SEARCH · Engineering Papers

Results for “online adaptivity”

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 163 records · Page 9

All sources NASA NTRS DOE OSTI

NASA NTRS2004

Online model-based diagnosis to support autonomous operation of an advanced life support system

This article describes methods for online model-based diagnosis of subsystems of the advanced life support system (ALS). The diagnosis methodology is tailored to detect, isolate, and identify faults in components of the system quickly so that fault-adaptive control techniques can be applied to maintain system operation without interruption. We describe the components of our hybrid modeling scheme and the diagnosis methodology, and then demonstrate the effectiveness of this methodology by building a detailed model of the reverse osmosis (RO) system of the water recovery system (WRS) of the ALS. This model is validated with real data collected from an experimental testbed at NASA JSC. A number of diagnosis experiments run on simulated faulty data are presented and the results are discussed.

Non-NASA Center↗

DOE OSTI2023

WiP Abstract: Edge-Based Privacy of Naturalistic Driving Data Collection

Collecting large driving datasets is important for data-driven transportation research and studied in naturalistic driving [3]. Due to the standard implementation of a Controller Area Network (CAN) bus for a vehicle’s inter-module communication, many off-the-shelf devices can easily transform a vehicle into a rich data collection utility [2]. Vehicles with Adaptive Cruise Control (ACC) are an example of a feature resulting in emergent traffic behavior when scaled [4]. While these utilities were designed with particular data use cases, data may be publicly shared to benefit other researchers through online tools like CyVerse [1]. However, such data should only be shared when any private information is removed. This private information may exist as a set of GPS coordinates, since the start and end points of a trip may designate a driver’s place of residence or work. When considering larger continuously-collected data sets with a focus on naturalistic driving, many drivers are needed to make data collection feasible. Removal of private information becomes much more of a challenge since every driver may uniquely define their geographic privacy. This project aims to build upon the foundation of libpanda [2] by adding features of edge-based data privacy enforcement. In it’s current form, libpanda uses a GPS in conjunction with a CAN interface to record data. Libpanda feature s a set of startup and shutdown scripts to perform automatic data collection and upload. With additional support hardware on a Raspberry Pi, the Pi can maintain power on vehicle shutdown to automatically upload data before shutdown.

Bunting, Matt↗

NASA NTRS1989

Case studies in configuration control for redundant robots

A simple approach to configuration control of redundant robots is presented. The redundancy is utilized to control the robot configuration directly in task space, where the task will be performed. A number of task-related kinematic functions are defined and combined with the end-effector coordinates to form a set of configuration variables. An adaptive control scheme is then utilized to ensure that the configuration variables track the desired reference trajectories as closely as possible. Simulation results are presented to illustrate the control scheme. The scheme has also been implemented for direct online control of a PUMA industrial robot, and experimental results are presented. The simulation and experimental results validate the configuration control scheme for performing various realistic tasks.

Seraji, H.↗

DOE OSTI2022

Contextual Active Online Model Selection with Expert Advice

How can we collect the most useful labels to learn a model selection policy, when presented with arbitrary heterogeneous data streams? In this paper, we formulate this task as a contextual active model selection problem, where at each round the learner receives an unlabeled data point along with a context. The goal is to output the best model for any given context without obtaining an excessive amount of labels. In particular, we focus on the task of selecting pre-trained classifiers, and propose a contextual active model selection algorithm (CAMS), which relies on a novel uncertainty sampling query criterion defined on a given policy class for adaptive model selection. In comparison to prior art, our algorithm does not assume a globally optimal model. We provide rigorous theoretical analysis for the regret and query complexity under both adversarial and stochastic settings. Our experiments on several benchmark classification datasets demonstrate the algorithm’s effectiveness in terms of both regret and query complexity. Notably, to achieve the same accuracy, CAMS incurs less than 10% of the label cost when compared to the best online model selection baselines on CIFAR10.

