SEARCH · Search NASA

Results for “Learning control”

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 1,027 records · Page 57

All sources NASA NTRS DOE OSTI

NASA NTRS2014

Biomechanics of the Treadmill Locomotion on the International Space Station

Exercise prescriptions completed by International Space Station (ISS) crewmembers are typically based upon evidence obtained during ground-based investigations, with the assumption that the results of long-term training in weightlessness will be similar to that attained in normal gravity. Coupled with this supposition are the assumptions that exercise motions and external loading are also similar between gravitational environments. Normal control of locomotion is dependent upon learning patterns of muscular activation and requires continual monitoring of internal and external sensory input [1]. Internal sensory input includes signals that may be dependent on or independent of gravity. Bernstein hypothesized that movement strategy planning and execution must include the consideration of segmental weights and inertia [2]. Studies of arm movements in microgravity showed that individuals tend to make errors but that compensation strategies result in adaptations, suggesting that control mechanisms must include peripheral information [3-5]. To date, however, there have been no studies examining a gross motor activity such as running in weightlessness other than using microgravity analogs [6-8]. The objective of this evaluation was to collect biomechanical data from crewmembers during treadmill exercise before and during flight. The goal was to determine locomotive biomechanics similarities and differences between normal and weightless environments. The data will be used to optimize future exercise prescriptions. This project addresses the Critical Path Roadmap risks 1 (Accelerated Bone Loss and Fracture Risk) and 11 (Reduced Muscle Mass, Strength, and Endurance). Data were collected from 7 crewmembers before flight and during their ISS missions. Before launch, crewmembers performed a single data collection session at the NASA Johnson Space Center. Three-dimensional motion capture data were collected for 30 s at speeds ranging from 1.5 to 9.5 mph in 0.5 mph increments with a 12-camera system. During flight, each crewmember completed up to 6 data collection sessions spread across their missions, performing their normal exercise prescription for the test day, resulting in varying data collection protocols between sessions. Motion data were collected by a single HD video camera positioned to view the crewmembers' left side, and tape markers were placed on their feet, legs, and neck on specific landmarks. Before data collection, the crewmembers calibrated the video camera. Video data were collected during the entire exercise session at 30 Hz. Kinematic data were used to determine left leg hip, knee, and ankle range of motion and contact time, flight time, and stride time for each stride. 129 trials in weightlessness were analyzed. Mean time-normalized strides were found for each trial, and cross-correlation procedures were used to examine the strength and direction of relationships between segment movement pattern timing in each gravitational condition. Cross-correlation analyses between gravitational conditions revealed highly consistent movement patterns at each joint. Peak correlation coefficients occurred at 0% phase, indicating there were no lags in movement timing. Joint ranges of motion were similar between gravitational conditions, with some slight differences between subjects. Motion patterns in weightlessness were highly consistent at a given speed with those occurring in 1G, indicating that despite differing sensory input, subjects maintain running kinematics. The data suggest that individuals are capable of compensating for loss of limb weight when creating movement strategies. These results have important implications for creating training programs for use in weightlessness as practitioners can have greater confidence in running motions transferring across gravitational environments. Furthermore, these results have implications for use by researchers investigating motor control mechanisms and investigating hypotheses related to movement strategies when using sensory input that is dependent upon gravity.

DeWitt, John↗

NASA NTRSDate not supplied

A Machine Learning Model for Solar Sail Shape Reconstruction Using Flight Data

Solar sail deformation leads to disturbance torques from solar radiation pressure, driving performance requirements for momentum management systems. For the Solar Cruiser technology demonstrator mission, we have developed a model leveraging neural network-based machine learning to derive sail shape characteristics. The model uses torque and attitude telemetry simulated from a reduced-order tensor model of the deformed sail mesh over a characterization sequence. The machine learning model predicts sail boom deflection with comparable accuracy to that of an onboard context camera. This model can discover sail shape with no additional mass or data downlink requirements, allowing for validation of sail force modeling assumptions using in flight data. The results from the project hold promise for the further implementation of machine learning techniques in solar sail telemetry analysis and control.

solar sail↗

NASA NTRSDate not supplied

A Machine Learning Model for Solar Sail Shape Reconstruction Using Flight Data

solar sail↗

DOE OSTI2022

Optimal Coordination of Distributed Energy Resources Using Deep Deterministic Policy Gradient

