Search NASA⌕ Search

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.

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

At least 1,045 records · Page 58
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Toward Real Time Neural Net Flight Controllers

NASA Ames Research Center has an ongoing program in neural network control technology targeted toward real time flight demonstrations using a modified F-15 which permits direct inner loop control of actuators, rapid switching between alternative control designs, and substitutable processors. An important part of this program is the ACTIVE flight project which is examining the feasibility of using neural networks in the design, control, and system identification of new aircraft prototypes. This paper discusses two research applications initiated with this objective in mind: utilization of neural networks for wind tunnel aircraft model identification and rapid learning algorithms for on line reconfiguration and control. The first application involves the identification of aerodynamic flight characteristics from analysis of wind tunnel test data. This identification is important in the early stages of aircraft design because complete specification of control architecture's may not be possible even though concept models at varying scales are available for aerodynamic wind tunnel testing. Testing of this type is often a long and expensive process involving measurement of aircraft lift, drag, and moment of inertia at varying angles of attack and control surface configurations. This information in turn can be used in the design of the flight control systems by applying the derived lookup tables to generate piece wise linearized controllers. Thus, reduced costs in tunnel test times and the rapid transfer of wind tunnel insights into prototype controllers becomes an important factor in more efficient generation and testing of new flight systems. NASA Ames Research Center is successfully applying modular neural networks as one way of anticipating small scale aircraft model performances prior to testing, thus reducing the number of in tunnel test hours and potentially, the number of intermediate scaled models required for estimation of surface flow effects.

Jorgensen, C. C.↗
DOE OSTI2023

DSS-SimPy-RL (Open-DSS and SimPy based Cyber-Physical RL environment) [SWR-23-29]

Recently, numerous data-driven approaches to control an electric grid using machine learning techniques have been investigated. With the advancement of reinforcement learning (RL) based techniques, gradually the conventional optimization based solvers are being replaced with RL approach where there is uncertainty in the environment such as renewable generation or cyber system emulation. However, to train an agent efficiently, it requires numerous interactions with an environment to learn the best policies. There are numerous RL environments for the power systems based on some well-known simulators, similarly there are environment for communication domains. While majority of the cyber emulators are based in an UNIX environment, the power simulators are based in the Windows-based operating system, the generation of cyber-physical mixed domain RL environment has been challenging. Existing co-simulation methods are efficient but resource and time intensive to generate large scale data set for training RL agents. Hence, this software focuses on development and validation of a mixed domain RL environment using Open DSS for the physical side and leverages a discrete event simulator python package, SimPy, for cyber-side emulation which is Operating Systems agnostic. Further utilizing this software co-simulation and training RL agents for re-routing based resilient control for network reconfiguration and volt-var control in power distribution feeder are performed.

Sahu, Abhijeet↗
NASA NTRS1993

Adaptive process control using fuzzy logic and genetic algorithms

Researchers at the U.S. Bureau of Mines have developed adaptive process control systems in which genetic algorithms (GA's) are used to augment fuzzy logic controllers (FLC's). GA's are search algorithms that rapidly locate near-optimum solutions to a wide spectrum of problems by modeling the search procedures of natural genetics. FLC's are rule based systems that efficiently manipulate a problem environment by modeling the 'rule-of-thumb' strategy used in human decision making. Together, GA's and FLC's possess the capabilities necessary to produce powerful, efficient, and robust adaptive control systems. To perform efficiently, such control systems require a control element to manipulate the problem environment, and a learning element to adjust to the changes in the problem environment. Details of an overall adaptive control system are discussed. A specific laboratory acid-base pH system is used to demonstrate the ideas presented.

Karr, C. L.↗
DOE OSTI2020

Value Gradient Learning Approach in Power and Frequency Regulation of Grid-Connected Synchronverters

In this paper, a neural network adaptive critic design (ACD) method based on value gradient learning (VGL) is used to optimally control a grid-connected synchronverter. The main drawback of the traditional synchronverters is their infeasibility to face non-inductive grids. To be able to implement a synchronverter technique in any impedance angle, a neural network-based adaptive controller is used. The advantage of adaptive dynamic programing is its ability to adjust itself when it faces changes and uncertainties in the power system. The proposed VGL consists of two subnetworks: the critic network and the action network. The action network is trained during the operation, and the critic network can be pretrained offline or can be simultaneously trained with the action network. To compare the effectiveness of the traditional synchronverter to the VGL-based synchronverter, the simulation results are provided.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2011