Liu, Xuefeng↗

DOE OSTI2024

SmoQyDQMC.jl: A flexible implementation of determinant quantum Monte Carlo for Hubbard and electron-phonon interactions

We introduce the SmoQyDQMC.jl package, a Julia implementation of the determinant quantum Monte Carlo algorithm. SmoQyDQMC.jl supports generalized tight-binding Hamiltonians with on-site Hubbard and generalized electron-phonon ( e e -ph) interactions, including non-linear e e -ph coupling and anharmonic lattice potentials. Our implementation uses hybrid Monte Carlo methods with exact forces for sampling the phonon fields, enabling efficient simulation of low-energy phonon branches, including acoustic phonons. The SmoQyDQMC.jl package also uses a flexible scripting interface, allowing users to adapt it to different workflows and interface with other software packages in the Julia ecosystem. The code for this package can be downloaded from our GitHub repository at https://github.com/SmoQySuite/SmoQyDQMC.jl or installed using the Julia package manager. The online documentation, including examples, can be obtained from our document page at https://smoqysuite.github.io/SmoQyDQMC.jl/stable/.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2024

Codebase release r0.3 for SmoQyDQMC.jl

Cohen-Stead, Benjamin (ORCID:0000000279156280)↗

NASA NTRS1990

30 years of adaptive neural networks - Perceptron, Madaline, and backpropagation

Fundamental developments in feedforward artificial neural networks from the past thirty years are reviewed. The history, origination, operating characteristics, and basic theory of several supervised neural-network training algorithms (including the perceptron rule, the least-mean-square algorithm, three Madaline rules, and the backpropagation technique) are described. The concept underlying these iterative adaptation algorithms is the minimal disturbance principle, which suggests that during training it is advisable to inject new information into a network in a manner that disturbs stored information to the smallest extent possible. The two principal kinds of online rules that have developed for altering the weights of a network are examined for both single-threshold elements and multielement networks. They are error-correction rules, which alter the weights of a network to correct error in the output response to the present input pattern, and gradient rules, which alter the weights of a network during each pattern presentation by gradient descent with the objective of reducing mean-square error (averaged over all training patterns).

Widrow, Bernard↗

NASA NTRS2010

Community-Based Services that Facilitate Interoperability and Intercomparison of Precipitation Datasets from Multiple Sources

Over the past 12 years, large volumes of precipitation data have been generated from space-based observatories (e.g., TRMM), merging of data products (e.g., gridded 3B42), models (e.g., GMAO), climatologies (e.g., Chang SSM/I derived rain indices), field campaigns, and ground-based measuring stations. The science research, applications, and education communities have greatly benefited from the unrestricted availability of these data from the Goddard Earth Sciences Data and Information Services Center (GES DISC) and, in particular, the services tailored toward precipitation data access and usability. In addition, tools and services that are responsive to the expressed evolving needs of the precipitation data user communities have been developed at the Precipitation Data and Information Services Center (PDISC) (http://disc.gsfc.nasa.gov/precipitation or google NASA PDISC), located at the GES DISC, to provide users with quick data exploration and access capabilities. In recent years, data management and access services have become increasingly sophisticated, such that they now afford researchers, particularly those interested in multi-data set science analysis and/or data validation, the ability to homogenize data sets, in order to apply multi-variant, comparison, and evaluation functions. Included in these services is the ability to capture data quality and data provenance. These interoperability services can be directly applied to future data sets, such as those from the Global Precipitation Measurement (GPM) mission. This presentation describes the data sets and services at the PDISC that are currently used by precipitation science and applications researchers, and which will be enhanced in preparation for GPM and associated multi-sensor data research. Specifically, the GES-DISC Interactive Online Visualization ANd aNalysis Infrastructure (Giovanni) will be illustrated. Giovanni enables scientific exploration of Earth science data without researchers having to perform the complicated data access and match-up processes. In addition, PDISC tool and service capabilities being adapted for GPM data will be described, including the Google-like Mirador data search and access engine; semantic technology to help manage large amounts of multi-sensor data and their relationships; data access through various Web services (e.g., OPeNDAP, GDS, WMS, WCS); conversion to various formats (e.g., netCDF, HDF, KML (for Google Earth)); visualization and analysis of Level 2 data profiles and maps; parameter and spatial subsetting; time and temporal aggregation; regridding; data version control and provenance; continuous archive verification; and expertise in data-related standards and interoperability. The goal of providing these services is to further the progress towards a common framework by which data analysis/validation can be more easily accomplished.