Recent studies showed that reinforcement learning (RL) is a promising approach for coordination and control of distributed energy resources (DER) under uncertainties. Many existing RL approaches, including Q-learning and approximate dynamic programming, are based on lookup table methods, which become inefficient when the problem size is large and infeasible when continuous states and actions are involved. In addition, when modeling battery energy storage system (BESS), the loss of life is not reasonably considered into the decision-making process. This paper proposes an innovative deep RL method for DER coordination considering BESS degradation. The proposed deep RL is designed based on an adaptive actor-critic architecture and employs an off-policy deterministic policy gradient method for determining the dispatch operation that minimizes the operation cost and BESS life loss. Case studies were performed to validate the proposed method and demonstrate the effects of incorporating degradation models into control design.

Das, Avijit↗

DOE OSTI2024

"Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test"

In this article, we explore the technical details of the reinforcement learning (RL) algorithms that were deployed in the largest field test of automated vehicles designed to smooth traffic flow in history as of 2023, uncovering the challenges and breakthroughs that come with developing RL controllers for automated vehicles. We delve into the fundamental concepts behind RL algorithms and their application in the context of self-driving cars, discussing the developmental process from simulation to deployment in detail, from designing simulators to reward function shaping. We present the results in both simulation and deployment, discussing the flow-smoothing benefits of the RL controller. From understanding the basics of Markov decision processes to exploring advanced techniques such as deep RL, our article offers a comprehensive overview and deep dive of the theoretical foundations and practical implementations driving this rapidly evolving field. We also showcase real-world case studies and alternative research projects that highlight the impact of RL controllers in revolutionizing autonomous driving. From tackling complex urban environments to dealing with unpredictable traffic scenarios, these intelligent controllers are pushing the boundaries of what automated vehicles can achieve. Furthermore, we examine the safety considerations and hardware-focused technical details surrounding deployment of RL controllers into automated vehicles. As these algorithms learn and evolve through interactions with the environment, ensuring their behavior aligns with safety standards becomes crucial. We explore the methodologies and frameworks being developed to address these challenges, emphasizing the importance of building reliable control systems for automated vehicles.

Jang, Kathy↗

DOE OSTI2025

Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids

As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2019

Model predictive control of phthalic anhydride synthesis in a fixed-bed catalytic reactor via machine learning modeling

Not Available

Wu, Zhe↗

DOE OSTI2023

Machine learning-based ethylene and carbon monoxide estimation, real-time optimization, and multivariable feedback control of an experimental electrochemical reactor

Electrochemical reduction of CO 2 gas is a novel CO 2 utilization technique that has the potential to mitigate the global climate crisis caused by anthropogenic CO 2 emissions, and enable the large-scale storage of energy generated from renewable sources in the form of carbon-based chemicals and fuels. However, due to the complexity of the electrochemical reactions, the explicit first-principles models for CO2 reduction are not available yet, and there has been a limited effort to develop process modeling, optimization and control of CO 2 electrochemical reactors. To this end, a rotating cylinder electrode (RCE) reactor has been constructed at UCLA to understand the mass transfer and reaction kinetics effects separately on the productivity. In the RCE reactor, the applied potential strongly influences the reaction energetics and the electrode rotation speed affects the hydrodynamic boundary layer and modifies the film mass transfer coefficient, which involves convective and diffusive transport. Further, the present work aims to develop a multi-input multi-output (MIMO) control scheme for the RCE reactor that integrates techniques from artificial and recurrent neural network modeling, nonlinear optimization, and process controller design. Specifically, production rates of two products from the experimental reactor, ethylene and carbon monoxide, are controlled by manipulating two inputs, applied potential and catalyst rotation speed. Process dynamics and controllability are analyzed, a feedback control strategy is designed and the controllers are tuned accordingly. The experimental electrochemical cell is employed to gather data for process modeling and implement the multivariable control system. Finally, the experimental results are presented which demonstrate excellent closed-loop performance by the control system and regulation of the outputs at three different set-points including an economically-optimal set-point.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Deep Multitask Learning Models for Radiation Estimation at High Energy Accelerator Facility

