Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptive learning”

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 847 records · Page 47

Adaptive Inverse Control for Rotorcraft Vibration Reduction

This thesis extends the Least Mean Square (LMS) algorithm to solve the mult!ple-input, multiple-output problem of alleviating N/Rev (revolutions per minute by number of blades) helicopter fuselage vibration by means of adaptive inverse control. A frequency domain locally linear model is used to represent the transfer matrix relating the higher harmonic pitch control inputs to the harmonic vibration outputs to be controlled. By using the inverse matrix as the controller gain matrix, an adaptive inverse regulator is formed to alleviate the N/Rev vibration. The stability and rate of convergence properties of the extended LMS algorithm are discussed. It is shown that the stability ranges for the elements of the stability gain matrix are directly related to the eigenvalues of the vibration signal information matrix for the learning phase, but not for the control phase. The overall conclusion is that the LMS adaptive inverse control method can form a robust vibration control system, but will require some tuning of the input sensor gains, the stability gain matrix, and the amount of control relaxation to be used. The learning curve of the controller during the learning phase is shown to be quantitatively close to that predicted by averaging the learning curves of the normal modes. For higher order transfer matrices, a rough estimate of the inverse is needed to start the algorithm efficiently. The simulation results indicate that the factor which most influences LMS adaptive inverse control is the product of the control relaxation and the the stability gain matrix. A small stability gain matrix makes the controller less sensitive to relaxation selection, and permits faster and more stable vibration reduction, than by choosing the stability gain matrix large and the control relaxation term small. It is shown that the best selections of the stability gain matrix elements and the amount of control relaxation is basically a compromise between slow, stable convergence and fast convergence with increased possibility of unstable identification. In the simulation studies, the LMS adaptive inverse control algorithm is shown to be capable of adapting the inverse (controller) matrix to track changes in the flight conditions. The algorithm converges quickly for moderate disturbances, while taking longer for larger disturbances. Perfect knowledge of the inverse matrix is not required for good control of the N/Rev vibration. However it is shown that measurement noise will prevent the LMS adaptive inverse control technique from controlling the vibration, unless the signal averaging method presented is incorporated into the algorithm.

Jacklin, Stephen A.↗

Operations for Learning with Graphical Models

This paper is a multidisciplinary review of empirical, statistical learning from a graphical model perspective. Well-known examples of graphical models include Bayesian net- works, directed graphs representing a Markov chain, and undirected networks representing a Markov field. These graphical models are extended to model data analysis and empirical learning using the notation of plates. Graphical operations for simplifying and manipulating a problem are provided including decomposition, differentiation, and the manipulation of probability models from the exponential family. These operations adapt existing techniques from statistics and automatic differentiation to graphs. Two standard algorithm schemes for learning are reviewed in a graphical framework: Gibbs sampling and the expectation maximization algorithm. Some algorithms are developed in this graphical framework including a generalized version of linear regression, techniques for feed-forward networks, and learning Gaussian and discrete Bayesian networks from data. The paper concludes by sketching some implications for data analysis and summarizing some popular algorithms that fall within the framework presented. The main original contributions here are the decomposition techniques and the demonstration that graphical models provide a framework for understanding and developing complex learning algorithms.

Buntine, Wray L.↗

Vergence-dependent adaptation of the vestibulo-ocular reflex

The gain of the vestibulo-ocular reflex (VOR) normally depends on the distance between the subject and the visual target, but it remains uncertain whether vergence angle can be linked to changes in VOR gain through a process of context-dependent adaptation. In this study, we examined this question with an adaptation paradigm that modified the normal relationship between vergence angle and retinal image motion. Subjects were rotated sinusoidally while they viewed an optokinetic (OKN) stimulus through either diverging or converging prisms. In three subjects the diverging prisms were worn while the OKN stimulus moved out of phase with the head, and the converging prisms were worn when the OKN stimulus moved in-phase with the head. The relationship between the vergence angle and OKN stimulus was reversed in the fourth subject. After 2 h of training, the VOR gain at the two vergence angles changed significantly in all of the subjects, evidenced by the two different VOR gains that could be immediately accessed by switching between the diverged and converged conditions. The results demonstrate that subjects can learn to use vergence angle as the contextual cue that retrieves adaptive changes in the angular VOR.