Liu, Zhong↗

DOE OSTI2026

Decentralised Reinforcement Learning for Dynamic Cyberattack Response in Microgrid Networks

Microgrids rely on communication networks for reliable operation, which makes them inherently vulnerable to cyberattacks. Such attacks can destabilise system dynamics and drive states away from their nominal operating trajectories. Although several physics-informed and machine learning-based strategies have been developed to counter these threats, the rapidly evolving cyber landscape enables adversaries to bypass static defences or rules-based mitigation approaches. This paper proposes a dynamic, online-trained and fully decentralised reinforcement learning (RL)-based cyberattack response framework to protect microgrids from evolving cyberattacks. The proposed framework deploys multiple deep Q-networks (DQNs), each associated with a distributed energy resource (DER), to enable localised and adaptive attack mitigation. In this framework, each DQN processes local voltage and frequency measurements—combined with intrusion detection system (IDS) alerts—as observations and rewards to guide decision-making. Extensive simulation studies demonstrate the robustness of the proposed framework under diverse attack scenarios and varying IDS-induced detection delays. Comparative analysis highlights its superiority over existing static or preexisting rules-based mitigation approaches. Finally, we present an analysis that shows the framework's scalability to real-life microgrids with more interacting agents.

24 POWER TRANSMISSION AND DISTRIBUTION↗

NASA NTRS2001

Integrated Component-based Data Acquisition Systems for Aerospace Test Facilities

The Multi-Instrument Integrated Data Acquisition System (MIIDAS), developed by the NASA Langley Research Center, uses commercial off the shelf (COTS) products, integrated with custom software, to provide a broad range of capabilities at a low cost throughout the system s entire life cycle. MIIDAS combines data acquisition capabilities with online and post-test data reduction computations. COTS products lower purchase and maintenance costs by reducing the level of effort required to meet system requirements. Object-oriented methods are used to enhance modularity, encourage reusability, and to promote adaptability, reducing software development costs. Using only COTS products and custom software supported on multiple platforms reduces the cost of porting the system to other platforms. The post-test data reduction capabilities of MIIDAS have been installed at four aerospace testing facilities at NASA Langley Research Center. The systems installed at these facilities provide a common user interface, reducing the training time required for personnel that work across multiple facilities. The techniques employed by MIIDAS enable NASA to build a system with a lower initial purchase price and reduced sustaining maintenance costs. With MIIDAS, NASA has built a highly flexible next generation data acquisition and reduction system for aerospace test facilities that meets customer expectations.

Ross, Richard W.↗

NASA NTRS2020

A Reinforcement Learning Framework for Space Missions in Unknown Environments

A land-and-traverse mission to icy worlds such as Europa and Enceladus is challenging due to lack of prior knowledge regarding the terrain conditions. Previous work [1] showed that rovers with high degrees of freedom (DoF) can achieve robust traversal by leveraging redundant modes for mobility to counter terrain uncertainty (e.g. walking, driving, or inch-worming). This paper presents a generic and scalable reinforcement learning scheme for enabling on-board decision making on rovers to automatically switch between modes of traversal based on online performance feedback. The objective is to maximize energy efficiency, minimize operator input and successfully negotiate unstructured terrain conditions without relying on exhaustive prior knowledge. The proposed methodology is well grounded in the literature on reinforcement learning and has been adapted to address conformance to validation and verification requirements and JPL flight operations history of using per-sol prescribed sequences for a space mission.

Tavallali, Peyman↗

DOE OSTI2026

HydraGNN_Predictive_GFM_2026 - Ensemble of predictive graph foundation models for atomistic materials modeling