Flight Planning Branch Space Shuttle Lessons Learned

Planning products and procedures that allow the mission flight control teams and the astronaut crews to plan, train and fly every Space Shuttle mission have been developed by the Flight Planning Branch at the NASA Johnson Space Center. As the Space Shuttle Program ends, lessons learned have been collected from each phase of the successful execution of these Shuttle missions. Specific examples of how roles and responsibilities of console positions that develop the crew and vehicle attitude timelines will be discussed, as well as techniques and methods used to solve complex spacecraft and instrument orientation problems. Additionally, the relationships and procedural hurdles experienced through international collaboration have molded operations. These facets will be explored and related to current and future operations with the International Space Station and future vehicles. Along with these important aspects, the evolution of technology and continual improvement of data transfer tools between the shuttle and ground team has also defined specific lessons used in the improving the control teams effectiveness. Methodologies to communicate and transmit messages, images, and files from Mission Control to the Orbiter evolved over several years. These lessons have been vital in shaping the effectiveness of safe and successful mission planning that have been applied to current mission planning work in addition to being incorporated into future space flight planning. The critical lessons from all aspects of previous plan, train, and fly phases of shuttle flight missions are not only documented in this paper, but are also discussed as how they pertain to changes in process and consideration for future space flight planning.

Price, Jennifer B.↗
NASA NTRS2006

Notional Airspace Operations Demonstration Plan

The airspace operations demonstration (AOD) is intended to show that the Access 5 Step 1 functional requirements can be met. The demonstration will occur in two phases. The initial on-range phase will be carried out in restricted airspace to demonstrate the cooperative collision avoidance (CCA) functional requirements and to provide risk-reduction for the AOD by allowing the test team to rehearse some elements of the demonstration mission. The CCA system to be used in these flights is based on Automatic Dependent Surveillance-Broadcast (ADS-B) which is a commercially-available system by which airplanes constantly broadcast their current position and altitude to other aircraft and ground resources over a dedicated radio datalink. The final phase will occur in the national airspace (NAS) and will be the formal demonstration of the remainder of the proposed functional requirements. The general objectives of the AOD are as follows: (1) Demonstrate that the UAS can aviate in the NAS (2) Demonstrate that the UAS can navigate in the NAS (3) Demonstrate that the UAS can communicate with the NAS (4) Demonstrate that the UAS can perform selected collision avoidance functions in the NAS (5) Demonstrate that the UAS can evaluate and avoid weather conflicts in the NAS (6) Demonstrate that the UAS can provide adequate command and control in the NAS In addition to the stated objectives, there are a number of goals for the flight demonstration. The demo can be accomplished successfully without achieving these goals, but these goals are to be used as a guideline for preparing for the mission. The goals are: (1) Mission duration of at least 24 hours (2) Loiter over heavy traffic to evaluate the data block issue identified during the Access 5 Airspace Operations Simulations (3) Document the contingency management process and lessons learned (4) Document the coordination process for Ground Control Stations (GCS) handoff (5) Document lessons learned regarding the process of flying in the NAS Preliminary planning for a notional mission to achieve the objectives and goals has been prepared. The planning is intended to serve as a guide for detailed planning of the AOD.

Trongale, Nicholas A.↗
DOE OSTI2020

Improving Primary Frequency Response in Networked Microgrid Operations using Multilayer Perceptron-Driven Reinforcement Learning

Individual microgrids can improve the reliability of power grids during extreme events, and networked microgrids can further improve efficiency through resource sharing and increase the resilience of critical end-use loads. However, networked microgrid operations are subject to large switching transients, which can cause dynamic instability and lead to system collapse. These transients are especially prevalent in microgrids with high penetrations of inverter-connected renewable energy resources, which do not provide the system inertia needed to mitigate the transients. Existing generator controls can be modified to invoke a drop in terminal voltage in response to a frequency deviation, thereby reducing load and improving frequency response. This paper investigates the use of a reinforcement-learning--based controller trained over several switching transient scenarios to modify generator controls during large frequency deviations. Compared to previously used proportional integral controllers, the proposed controller can improve primary frequency response while adapting to changes in system topologies and events.