NASA Discipline Developmental Biology↗

Magellan mission to Venus - Radar system design and operational challenges

The Magellan radar mission to Venus was launched in May 1989 and placed into orbit around Venus in August 1990. After several weeks of check-out including two complete signal loss events from the spacecraft, the mission began collecting data from the radar instrument in the three modes of synthetic aperture, altimetry, and passive radiometry. The author presents an overview of the mission and shows some results, concentrating on the engineering aspects of the results. He also describes how the many challenges were overcome and the system was adapted to the realities of Venus and the radar system that is being used to map the planet. It is concluded that this mission has presented many lessons learned about not only the design of an imaging and altimetric radar system but also the adaptation of this design to the mission operational constraints.

Johnson, William T. K.↗

Explaining and predicting human behavior and social dynamics in simulated virtual worlds: reproducibility, generalizability, and robustness of causal discovery methods

Ground Truth program was designed to evaluate social science modeling approaches using simulation test beds with ground truth intentionally and systematically embedded to understand and model complex Human Domain systems and their dynamics Lazer et al. (Science 369:1060–1062, 2020). Our multidisciplinary team of data scientists, statisticians, experts in Artificial Intelligence (AI) and visual analytics had a unique role on the program to investigate accuracy, reproducibility, generalizability, and robustness of the state-of-the-art (SOTA) causal structure learning approaches applied to fully observed and sampled simulated data across virtual worlds. In addition, we analyzed the feasibility of using machine learning models to predict future social behavior with and without causal knowledge explicitly embedded. In this paper, we first present our causal modeling approach to discover the causal structure of four virtual worlds produced by the simulation teams—Urban Life, Financial Governance, Disaster and Geopolitical Conflict. Our approach adapts the state-of-the-art causal discovery (including ensemble models), machine learning, data analytics, and visualization techniques to allow a human-machine team to reverse-engineer the true causal relations from sampled and fully observed data. We next present our reproducibility analysis of two research methods team’s performance using a range of causal discovery models applied to both sampled and fully observed data, and analyze their effectiveness and limitations. We further investigate the generalizability and robustness to sampling of the SOTA causal discovery approaches on additional simulated datasets with known ground truth. Our results reveal the limitations of existing causal modeling approaches when applied to large-scale, noisy, high-dimensional data with unobserved variables and unknown relationships between them. We show that the SOTA causal models explored in our experiments are not designed to take advantage from vasts amounts of data and have difficulty recovering ground truth when latent confounders are present; they do not generalize well across simulation scenarios and are not robust to sampling; they are vulnerable to data and modeling assumptions, and therefore, the results are hard to reproduce. Finally, when we outline lessons learned and provide recommendations to improve models for causal discovery and prediction of human social behavior from observational data, we highlight the importance of learning data to knowledge representations or transformations to improve causal discovery and describe the benefit of causal feature selection for predictive and prescriptive modeling.

97 MATHEMATICS AND COMPUTING↗

Research on a Pulmonary Nodule Segmentation Method Combining Fast Self-Adaptive FCM and Classification

The key problem of computer-aided diagnosis (CAD) of lung cancer is to segment pathologically changed tissues fast and accurately. As pulmonary nodules are potential manifestation of lung cancer, we propose a fast and self-adaptive pulmonary nodules segmentation method based on a combination of FCM clustering and classification learning. The enhanced spatial function considers contributions to fuzzy membership from both the grayscale similarity between central pixels and single neighboring pixels and the spatial similarity between central pixels and neighborhood and improves effectively the convergence rate and self-adaptivity of the algorithm. Experimental results show that the proposed method can achieve more accurate segmentation of vascular adhesion, pleural adhesion, and ground glass opacity (GGO) pulmonary nodules than other typical algorithms.

59 BASIC BIOLOGICAL SCIENCES↗

Combining machine-learned and empirical force fields with the parareal algorithm: application to the diffusion of atomistic defects

We numerically investigate an adaptive version of the parareal algorithm in the context of molecular dynamics. This adaptive variant has been originally introduced in [1]. We focus here on test cases of physical interest where the dynamics of the system is modelled by the Langevin equation and is simulated using the molecular dynamics software LAMMPS. In this work, the parareal algorithm uses a family of machine-learning spectral neighbor analysis potentials (SNAP) as fine, reference, potentials and embedded-atom method potentials (EAM) as coarse potentials. We consider a self-interstitial atom in a tungsten lattice and compute the average residence time of the system in metastable states. Our numerical results demonstrate significant computational gains using the adaptive parareal algorithm in comparison to a sequential integration of the Langevin dynamics. We also identify a large regime of numerical parameters for which statistical accuracy is reached without being a consequence of trajectorial accuracy.