Controlling the dose of radiation exposure in potential radioactive facilities is critical for ensuring the safety of staff and the public. Here, in this paper, we developed machine learning models to estimate radiation exposure efficiently at the Thomas Jefferson National Accelerator Facility (JLab), aiming to enhance safety in both accelerator facilities and public areas. Multiple sensors were deployed around the three experimental halls at JLab. Data on single-beam currents, energy levels, and radiation values at the sensor locations were collected during accelerator operation. We proposed a multi-task learning model for radiation estimation, utilizing either one-dimensional convolutional neural networks (1-D CNNs) or long short-term memory networks (LSTMs) as the backbone. The proposed model was trained to simultaneously estimate radiation levels at the sensor locations. Experimental results demonstrated that the proposed model with LSTM backbone achieved the best estimation performance, with an average R 2 score of 0.7557 for estimation within the same year and 0.7157 for estimation across different years. These results significantly surpassed those of competing models.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Cutting the Deployment Costs of Physics-Based MPC in Buildings by Simulation-Based Imitation Learning

It has been shown that model predictive control (MPC) is a promising solution for energy-efficient building operations. However, the deployment of MPC in a large portion of the building stock has not been possible partially because of high installation costs. Every building is unique and requires a tailored MPC solution. The best performing solutions are often based on physics-based modeling, which is, however, computationally expensive and requires dedicated software. A promising direction that tackles this problem is to train a neural network-based optimal control policy to imitate the behavior of physics-based MPC from the simulation data generated offline. The neural networks give control actions that closely approximate those produced by physics-based MPC, but with a fraction of the computational and memory requirements and without the need for licensed software. The main advantage of the proposed approach stems from simple evaluation at execution time, leading to low computational footprints and easy deployment on embedded HW platforms. In the case study, we present the energy savings potential of physics-based MPC applied to an office building in Belgium. We demonstrate how neural network approximators can be used to cut the implementation and maintenance costs of MPC deployment without compromising performance. We also critically assess the presented approach by pointing out the remaining challenges and open research questions.

Drgona, Jan↗

NASA NTRS2024

Shape Servoing of Deformable Objects Using Model Estimation and Barrier Lyapunov Function

An adaptive shape servoing control method is presented in this article to manipulate a deformable object into a desired shape in 3-D. A finite-point-based representation of the deformable object is used and the deformation Jacobian matrix is approximated using Fourier series basis functions. The unknown parameters of the deformation Jacobian are learned by using the velocity applied to a control point on the object and corresponding change of positions of the points describing the entire object. An integral concurrent learning (ICL)-based parameter update law is designed along with a constrained controller to satisfy the state constraints on the motion of the control point using Barrier Lyapunov function analysis. ICL-based parameter update law uses data history of velocity and corresponding positions of the points along with their current values. An efficient algorithm to update the history stack using singular value maximization is proposed based on the structure of the regressor matrix. Simulations using a physical simulator and experiments using a robot platform are performed to validate the performance of the proposed controller on two different deformable objects.

Vrithik Raj Guthikonda↗

DOE OSTI2024

The ReSWARM microgravity flight experiments: Planning, control, and model estimation for on‐orbit close proximity operations

Abstract On‐orbit close proximity operations involve robotic spacecraft maneuvering and making decisions for a growing number of mission scenarios demanding autonomy, including on‐orbit assembly, repair, and astronaut assistance. Of these scenarios, on‐orbit assembly is an enabling technology that will allow large space structures to be built in situ, using smaller building block modules. However, like many of these scenarios, robotic on‐orbit assembly involves several technical hurdles, such as changing system models. For instance, grappled modules moved by a free‐flying “assembler” robot can cause significant changes in the combined system inertia, which have cascading impacts on motion planning and control portions of the autonomy stack. Further, on‐orbit assembly and other scenarios require collision‐avoiding motion planning, particularly when operating in a “construction site” scenario of multiple assembler robots and structures. Multiple key technologies that address these complicating factors for autonomous microgravity close proximity operations are detailed in this work, in particular: (1) application of global long‐horizon planning, accomplished using offline and online sampling‐based planner options that consider the system dynamics; (2) adaptation of the recently proposed RATTLE information‐aware planning framework for on‐orbit reconfiguration model learning; and (3) connection with robust control tools to provide low‐level control robustness using current system knowledge. These approaches were demonstrated for an autonomous on‐orbit assembly use case by the RElative Satellite sWarming and Robotic Maneuvering (ReSWARM) experiments using NASA's Astrobee robots on the International Space Station. Results of the ReSWARM experiments are provided along with significant operational and implementation detail discussing the practicalities of hardware implementation and unique aspects of working with the Astrobee free‐flyer robots in microgravity. ReSWARM provides a base set of planning and control tools for robotic close proximity operations, demonstrates them in microgravity, and outlines some of the important hardware aspects that future autonomous free‐flyers will need to consider.