Radhakrishnan, Nikitha↗
NASA NTRS1998

Feedback Linearized Aircraft Control Using Dynamic Cell Structure

A Dynamic Cell Structure (DCS ) Neural Network was developed which learns a topology representing network (TRN) of F-15 aircraft aerodynamic stability and control derivatives. The network is combined with a feedback linearized tracking controller to produce a robust control architecture capable of handling multiple accident and off-nominal flight scenarios. This paper describes network and its performance for accident scenarios including differential stabilator lock, soft sensor failure, control, stability derivative variation, and turbulence.

Jorgensen, C. C.↗
NASA NTRS2010

Space Flight Resource Management for ISS Operations

Although the astronaut training flow for the International Space Station (ISS) spans 2 years, each astronaut or cosmonaut often spends most of their training alone. Rarely is it operationally feasible for all six ISS crewmembers to train together, even more unlikely that crewmembers can practice living together before launch. Likewise, ISS Flight Controller training spans 18 months of learning to manage incredibly complex systems remotely in plug-and-play ground teams that have little to no exposure to crewmembers before a mission. How then do all of these people quickly become a team - a team that must respond flexibly yet decisively to a variety of situations? The answer implemented at NASA is Space Flight Resource Management (SFRM), the so-called "soft skills" or team performance skills. Based on Crew Resource Management, SFRM was developed first for shuttle astronauts and focused on managing human errors during time-critical events (Rogers, et al. 2002). Given the nature of life on ISS, the scope of SFRM for ISS broadened to include teamwork during prolonged and routine operations (O'Keefe, 2008). The ISS SFRM model resembles a star with one competency for each point: Communication, Cross-Culture, Teamwork, Decision Making, Team Care, Leadership/Followership, Conflict Management, and Situation Awareness. These eight competencies were developed with international participation by the Human Behavior and Performance Training Working Group. Over the last two years, these competencies have been used to build a multi-modal SFRM training flow for astronaut candidates and flight controllers that integrates team performance skills into the practice of technical skills. Preliminary results show trainee skill increases as the flow progresses; and participants find the training invaluable to performing well and staying healthy during ISS operations. Future development of SFRM training will aim to help support indirect handovers as ISS operations evolve further with the retirement of the Space Shuttle Program.

Schmidt, Lacey L.↗
DOE OSTI2023

Seasonal drivers of dissolved oxygen across a tidal creek–marsh interface revealed by machine learning

Abstract Dissolved oxygen (DO) is a key biogeochemical control in coastal systems, and its concentration and drivers vary markedly through time and space. This makes it difficult to accurately represent coastal DO and associated biogeochemical processes in models, limiting our ability to predict how these systems will respond to global change. We obtained high‐frequency (5‐min) in situ measurements of DO collected at three locations across the interface of a tidal creek and coastal marsh in the Pacific Northwest, USA. Random Forest machine learning models quantified the importance of three categories of environmental drivers (Aquatic, Climatic, and Terrestrial) of DO variability across the creek–marsh interface. We selected two 4‐month datasets representing Summer and Winter seasonal periods to test two hypotheses on the dominant drivers of DO at the coastal interface. We found that the Terrestrial driver—characterized by long periods of anaerobic conditions and episodic pulses in DO after floods—was most important during the Winter, whereas the Aquatic driver—characterized by variability over tidal, diel, and lunar cycles—was most important during the Summer. We explored how future climate change scenarios could alter the drivers of DO variability using a cumulative sums driver–response framework. Our results suggest that under climate change, Aquatic and Climatic drivers may increase in importance during the Summer, potentially linked to changing metabolic regimes and sea level, with Terrestrial driver importance potentially increasing during the Winter. Our approach highlights useful methods for understanding the spatiotemporal complexity of oxygen across coastal interfaces and quantifying the relative importance of distinct environmental drivers.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