36 MATERIALS SCIENCE↗

Reinforcement Learning for Intentional Islanding in Resilient Power Transmission Systems

Intentional islanding is the process of identifying and deliberately decomposing the transmission network to form self-sustained islands from an endangered network during disruptions to improve resilience and security. Most existing intentional islanding models are offline resilience decision tools and hence do not provide outage responses in a timely manner. In this paper, a reinforcement learning (RL) based model for intentional islanding is developed, which offers real-time switching control, online deployability, and adaptability to varying system conditions. The intentional islanding process is formulated as a Markov decision process, where the optimal transmission switching policy is learned using the RL approach. The control policy is learned over an environment that encompasses a Power System Simulator for Engineering (PSS/E) model of the transmission network, facilitated by an interface to the standard openAI Gym framework. The proposed RL-based methodology aims to form stable and self-sustainable islands by ensuring voltage stability while reducing the power mismatch in the formed islands. A proximal policy optimization algorithm is designed, which is suitable for controlling the on/off status of the switches with multi-layer perceptron as value and actor networks. The effectiveness of the proposed framework in the self-recovery of the grid by island formation is applied on the modified IEEE 39-bus test network and validated by dynamic simulations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

SpaceDock: A Performance Task Platform for Spaceflight Operations

Preliminary evidence during both short- and long-duration spaceflight indicates that perceptual-motor coordination changes occur and persist in-flight. However, there is presently no in-flight method for evaluating astronaut performance on mission-critical tasks such as docking. We present a portable platform we have developed for attempting and evaluating docking, and describe the results of a pilot study wherein flight novices learned the docking task. Methods: A dual-joystick, six degrees of freedom platform-called SpaceDock-was developed to enable portable, adaptable performance testing in a spaceflight operations setting. Upon this platform, a simplified docking task was created, involving a constant rate of approach towards a docking target and requiring the user to correct translation in two dimensions and attitude orientation along one dimension (either pitch or roll). Ten flight naive subjects performed the task over a 45 min period and all joystick inputs and timings were collected, from which we could successfully reconstruct travel paths, input profiles and relative target displacements. Results: Subjects exhibited significant improvements in docking over the course of the experiment. Learning to compensate for roll-alterations was robust, whereas compensation for pitch-alterations was not in evidence in this population and relatively short training period. Conclusion: The SpaceDock platform can provide a novel method for training and testing subjects, on a spaceflight-relevant task, and can be used to examine behavioral learning, strategy use, and has been adapted for use in brain imaging experiments.

Marshburn, Thomas H.↗

Automation of Laser Plasma Focused Ion Beam Microscopy for Next-Gen Energy Materials

Automation can revolutionize the use of ultrafast laser ablation and plasma-focused ion beam (PFIB) techniques for high-throughput, reproducible cross-sectioning and various sample preparation in materials characterization. As these methods become essential for analyzing complex energy materials and next-generation devices, efficient, standardized workflows are needed to minimize variability and enhance precision. This work highlights our advancements in developing automated processes for sample preparation that integrates machine learning, workflow optimization, and large-scale data acquisition to improve efficiency and scalability in applications such as electrolyzers, photovoltaic cells, and microelectronics. To streamline cross-sectioning and lamella fabrication, we have implemented fully automated workflows that standardize laser ablation and PFIB milling sequences. These workflows incorporate pre-programmed protocols for material removal, alignment, and thinning, reducing user intervention and ensuring consistency across different sample types. Machine learning algorithms further enhance automation by predicting optimal milling strategies and adapting parameters based on material properties and sectioning requirements. This approach significantly improves throughput while maintaining the structural integrity of prepared samples for high-resolution imaging and analysis, including transmission electron microscopy. Beyond sample preparation, our automation platform enables the acquisition of large, high-resolution datasets through serial sectioning, image alignment, and 3D reconstruction. These automated routines facilitate multi-scale characterization, capturing structural and compositional details from the nanoscale to the device level. By reducing variability and increasing efficiency, our automated approach enhances defect analysis, failure diagnostics, and process optimization, accelerating advancements in materials research and device engineering.