This release contains data and parameters of HydraGNN-based graph foundation models trained as a result of the work published in the pre-print "Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data" by M. Lupo Pasini et al. (https://arxiv.org/abs/2604.15380). We jointly train on 16 open first-principles datasets (544+ million structures covering 85+ elements) using a multi-task architecture with per-dataset heads and a scalable ADIOS2/DDStore data pipeline. On Frontier, we execute six large-scale DeepHyper hyperparameter optimization campaigns in FP64 and promote the top-performing message-passing models to sustained 2,048-node training, yielding a PaiNN-based lead model. The version of HydraGNN used to generate the outputs provided in this release is HydraGNN v5.0 (https://github.com/ORNL/HydraGNN/releases/tag/v5.0) The list of datasets used for the training of the graph foundation model is the following: 1) Alexandria [1] 2) ANI1x [2] 3) MPTrj [3] 4) Open Catalyst 2020 (OC20) [4] 5) Open Catalyst 2022 (OC22) [5] 6) Open Catalyst 2025 (OC25) [6] 7) Open Direct ir Capture 2023 (ODAC23) [7] 8) Open Materials 2024 (OMat24) [8] 9) Open Molecules 2025 (OMol25) [9] 10) OMol25-neutral (subset of OMol25 that contains only molecules with zero total charge) 11) OMol25-non-neutral (subset of OMol25 that contains only molecules with non-zero total charge) 12) Open Polymers 2026 (OPoly2026) [10] 13) Nabla2DFT [11] 14) QCML [12] 15) QM7X [reference 13] 16) transition1x [14] Dataset references: [1] J. Schmidt et al., “A dataset of 175k stable and metastable materials calculated with the PBEsol and SCAN functionals,” Scientific Data, vol. 9, p. 64, 2022. [2] J. S. Smith et al., “The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules,” Scientific Data, vol. 7, p. 134, 2020. [Online]. Available: https: //www.nature.com/articles/s41597-020-0473-z [3] A. Jain et al., “Commentary: The Materials Project: A materials genome approach to accelerating materials innovation,” APL Materials, vol. 1, no. 1, p. 011002, 07 2013. [Online]. Available: https://doi.org/10.1063/1.4812323 [4] L. Chanussot et al., “Open catalyst 2020 (oc20) dataset and community challenges,” ACS Catalysis, vol. 11, no. 10, pp. 6059–6072, 2021. [Online]. Available: https://doi.org/10.1021/acscatal.0c04525 [5] K. Tran et al., “Open catalyst 2022 (oc22) dataset and challenges for oxidation electrocatalysts,” ACS Catalysis, vol. 13, no. 5, pp. 3066–3084, 2023. [Online]. Available: https://doi.org/10.1021/acscatal.2c05426 [6] S. J. Sahoo et al., “The open catalyst 2025 (oc25) dataset and models for solid-liquid interfaces,” arXiv preprint arXiv:2509.17862, 2025. [Online]. Available: https://arxiv.org/abs/2509.17862 [7] A. Sriram et al., “The open DAC 2023 dataset and challenges for sorbent discovery in direct air capture,” ACS Central Science, vol. 10, no. 5, pp. 923–941, 2024. [8] L. Barroso-Luque et al., “Open materials 2024 (omat24) inorganic materials dataset and models,” 2024. [Online]. Available: https://arxiv.org/abs/2410.12771 [9] D. S. Levine et al., “The open molecules 2025 (OMol25) dataset, evaluations, and models,” 2025. [Online]. Available: https://arxiv.org/abs/2505.08762 [10] D. S. Levine et al., The open polymers 2026 (OPoly26) dataset and evaluations,” arXiv preprint arXiv:2512.23117, 2025. [Online]. Available: https://arxiv.org/abs/2512.23117 [11] K. Khrabrov et al., “Nabla2dft: A universal quantum chemistry dataset of drug-like molecules and a benchmark for neural network potentials,” in NeurIPS 2024 Datasets and Benchmarks Track, 2024. [Online]. Available: https://openreview.net/forum?id=ElUrNM9U8c [12] S. Ganscha et al., “The QCML dataset, quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations,” Scientific Data, vol. 12, p. 406, 2025. [13] J. Hoja et al., “QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules,” Scientific Data, vol. 8, p. 43, 2021. [Online]. Available: https://www.nature.com/articles/s41597-021-00812-2 [14] M. Schreiner et al., “Transition1x - a dataset for building generalizable reactive machine learning potentials,” Scientific Data, vol. 9, p. 779, 2022. The folder "datasets_ADIOS2_format" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "datasets_ADIOS2_format" directory contains 2 sub-directories, one for the version "v1" of the datasets and one for the version "v2" of the datasets. The version "v1" of the datasets provides values of the total energy as they are extracted from the original data as it was released by the respective institutions. The version "v2" of the datasets provides values of the energy that have been realigned. The realignment was performed by training a linear regression model that predicts the total energy as a function of the chemical composition of the atomistic structure, and then subtract such prediction from the original value of the total energy. Both folders "v1" and "v2" contain 16 sub-directories, each corresponding to an ADIOS2-formatted dataset The folder "DeepHyper-results" contains the configurational files and model's parameters for all the 186 HPO trials that were successfully completed by the scalable hyperparameter optimization (HPO) runs on Frontier. The content of the folder "DeepHyper-results" I structured as follows: 1) task-list.txt: list of mpnn name, jobid, and deephyper task id 2) gfm_${MPNN}_${JOBID}_0.${TASKID}: run directory with checkpoint files 3) gfm_${MPNN}: deephyper summary directory (*.csv) for each specific MPNN type 4) deephyper-experiment-${JOBID}: output and error logs for each job The file "deephyper-sorted.csv" contains the details of each HydraGNN model built and tested by HPO, obtained by merging the (*.csv) filed from each HPO run executed. Out of all the HPO trials, we selected 10 to continue the training of the respective HydraGNN models. Due to limited computational budget available in the LRN070 allocation we could not complete the training till convergence for all these 10 selected models. The folder "models" contains multiple sub-folders, one per each HydraGNN model trained. Each model sub-folder contains the parameters of each HydraGNN model, with multiple checkpoint-restarts. The list of sub-folders are as follows: 1) multidataset_hpo-BEST1-fp64 2) multidataset_hpo-BEST2-fp64 3) multidataset_hpo-BEST3-fp64 4) multidataset_hpo-BEST4-fp64 5) multidataset_hpo-BEST5-fp64 6) multidataset_hpo-BEST6-fp64 7) multidataset_hpo-BEST7-fp64 8) multidataset_hpo-BEST8-fp64 9) multidataset_hpo-BEST9-fp64 10) multidataset_hpo-BEST10-fp64 Within each one of these folders, additional auxiliary log files are provided with descriptions about how the training proceeded. The lead PaiNN-model is contained inside "multidataset_hpo-BEST6-fp64". The file "mlp_branch_weights" contains the parameters of the multi-layer perceptron (MLP) used to reconcile the predictions of the 16 output decoding heads of the HydragNN architectures. The MLP takes in input the chemical composition of the atomistic structure and predicts averaging weights to linearly mix the predictions of each output decoding head toward consolidating them into a single one. The folder "1.1billion-structure-inference" contains 1.1 billion atomistic structures randomly generated. Each structures is associated with energy and forces predicted with the lead-PaiNN model combined with the MLP model for reconciliation of the multi-branch predictions generated by the 16 output decoding heads. The folder "1.1billion-structure-inference" contains 9,300 (*.tar.gz) subdirectories, one per Frontier compute node used to execute the inference at exascale. Once uncompressed, each (*.tar.gz) subdirectory contains an ADIOS2 (*.bp) file container, where each atomistic structure is stored as a PyTorch-Geometric Data object. The file "export_dataset_environment_variables.sh" contains the environment variables that need to be set before running the HydraGNN code to reproduce the results provided in this dataset release. The code that can be used to load the ADIOS2 files, load HydraGNN models, and run inference is available at: https://github.com/ORNL/HydraGNN/releases/tag/v5.0

