro-logistics to the Moon and Mars, and began collecting data for modeling purposes. We also tested new technologies and procedures to enhance the ability of humans and robots to jointly explore remote environments. The expedition had four main objectives. We briefly summarize our key findings in each of these areas. 1. Classes of Supply: First, we wanted to understand what supply items existed at the HMP research station in support of planetary science and exploration research at and around the Haughton Crater. We also wanted to quantify the total amount of imported mass at HMP and compare this with predictions from existing parametric lunar base demand models. 2. Macro-Logistics Transportation Network: Our second objective was to understand the nodes, transportation routes, vehicles, capacities and crew and cargo mass flow rates required to support the HMP logistics network. 3. Agent and Asset Tracking: Since the current inventory management system on ISS relies heavily on barcodes and manual tracking, we wanted to test new automated technologies and procedures such as radio frequency identification RFID) to support exploration logistics. 4. Micro-Logistics (EVA): Finally, we wanted to understand the micro-logistical requirements of conducting both short (<1 day) and long traverses in the Mars-analog terrain on Devon Island. Micro-logistics involves the movement of surface vehicles, people and supplies from base to various exploration sites over short distances (<100 km).

deWeck, Olivier↗

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↗

NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

To support sustainable infrastructure on the Moon, NASA needs to leverage lunar resources for in-situ processing and construction. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for these tasks. To reliably perform these operations on the lunar surface, RASSOR's sensors and control systems need to be robust and maximize information extracted from a reduced sensor payload. Herein, we present our findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments in which we applied reinforcement learning algorithms to learn autonomous trenching controllers and produced state estimation architectures. We developed two simulations: a 2D excavation simulation used to facilitate parameter selection, and a 3D simulation developed using a game physics engine to simulate simplified soil interactions and incorporate robotic agents parameterized by dynamic models. Within these simulations, we learned autonomous excavation routines that exceed excavation efficiency measures as compared against RASSOR's existing control and teleoperation-based methods.

RASSOR↗

NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

RASSOR↗

DOE OSTI2025

Autonomous alloy composition optimization using molecular dynamics guided by a large language model

Here, we present an autonomous materials discovery framework that couples a large language model (LLM) with molecular dynamics (MD) simulations to optimize Fe–Cr–Mn alloy compositions for tensile strength. Starting from six distinct compositions, the LLM operated as an intelligent agent, iteratively proposing changes based on prior simulation results and constraints. Over 50 iterations per case, the LLM adaptively explored the composition space, identifying high-strength regions, not easily accessible by conventional methods. The highest strength, 18.7 GPa, was achieved with Fe 71 Cr 25 Mn 4 composition, identified from a Fe 75 Cr 20 Mn 5 starting point. The LLM autonomously adjusted its strategy in real time, demonstrating closed-loop decision-making using commodity hardware. This approach showcases the potential of LLMs as scientific co-pilots, capable of accelerating materials discovery and generalizable to other domains like biology and drug design.

Autonomy↗

DOE OSTI2024

CACTUS: Chemistry Agent Connecting Tool Usage to Science

Large language models (LLMs) have shown remarkable potential in various domains but often lack the ability to access and reason over domain-specific knowledge and tools. In this article, we introduce Chemistry Agent Connecting Tool-Usage to Science (CACTUS), an LLM-based agent that integrates existing cheminformatics tools to enable accurate and advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama3-8b, and Mistral-7b, on a benchmark of thousands of chemistry questions. Our results demonstrate that CACTUS significantly outperforms baseline LLMs, with the Gemma-7b, Mistral-7b, and Llama3-8b models achieving the highest accuracy regardless of the prompting strategy used. Moreover, we explore the impact of domain-specific prompting and hardware configurations on model performance, highlighting the importance of prompt engineering and the potential for deploying smaller models on consumer-grade hardware without a significant loss in accuracy. By combining the cognitive capabilities of open-source LLMs with widely used domain-specific tools provided by RDKit, CACTUS can assist researchers in tasks such as molecular property prediction, similarity searching, and drug-likeness assessment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Attention Enabled Multi-Agent DRL for Decentralized Volt-VAR Control of Active Distribution System Using PV Inverters and SVCs

