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 631 records · Page 35

Hybrid Decompositional Verification for Discovering Failures in Adaptive Flight Control Systems

Adaptive flight control systems hold tremendous promise for maintaining the safety of a damaged aircraft and its passengers. However, most currently proposed adaptive control methodologies rely on online learning neural networks (OLNNs), which necessarily have the property that the controller is changing during the flight. These changes tend to be highly nonlinear, and difficult or impossible to analyze using standard techniques. In this paper, we approach the problem with a variant of compositional verification. The overall system is broken into components. Undesirable behavior is fed backwards through the system. Components which can be solved using formal methods techniques explicitly for the ranges of safe and unsafe input bounds are treated as white box components. The remaining black box components are analyzed with heuristic techniques that try to predict a range of component inputs that may lead to unsafe behavior. The composition of these component inputs throughout the system leads to overall system test vectors that may elucidate the undesirable behavior

Thompson, Sarah↗

Neural Architectures for Control

The cerebellar model articulated controller (CMAC) neural architectures are shown to be viable for the purposes of real-time learning and control. Software tools for the exploration of CMAC performance are developed for three hardware platforms, the MacIntosh, the IBM PC, and the SUN workstation. All algorithm development was done using the C programming language. These software tools were then used to implement an adaptive critic neuro-control design that learns in real-time how to back up a trailer truck. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. CMAC neural architectures are also used in conjunction with a hierarchical planning approach to find collision-free paths over 2-D analog valued obstacle fields. The method constructs a coarse resolution version of the original problem and then finds the corresponding coarse optimal path using multipass dynamic programming. CMAC artificial neural architectures are used to estimate the analog transition costs that dynamic programming requires. The CMAC architectures are trained in real-time for each obstacle field presented. The coarse optimal path is then used as a baseline for the construction of a fine scale optimal path through the original obstacle array. These results are a very good indication of the potential power of the neural architectures in control design. In order to reach as wide an audience as possible, we have run a seminar on neuro-control that has met once per week since 20 May 1991. This seminar has thoroughly discussed the CMAC architecture, relevant portions of classical control, back propagation through time, and adaptive critic designs.

Peterson, James K.↗

Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning

Calculating thermodynamic potentials and observables efficiently and accurately is key for the application of statistical mechanics simulations to materials science. However, naive Monte Carlo approaches, on which such calculations are often dependent, struggle to scale to complex materials in many state-of-the-art disciplines such as the design of high entropy alloys or multi-component catalysts. To address this issue, we adapt sampling tools built upon machine learning-based generative modeling to the materials space by transforming them into the semi-grand canonical ensemble. Furthermore, we show that the resulting models are transferable across wide ranges of thermodynamic conditions and can be implemented with any internal energy model U, allowing integration into many existing materials workflows. We demonstrate the applicability of this approach to the simulation of benchmark systems (AgPd, CuAu) that exhibit diverse thermodynamic behavior in their phase diagrams. Finally, we discuss remaining challenges in model development and promising research directions for future improvements.