Robotics↗

DOE OSTI2020

Optimization-based control using input convex neural networks

Input convex neural networks (ICNNs) are a family of deep learning models where the outputs are constructed to be convex functions of the inputs. By parameterizing system models using ICNNs, optimization-based control problems can be solved as convex optimization problems, leading to improved performance and robustness. This work proposes a novel framework where the control objective function and constraints are modelled using ICNNs. A case study of optimization-based control with output constraints is conducted on a process with input multiplicity and nonminimum phase behavior. The simulation results demonstrate improved economic yield compared with normal neural networks. Additionally, the input convexity formulation is compared with simple regularization techniques, and unique benefits such as improved data efficiency and robustness of the proposed formulation are shown. Finally, by explicitly incorporating prior knowledge about convexity, this framework provides a good balance between the universal approximation power of deep learning and computational feasibility required by control.

42 ENGINEERING↗

NASA NTRS2010

Lessons Learned in Building the Ares Projects

Since being established in 2005, the Ares Projects at Marshall Space Flight Center have been making steady progress designing, building, testing, and flying the next generation of exploration launch vehicles. Ares is committed to rebuilding crucial capabilities from the Apollo era that made the first human flights to the Moon possible, as well as incorporating the latest in computer technology and changes in management philosophy. One example of an Apollo-era practice has been giving NASA overall authority over vehicle integration activities, giving civil service engineers hands-on experience in developing rocket hardware. This knowledge and experience help make the agency a "smart buyer" of products and services. More modern practices have been added to the management tool belt to improve efficiency, cost effectiveness, and institutional knowledge, including knowledge management/capture to gain better insight into design and decision making; earned value management, where Ares won a NASA award for its practice and implementation; designing for operability; and Lean Six Sigma applications to identify and eliminate wasted time and effort. While it is important to learn technical lessons like how to fly and control unique rockets like the Ares I-X flight test vehicle, the Ares management team also has been learning important lessons about how to manage large, long-term projects.

Sumrall, John Phil↗

DOE OSTI2024

Observational benchmarks inform representation of soil organic carbon dynamics in land surface models

Abstract. Representing soil organic carbon (SOC) dynamics in Earth system models (ESMs) is a key source of uncertainty in predicting carbon–climate feedbacks. Machine learning models can help identify dominant environmental controllers and establish their functional relationships with SOC stocks. The resulting knowledge can be integrated into ESMs to reduce uncertainty and improve predictions of SOC dynamics over space and time. In this study, we used a large number of SOC field observations (n=54 000), geospatial datasets of environmental factors (n=46), and two machine learning approaches (namely random forest, RF, and generalized additive modeling, GAM) to (1) identify dominant environmental controllers of global and biome-specific SOC stocks, (2) derive functional relationships between environmental controllers and SOC stocks, and (3) compare the identified environmental controllers and predictive relationships with those in models used in Phase 6 of the Coupled Model Intercomparison Project (CMIP6). Our results showed that the diurnal temperature, drought index, cation exchange capacity, and precipitation were important observed environmental predictors of global SOC stocks. While the RF model identified 14 environmental factors that describe climatic, vegetation, and edaphic conditions as important predictors of global SOC stocks (R2=0.61, RMSE = 0.46 kg m−2), current ESMs oversimplify the relationships between environmental factors and SOC, with precipitation, temperature, and net primary productivity explaining > 96 % of the variability in ESM-modeled SOC stocks. Further, our study revealed notable disparities among the functional relationships between environmental factors and SOC stocks simulated by ESMs compared with observed relationships. To improve SOC representations in ESMs, it is imperative to incorporate additional environmental controls, such as the cation exchange capacity, and refine the functional relationships to align more closely with observations.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Protecting and Defending against Autonomous Control Systems and Digital Twin Cyber Attacks: Response Strategy for Hyperparameter attacks of Digital Twin Machine Learning Models in Nuclear Power Plants (Final)