This paper proposes attention enabled multi-agent deep reinforcement learning (MADRL) framework for active distribution network decentralized Volt-VAR control. Using the unsupervised clustering, the whole distribution system can be decomposed into several sub-networks according to the voltage and reactive power sensitivity relationships. Then, the distributed control problem of each sub-network is modeled as Markov games and solved by the improved MADRL algorithm, where each sub-network is modeled as an adaptive agent. An attention mechanism is developed to help each agent focus on specific information that is mostly related to the reward. All agents are centrally trained offline to learn the optimal coordinated Volt-VAR control strategy and executed in a decentralized manner to make online decisions with only local information. Compared with other distributed control approaches, the proposed method can effectively deal with uncertainties, achieve fast decision makings, and significantly reduce the communication requirements. Comparison results with model-based and other data-driven methods on IEEE 33-bus and 123-bus systems demonstrate the benefits of the proposed approach.

distribution network↗

DOE OSTI2023

Microgrid energy scheduling under uncertain extreme weather: Adaptation from parallelized reinforcement learning agents

Microgrids are useful solutions for integrating renewable energy resources and providing seamless green electricity to minimize carbon footprint. In recent years, extreme weather events happened often worldwide and caused significant economic and societal losses. Such events bring uncertainties to the microgrid energy scheduling problems and increase the challenges of microgrid operation. Traditional optimization approaches suffer from the inaccuracy of the uncertain microgrid model and the unseen events. Existing reinforcement learning (RL) - based approaches are also hampered by the limited generalization and the increasing computational burden when stochastic formulations are required to accommodate the uncertainties. This paper proposes a new parallelized reinforcement learning (PRL) method based on the probabilistic events to handle the microgrid energy uncertainties. Specifically, several local learning agents are employed to interact with pertinent microgrid environments in a distributed manner and report outcomes to the global agent, which will optimize microgrid energy resources online during extreme events. The stochastic microgrid energy optimization problem is reformulated to include all possible scenarios with probabilities. The advantage estimate functions of learning agents are designed with a backward sweep to transfer the outcomes to the value function updating process. Two simulation studies, stochastic optimization and online testing, are performed to compare with several existing RL approaches. Results substantiate that the proposed PRL method can achieve up to 20% optimization performance improvement with 4 and 28 times less computation cost than Q-learning with experience replay and multi-agent Q-learning approaches, respectively.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2021

Extending the Near-Infrared Emission Range of Indium Phosphide Quantum Dots for Multiplexed In Vivo Imaging

This report of the reddest emitting indium phosphide quantum dots (InP QDs) to date demonstrates tunable, near-infrared (NIR) photoluminescence (PL) as well as PL multiplexing in the first optical tissue window while avoiding toxic constituents. This synthesis overcomes the InP “growth bottleneck” and extends the emission peak of InP QDs deeper into the first optical tissue window using an inverted QD heterostructure, specifically ZnSe/InP/ZnS core/shell/shell nanoparticles. The QDs exhibit InP shell thickness-dependent tunable emission with peaks ranging from 515–845 nm. The high absorptivity of InP yields effective photoexcitation of the QDs with UV, visible, and NIR wavelengths. These nanoparticles extend the range of tunable direct-bandgap emission from InP-based nanostructures, effectively overcoming a synthetic barrier that has prevented InPbased QDs from reaching their full potential as NIR imaging agents. Further, multiplexed lymph node imaging in a mouse model demonstrates the potential of the NIR-emitting InP particles for in vivo imaging.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

DOE OSTI2022

A high-fidelity building performance simulation test bed for the development and evaluation of advanced controls

We present an open-source building performance simulation test bed, the Advanced Controls Test Bed (ACTB), that interfaces high-fidelity Spawn of EnergyPlus building models, with advanced controllers implemented in Python. Additionally, the ACTB leverages the Building Optimization Testing and Alfalfa platforms for managing simulations, providing an external clock, a representational state transfer (REST) application programming interface (API), and key performance indicators for evaluating the effectiveness of control strategies. The REST API allows the development of external controllers programmed in languages such as Python, which provides flexibility and a rich choice of scientific libraries for designing control sequences. We present three test cases based on the U.S. Department of Energy's Reference Small Office Building to demonstrate the ACTB's capabilities: (a) rule-based controls compliant with ASHRAE Guideline 36 control sequences; (b) an economic model predictive control implemented using do-mpc; and (c) a deep Q-network reinforcement learning agent implemented using OpenAI Gym.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