36 MATERIALS SCIENCE↗

DOE OSTI2026

Adaptation of virtual synchronous generators to dynamic conditions in power grids

Virtual synchronous generators (VSGs) are widely adopted as grid-forming controls for inverter-based resources. However, when grid conditions vary significantly as characterized by changes in short-circuit ratio (SCR) and the reactance-to-resistance (X/R) ratio, fixed-gain designs and the commonly used P–Q decoupling assumption can become inaccurate. Such conditions can degrade transient power performance, leading to oscillations, prolonged settling, and overshoot, particularly in stiff-grid operating points. This paper quantifies how grid strength and impedance-dependent coupling affect the active–reactive power dynamics of a conventional VSG over a broad range of SCR and X/R values. An adaptive VSG tuning framework is then developed by combining (i) a coupling-explicit, impedance-parameterized state-space model to enable systematic controller synthesis, (ii) a full-state-feedback law designed via pole placement to meet prescribed damping and settling-time specifications, and (iii) a physics-informed neural network (PINN)–based online grid-impedance estimator that updates controller gains in real time as grid conditions vary. Offline simulations in MATLAB/Simulink and real-time validation on an OPAL-RT platform show that the proposed method preserves consistent damping and settling behavior with reduced overshoot across wide SCR and X/R ranges, compared with fixed-gain VSG baselines.