36 MATERIALS SCIENCE↗

Incorporation of Physics Phenomenology into an Adaptive Algorithm Framework (Final Report)

We attempt to incorporate prior physics knowledge into a machine learning architecture at an applied application level (empirical) as opposed to the level of fundamental physics (first principles). The purpose of this work is to allow for the application of methods of physics-informed machine learning to a broad range of national security problems, while enhancing the trust in machine-learned models by decreasing the “black box” nature of such methods.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Gaming the beamlines—employing reinforcement learning to maximize scientific outcomes at large-scale user facilities

Abstract Beamline experiments at central facilities are increasingly demanding of remote, high-throughput, and adaptive operation conditions. To accommodate such needs, new approaches must be developed that enable on-the-fly decision making for data intensive challenges. Reinforcement learning (RL) is a domain of AI that holds the potential to enable autonomous operations in a feedback loop between beamline experiments and trained agents. Here, we outline the advanced data acquisition and control software of the Bluesky suite, and demonstrate its functionality with a canonical RL problem: cartpole. We then extend these methods to efficient use of beamline resources by using RL to develop an optimal measurement strategy for samples with different scattering characteristics. The RL agents converge on the empirically optimal policy when under-constrained with time. When resource limited, the agents outperform a naive or sequential measurement strategy, often by a factor of 100%. We interface these methods directly with the data storage and provenance technologies at the National Synchrotron Light Source II, thus demonstrating the potential for RL to increase the scientific output of beamlines, and layout the framework for how to achieve this impact.

36 MATERIALS SCIENCE↗

SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches, particularly Graph Neural Networks (GNNs) for materials science. These methods have emerged as powerful tools for high-throughput prediction of material properties, offering a compelling enhancement and alternative to traditional first-principles calculations. While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy, such approaches often lack physical interpretability and insights into materials behavior. Here, we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression (SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression. Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintaining O(n) computational scaling. The integrated SR module subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships, achieving 23 × acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input. This work suggests a new framework in computational materials science, bridging the gap between predictive accuracy and physical interpretability, offering valuable physical insights into material behavior.

36 MATERIALS SCIENCE↗

YOLO for Radio Frequency Signal Classification

Radio frequency signal classification plays a pivotal role in various applications, including spectrum management, wireless security, and cognitive radio. Extant signal classification methods require significant data throughput and are not multilabel. We propose a novel approach to radio frequency signal classification by leveraging the You Only Look Once (YOLO) object detection method. YOLO is a state-of-the-art deep learning model renowned for its real-time object detection capabilities in computer vision applications. We adapt YOLO for signal classification to enable the automatic and efficient identification of various signal types within a power spectral density image. Index Terms—radio-frequency analysis, object detection, neural networks, machine learning, deep learning.

42 ENGINEERING↗

SoMoGym: A Toolkit for Developing and Evaluating Controllers and Reinforcement Learning Algorithms for Soft Robots

Soft robotsoffer a host of benefits over traditional rigid robots, including inherent compliance that lets them passively adapt to variable environments and operate safely around humans and fragile objects. However, that same compliance makes it hard to use model-based methods in planning tasks requiring high precision or complex actuation sequences. Reinforcement learning (RL) can potentially find effective control policies, but training RL using physical soft robots is often infeasible, and training using simulations has had a high barrier to adoption. To accelerate research in control and RL for soft robotic systems, we introduce SoMoGym ( So ft Mo tion Gym ), a software toolkit that facilitates training and evaluating controllers for continuum robots. SoMoGym provides a set of benchmark tasks in which soft robots interact with various objects and environments. It allows evaluation of performance on these tasks for controllers of interest, and enables the use of RL to generate new controllers. Custom environments and robots can likewise be added easily. We provide and evaluate baseline RL policies for each of the benchmark tasks. These results show that SoMoGym enables the use of RL for continuum robots, a class of robots not covered by existing benchmarks, giving them the capability to autonomously solve tasks that were previously unattainable.

Moritz A. Graule↗

Securing the Clean Energy Transition with Cyber-Informed Engineering

The Bipartisan Infrastructure Law kick-started a surge in clean energy investments in the United States. Securing these systems and their supporting infrastructure from the outset is imperative, starting from the conceptual design and continuing through the entire engineering lifecycle. Cyber-Informed Engineering is an ideal approach to seamlessly integrate the necessary advanced control capabilities and adaptive protection systems, especially considering the trend towards cloud-based infrastructure and process controls. Learn more about CIE at https://www.energy.gov/ceser/articles/cyber-informed-engineering-bridge-between-cyber-and-critical-infrastructure-securing.

14 SOLAR ENERGY↗

Monte Carlo Tree Search for Integrated Planning, Learning, and Execution in Nondeterministic Python

We present a novel use of Monte Carlo Tree Search (MCTS),adapted to explore a search space produced by the choice points embedded in Python code. The choice points are non-deterministic assignment statements and subroutine calls. We present MCTS extensions required for doing tree search in this context which includes control constructs like hierarchical decomposition (subroutine calls), iterative while loops and conditional statements. We demonstrate how the system works in a simulated rideshare scenario in an urban setting, and present preliminary experiments as a proof of concept.

Automatic planning↗