A Self-Sustained CPS Design for Reliable Wildfire Monitoring

Continuous monitoring of areas nearby the electric grid is critical for preventing and early detection of devastating wildfires. Existing wildfire monitoring systems are intermittent and oblivious to local ambient risk factors, resulting in poor wildfire awareness. Ambient sensor suites deployed near the gridlines can increase the monitoring granularity and detection accuracy. However, these sensors must address two challenging and competing objectives at the same time. First, they must remain powered for years without manual maintenance due to their remote locations. Second, they must provide and transmit reliable information if and when a wildfire starts. The first objective requires aggressive energy savings and ambient energy harvesting, while the second requires continuous operation of a range of sensors. To the best of our knowledge, this paper presents the first self-sustained cyber-physical system that dynamically co-optimizes the wildfire detection accuracy and active time of sensors. The proposed approach employs reinforcement learning to train a policy that controls the sensor operations as a function of the environment (i.e., current sensor readings), harvested energy, and battery level. Here, the proposed cyber-physical system is evaluated extensively using real-life temperature, wind, and solar energy harvesting datasets and an open-source wildfire simulator. In long-term (5 years) evaluations, the proposed framework achieves 89% uptime, which is 46% higher than a carefully tuned heuristic approach. At the same time, it averages a 2-minute initial response time, which is at least 2.5× faster than the same heuristic approach. Furthermore, the policy network consumes 0.6 mJ per day on the TI CC2652R microcontroller using TensorFlow Lite for Micro, which is negligible compared to the daily sensor suite energy consumption.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Foveal vision reduces neural resources in agent-based game learning

Efficient processing of information is crucial for the optimization of neural resources in both biological and artificial visual systems. In this paper, we study the efficiency that may be obtained via the use of a fovea. Using biologically-motivated agents, we study visual information processing, learning, and decision making in a controlled artificial environment, namely the Atari Pong video game. We compare the resources necessary to play Pong between agents with and without a fovea. Our study shows that a fovea can significantly reduce the neural resources, in the form of number of neurons, number of synapses, and number of computations, while at the same time maintaining performance at playing Pong. To our knowledge, this is the first study in which an agent must simultaneously optimize its visual system, along with its decision making and action generation capabilities. That is, the visual system is integral to a complete agent.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

A Generation-Storage Coordination Dispatch Strategy for Power System Based on Causal Reinforcement Learning

In the backdrop of global energy transformation, power systems integrating high proportions of renewable energy sources are facing unprecedented challenges in operational stability and dispatch efficiency. To address these challenges, this study introduces a generation-storage coordination real-time dispatch strategy based on Causal Power System Dynamic Reinforcement Learning (CPSDRL). Diverging from traditional reinforcement learning approaches, CPSDRL innovatively incorporates causal inference within the state prediction model - the crux of model-based reinforcement learning - thereby establishing the Power Causal Dynamic Model (PCDM). Assisted by the prior knowledge of power systems, the model significantly enhances prediction accuracy and reliability through a two-stage training process. Utilizing PCDM, this study further applies a direct policy search algorithm to optimize the real-time dispatch strategy. Experimental results indicate that the proposed method improves the stability of generation-storage coordination real-time dispatch and exhibits competitive advantages in sample efficiency and computational speed, compared to traditional model-based and model-free reinforcement learning algorithms. This method is expected to enhance the practicality and adaptability of causal reinforcement learning techniques in power system scheduling and control.

causal reinforcement learning↗
NASA NTRS2012

Image Mapping and Visual Attention on the Sensory Ego-Sphere

The Sensory Ego-Sphere (SES) is a short-term memory for a robot in the form of an egocentric, tessellated, spherical, sensory-motor map of the robot s locale. Visual attention enables fast alignment of overlapping images without warping or position optimization, since an attentional point (AP) on the composite typically corresponds to one on each of the collocated regions in the images. Such alignment speeds analysis of the multiple images of the area. Compositing and attention were performed two ways and compared: (1) APs were computed directly on the composite and not on the full-resolution images until the time of retrieval; and (2) the attentional operator was applied to all incoming imagery. It was found that although the second method was slower, it produced consistent and, thereby, more useful APs. The SES is an integral part of a control system that will enable a robot to learn new behaviors based on its previous experiences, and that will enable it to recombine its known behaviors in such a way as to solve related, but novel, task problems with apparent creativity. The approach is to combine sensory-motor data association and dimensionality reduction to learn navigation and manipulation tasks as sequences of basic behaviors that can be implemented with a small set of closed-loop controllers. Over time, the aggregate of behaviors and their transition probabilities form a stochastic network. Then given a task, the robot finds a path in the network that leads from its current state to the goal. The SES provides a short-term memory for the cognitive functions of the robot, association of sensory and motor data via spatio-temporal coincidence, direction of the attention of the robot, navigation through spatial localization with respect to known or discovered landmarks, and structured data sharing between the robot and human team members, the individuals in multi-robot teams, or with a C3 center.