Adaptive control↗

NASA NTRSDate not supplied

Online Rapid Analysis of Laser Heterodyne Radiometer (LHR) Data Using the Planetary Spectrum Generator (PSG)

One of the biggest challenges in developing scientific instruments is not just the build and testing of an instrument, but the method for processing the data and producing a consistent, well characterized data product that can be confidently used by the public and scientific community. Raw data products are frequently an array of numbers that are a read-out of voltages. The challenge is to convert these arrays into meaningful information as well as remove noise and interferences. Because this can be a tedious and time-consuming, the goal is to automate the process so that data ca be processed rapidly and be available in real-time for event monitoring. Here we present a rapid analysis method for Laser Heterodyne Radiometer (LHR) data that can be used to analyze data taken from a range of LHR observation modes (column, limb, etc.). This online tool uses the versatile Planetary Spectrum Generator (PSG) and allows LHR users to quickly analyze their own data using a NASA Goddard Space Flight Center (GSFC) monitored capability to ensure quality and reproducibility in the data products. Background: Development of a miniaturized LHR (mini-LHR) as a ground instrument for measuring carbon dioxide (CO 2 ) and methane (CH 4 ) in the atmospheric column started in 2009 with the commercial availability of distributive feedback lasers (DFB) in wavelengths that could measure absorption of gases in the near-IR. As new DFB lasers, detectors and hardware emerged at different wavelengths, additional gases were added to the capability. The mini-LHR was adapted into an occultation-viewing CubeSat with Lawrence Livermore National Laboratory (LLNL) for observing CO 2 , CH 4 , and H 2 O in the limb and was launched in 2019. Other versions of the LHR technology have been designed for observation of water vapor in the lunar exosphere as well as observations of trace gases in planetary atmospheres and plumes from icy moons. The PSG is an online tool developed at GSFC that can be used for synthesizing Earth and planetary spectra (atmospheres and surfaces) over a broad range of wavelengths (0.1 μm to 100 mm) for any observatory, orbiter or lander. Spectra are simulated by combining several state-of-the-art radiative transfer models, spectroscopic databases, planetary databases, as well as modern-era retrospective analysis for research and applications, version 2 (MERRA-2) data set which provides meteorological inputs such as modeled surface pressure for calculating dry-air columns.

Emily Wilson↗

NASA NTRS2016

Serious Gaming for Test & Evaluation of Clean-Slate (Ab Initio) National Airspace System (NAS) Designs

Incremental approaches to air transportation system development inherit current architectural constraints, which, in turn, place hard bounds on system capacity, efficiency of performance, and complexity. To enable airspace operations of the future, a clean-slate (ab initio) airspace design(s) must be considered. This ab initio National Airspace System (NAS) must be capable of accommodating increased traffic density, a broader diversity of aircraft, and on-demand mobility. System and subsystem designs should scale to accommodate the inevitable demand for airspace services that include large numbers of autonomous Unmanned Aerial Vehicles and a paradigm shift in general aviation (e.g., personal air vehicles) in addition to more traditional aerial vehicles such as commercial jetliners and weather balloons. The complex and adaptive nature of ab initio designs for the future NAS requires new approaches to validation, adding a significant physical experimentation component to analytical and simulation tools. In addition to software modeling and simulation, the ability to exercise system solutions in a flight environment will be an essential aspect of validation. The NASA Langley Research Center (LaRC) Autonomy Incubator seeks to develop a flight simulation infrastructure for ab initio modeling and simulation that assumes no specific NAS architecture and models vehicle-to-vehicle behavior to examine interactions and emergent behaviors among hundreds of intelligent aerial agents exhibiting collaborative, cooperative, coordinative, selfish, and malicious behaviors. The air transportation system of the future will be a complex adaptive system (CAS) characterized by complex and sometimes unpredictable (or unpredicted) behaviors that result from temporal and spatial interactions among large numbers of participants. A CAS not only evolves with a changing environment and adapts to it, it is closely coupled to all systems that constitute the environment. Thus, the ecosystem that contains the system and other systems evolves with the CAS as well. The effects of the emerging adaptation and co-evolution are difficult to capture with only combined mathematical and computational experimentation. Therefore, an ab initio flight simulation environment must accommodate individual vehicles, groups of self-organizing vehicles, and large-scale infrastructure behavior. Inspired by Massively Multiplayer Online Role Playing Games (MMORPG) and Serious Gaming, the proposed ab initio simulation environment is similar to online gaming environments in which player participants interact with each other, affect their environment, and expect the simulation to persist and change regardless of any individual player's active participation.