Navigating through the complex tapestry of technological advancements, "Response Strategy for Hyperparameter attacks of Digital Twin Machine Learning Model in Nuclear Power Plants" stands at the intersection of cybersecurity and nuclear power plant operations, embarking on a journey through the intricacies of securing digital twins against malicious cyber activities. As nuclear power plants progressively integrate digital twin technology and machine learning models to optimize operations and ensure system reliability, they inadvertently expose themselves to a new spectrum of vulnerabilities, notably in the realm of hyperparameter attacks. Hyperparameters, integral in machine learning model tuning and optimal performance of digital twins, have emerged as a target for adversaries aiming to destabilize the predictive capabilities and therefore, the operational accuracy of these digital entities within critical infrastructures like nuclear plants. This paper, therefore, meticulously threads the needle through the development of a robust response strategy, poised to shield these digital reflections against calculated hyperparameter manipulations, ensuring that the digital twin can effectively and securely function as a reliable proxy for its physical counterpart. The ensuing sections delve into the orchestrated maelstrom of multi-rate time-changing intelligent coordinated hyperparameter attacks and the implementation of event-triggered predictive control, laying down a structured, predictive, and responsive framework that safeguards the nexus where the digital and physical realms of nuclear power plants coalesce. The operational integrity of digital twins in nuclear power plants depends critically on the security of machine learning hyperparameters. This study makes two different contributions. First, a decision-based idea known as a multi-rate time changing intelligent coordinated hyperparameter attack is put forth. In this attack, many hyperparameters are repeatedly changed using both random and intelligent optimal techniques by the attacker. These assaults introduce varied rates at different attack steps, compromise various amounts of hyperparameters, and improve stealth and flexibility. Second, a technique is developed for event triggered predictive control to rapidly respond to potential hyperparameter attacks. This control integrates a sliding window framework, retaining a history of previous data points and employing linear regression to predict the next data point from the current dataset. The control gain K is determined using the Lyapunov-Krasovskii method, and subsequently, an action is developed. Finally, the outcome of the simulation demonstrates the viability of the proposed method for defending nuclear power plant digital twins from hyperparameter attacks.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

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 NTRS2006

Robust Coordination for Large Sets of Simple Rovers

The ability to coordinate sets of rovers in an unknown environment is critical to the long-term success of many of NASA;s exploration missions. Such coordination policies must have the ability to adapt in unmodeled or partially modeled domains and must be robust against environmental noise and rover failures. In addition such coordination policies must accommodate a large number of rovers, without excessive and burdensome hand-tuning. In this paper we present a distributed coordination method that addresses these issues in the domain of controlling a set of simple rovers. The application of these methods allows reliable and efficient robotic exploration in dangerous, dynamic, and previously unexplored domains. Most control policies for space missions are directly programmed by engineers or created through the use of planning tools, and are appropriate for single rover missions or missions requiring the coordination of a small number of rovers. Such methods typically require significant amounts of domain knowledge, and are difficult to scale to large numbers of rovers. The method described in this article aims to address cases where a large number of rovers need to coordinate to solve a complex time dependent problem in a noisy environment. In this approach, each rover decomposes a global utility, representing the overall goal of the system, into rover-specific utilities that properly assign credit to the rover s actions. Each rover then has the responsibility to create a control policy that maximizes its own rover-specific utility. We show a method of creating rover-utilities that are "aligned" with the global utility, such that when the rovers maximize their own utility, they also maximize the global utility. In addition we show that our method creates rover-utilities that allow the rovers to create their control policies quickly and reliably. Our distributed learning method allows large sets rovers be used unmodeled domains, while providing robustness against rover failures and changing environments. In experimental simulations we show that our method scales well with large numbers of rovers in addition to being robust against noisy sensor inputs and noisy servo control. The results show that our method is able to scale to large numbers of rovers and achieves up to 400% performance improvement over standard machine learning methods.

Tumer, Kagan↗