Fleming, Katherine Achim↗
DOE OSTI2022

Learning high-dimensional parametric maps via reduced basis adaptive residual networks

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is beneficial to have a compact parametrization in order to ameliorate the ill-posedness of the neural network training problem. By linearly restricting high-dimensional maps to informed reduced bases of the inputs, one can compress high-dimensional maps in a constructive way that can be used to detect appropriate basis ranks, equipped with rigorous error estimates. A scalable neural network learning framework is thus to learn the nonlinear compressed reduced basis mapping. Unlike the reduced basis construction, however, neural network constructions are not guaranteed to reduce errors by adding representation power, making it difficult to achieve good practical performance. Inspired by recent approximation theory that connects ResNets to sequential minimizing flows, we present an adaptive ResNet construction algorithm. This algorithm allows for depth-wise enrichment of the neural network approximation, in a manner that can achieve good practical performance by first training a shallow network and then adapting. We prove universal approximation of the associated neural network class for $L^2_v$ functions on compact sets. Our overall framework allows for constructive means to detect appropriate breadth and depth, and related compact parametrizations of neural networks, significantly reducing the need for architectural hyperparameter tuning. Numerical experiments for parametric PDE problems and a 3D CFD wing design optimization parametric map demonstrate that the proposed methodology can achieve remarkably high accuracy for limited training data, and outperformed other neural network strategies we compared against.

42 ENGINEERING↗
NASA NTRS2011

NASA Flight Planning Branch Space Shuttle Lessons Learned

Planning products and procedures that allowed the mission Flight Control Teams and the Astronaut crews to plan, train and fly every Space Shuttle mission were developed by the Flight Planning Branch at the NASA Johnson Space Center in Houston, Texas. As the Space Shuttle Program came to a close, lessons learned were collected from each phase of the successful execution of these Space Shuttle missions. Specific examples of how roles and responsibilities of console positions that develop the crew and vehicle attitude timelines have been analyzed and will be discussed. Additionally, the relationships and procedural hurdles experienced through international collaboration have molded operations. These facets will be explored and related to current and future operations with the International Space Station and future vehicles. Along with these important aspects, the evolution of technology and continual improvement of data transfer tools between the Space Shuttle and ground team has also defined specific lessons used in improving the control team s effectiveness. Methodologies to communicate and transmit messages, images, and files from the Mission Control Center to the Orbiter evolved over several years. These lessons were vital in shaping the effectiveness of safe and successful mission planning and have been applied to current mission planning work in addition to being incorporated into future space flight planning. The critical lessons from all aspects of previous plan, train, and fly phases of Space Shuttle flight missions are not only documented in this paper, but are also discussed regarding how they pertain to changes in process and consideration for future space flight planning.

Clevenger, Jennifer D.↗
NASA NTRS1995

Locomotion training of legged robots using hybrid machine learning techniques

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Simon, William E.↗
DOE OSTI2026

Autonomous fabrication of tailored defect structures in 2D materials using machine learning-enabled scanning transmission electron microscopy

Materials with tailored quantum properties can be engineered from atomic-scale assembly techniques, but existing methods often lack the agility and accuracy to precisely and intelligently control the manufacturing process. Here, we demonstrate a fully autonomous approach for fabricating atomic-level defects using electron beams in scanning transmission electron microscopy (STEM) that combines advanced machine learning and automated beam control. As a proof of concept, we achieved controlled fabrication of MoS-nanowire (MoS-NW) edge structures by iterative and targeted exposure of MoS 2 monolayer to a focused electron beam to selectively eject sulfur atoms, utilizing high-angle annular dark-field (HAADF) imaging for feedback-controlled monitoring of structural evolution of defects. A machine learning framework combining a random forest model and a convolutional neural network (CNN) was developed to decode the HAADF image and accurately identify atomic positions and species. This atomic-level information was then integrated into an autonomous decision-making platform, which applied predefined fabrication strategies to instruct beam control about atomic sites to be ejected. The selected sites were subsequently exposed to a localized electron beam using an FPGA-controlled scan routine with precise control over beam positioning and duration. While the MoS-NW edge structures produced exhibit promising mechanical and electronic properties, the proposed methods to build the autonomous fabrication framework is material-agnostic and can be extended to other 2D materials for the creation of diverse defect structures and heterostructures beyond Mo S2 .

Engineering↗