Allen, B. Danette↗

DOE OSTI2022

Reinforcement Learning for feedback-enabled cyber resilience

The rapid growth in the number of devices and their connectivity has enlarged the attack surface and made cyber systems more vulnerable. As attackers become increasingly sophisticated and resourceful, mere reliance on traditional cyber protection, such as intrusion detection, firewalls, and encryption, is insufficient to secure the cyber systems. Cyber resilience provides a new security paradigm that complements inadequate protection with resilience mechanisms. A Cyber-Resilient Mechanism (CRM) adapts to the known or zero-day threats and uncertainties in real-time and strategically responds to them to maintain the critical functions of the cyber systems in the event of successful attacks. Feedback architectures play a pivotal role in enabling the online sensing, reasoning, and actuation process of the CRM. Reinforcement Learning (RL) is an important gathering of algorithms that epitomize the feedback architectures for cyber resilience. It allows the CRM to provide dynamic and sequential responses to attacks with limited or without prior knowledge of the environment and the attacker. In this work, we review the literature on RL for cyber resilience and discuss the cyber-resilient defenses against three major types of vulnerabilities, i.e., posture-related, information-related, and human-related vulnerabilities. Here we introduce moving target defense, defensive cyber deception, and assistive human security technologies as three application domains of CRMs to elaborate on their designs. The RL algorithms also have vulnerabilities themselves. We explain the major vulnerabilities of RL and present develop several attack models where the attacker target the information exchanged between the environment and the agent: the rewards, the state observations, and the action commands. We show that the attacker can trick the RL agent into learning a nefarious policy with minimum attacking effort. The paper introduces several defense methods to secure the RL-enabled systems from these attacks. However, there is still a lack of works that focuses on the defensive mechanisms for RL-enabled systems. Last but not least, we discuss the future challenges of RL for cyber security and resilience and emerging applications of RL-based CRMs.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1987

Adaptive force and position control of manipulators

Systematic methods for the design of adaptive force and position controllers for robot manipulators within the hybrid control architecture are presented. The force controller tracks the desired force setpoints while the position controller tracks the desired position trajectories. The present control schemes are computationally efficient and suitable for implementation in online control with high sampling rates.

Seraji, H.↗

DOE OSTI2026

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

High-throughput scientific facilities such as the Large Hadron Collider depend on real-time event filtering (\textit{triggering}) under tight constraints on bandwidth, latency, and storage. In practice, trigger menus are largely static and hand-tuned and can become suboptimal as detector conditions, pileup, and background composition drift over time. We cast online threshold tuning as a sequential decision-making problem: a reinforcement learning agent ingests streaming summaries of recent rates and signal-sensitive features and updates trigger thresholds to maximize signal efficiency while tracking a target background rate within a tolerance band. We adapt Group-Filtered Policy Optimization (GFPO) to streaming control and introduce two variants (GFPO-F, GFPO-FR) that enforce background rate feasibility during training. On a benchmark that emulates realistic collider operation, we study two representative triggers: a total transverse energy ($H_{T}$) trigger sensitive to pileup variation, and an anomaly-detection (AD) trigger based on reconstruction loss for rare or non-standard signatures. On Monte Carlo streams, our agent increases the fraction of in-tolerance time intervals by 48% ($H_T$) and 28% (AD), with a cumulative gain of up to 2% in signal efficiency on those in-tolerance intervals. Transferring from simulation to \emph{real} collision data (CMS Run 283408), the same agent, without fine-tuning, achieves a 56% ($H_T$) and 28% (AD) in-tolerance improvement over baselines, with further signal-efficiency gain on both triggers. To our knowledge, this is the \emph{first} demonstration of RL-based trigger control on real Large Hadron Collider collision data. Code is available at https://github.com/Zixind/GFPO_LHC (see repo for details).

Ding, Zixin [Chicago U.]↗