36 MATERIALS SCIENCE↗

Customizing the JPL Multimission Ground Data System: Lessons learned

The Multimission Ground Data System (MGDS) at NASA's Jet Propulsion Laboratory has brought improvements and new technologies to mission operations. It was designed as a generic data system to meet the needs of multiple missions and avoid re-inventing capabilities for each new mission and thus reduce costs. It is based on adaptable tools that can be customized to support different missions and operations scenarios. The MGDS is based on a distributed client/server architecture, with powerful Unix workstations, incorporating standards and open system architectures. The distributed architecture allows remote operations and user science data exchange, while also providing capabilities for centralized ground system monitor and control. The MGDS has proved its capabilities in supporting multiple large-class missions simultaneously, including the Voyager, Galileo, Magellan, Ulysses, and Mars Observer missions. The Operations Engineering Lab (OEL) at JPL has been leading Customer Adaptation Training (CAT) teams for adapting and customizing MGDS for the various operations and engineering teams. These CAT teams have typically consisted of only a few engineers who are familiar with operations and with the MGDS software and architecture. Our experience has provided a unique opportunity to work directly with the spacecraft and instrument operations teams and understand their requirements and how the MGDS can be adapted and customized to minimize their operations costs. As part of this work, we have developed workstation configurations, automation tools, and integrated user interfaces at minimal cost that have significantly improved productivity. We have also proved that these customized data systems are most successful if they are focused on the people and the tasks they perform and if they are based upon user confidence in the development team resulting from daily interactions. This paper will describe lessons learned in adapting JPL's MGDS to fly the Voyager, Galileo, and Mars Observer missions. We will explain how powerful, existing ground data systems can be adapted and packaged in a cost effective way for operations of small and large planetary missions. We will also describe how the MGDS was adapted to support operations within the Galileo Spacecraft Testbed. The Galileo testbed provided a unique opportunity to adapt MGDS to support command and control operations for a small autonomous operations team of a handful of engineers flying the Galileo Spacecraft flight system model.

Murphy, Susan C.↗

Adaptivity in Agent-Based Routing for Data Networks

Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems (MAS s) in noisy environments. One important consideration in designing adaptive agents is choosing their action spaces to be as amenable as possible to machine learning techniques, especially to reinforcement learning (RL) techniques. One important way to have the interaction structure connecting agents itself be adaptive is to have the intentions and/or actions of the agents be in the input spaces of the other agents, much as in Stackelberg games. We consider both kinds of adaptivity in the design of a MAS to control network packet routing. We demonstrate on the OPNET event-driven network simulator the perhaps surprising fact that simply changing the action space of the agents to be better suited to RL can result in very large improvements in their potential performance: at their best settings, our learning-amenable router agents achieve throughputs up to three and one half times better than that of the standard Bellman-Ford routing algorithm, even when the Bellman-Ford protocol traffic is maintained. We then demonstrate that much of that potential improvement can be realized by having the agents learn their settings when the agent interaction structure is itself adaptive.

Wolpert, David H.↗

Spatial Mode Correction of Single Photons Using Machine Learning

Abstract Spatial modes of light constitute valuable resources for a variety of quantum technologies ranging from quantum communication and quantum imaging to remote sensing. Nevertheless, their vulnerabilities to phase distortions, induced by random media, impose significant limitations on the realistic implementation of numerous quantum‐photonic technologies. Unfortunately, this problem is exacerbated at the single‐photon level. Over the last two decades, this challenging problem has been tackled through conventional schemes that utilize optical nonlinearities, quantum correlations, and adaptive optics. In this article, the self‐learning and self‐evolving features of artificial neural networks are exploited to correct the complex spatial profile of distorted Laguerre–Gaussian modes at the single‐photon level. Furthermore, the potential of this technique is used to improve the channel capacity of an optical communication protocol that relies on structured single photons. The results have important implications for real‐time turbulence correction of structured photons and single‐photon images.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better at higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO 2 , NO x , VOC, PM 10 ) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.

33 ADVANCED PROPULSION SYSTEMS↗

Indirect decentralized repetitive control

Learning control refers to controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work, the authors presented a theory of indirect decentralized learning control based on use of indirect adaptive control concepts employing simultaneous identification and control. This paper extends these results to apply to the indirect repetitive control problem in which a periodic (i.e., repetitive) command is given to a control system. Decentralized indirect repetitive control algorithms are presented that have guaranteed convergence to zero tracking error under very general conditions. The original motivation of the repetitive control and learning control fields was learning in robots doing repetitive tasks such as on an assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the desired trajectory. Decentralized repetitive control is natural for this application because the feedback control for link rotations is normally implemented in a decentralized manner, treating each link as if it is independent of the other links.

Lee, Soo Cheol↗

Perceptual adaptation in the use of night vision goggles

The image intensification (I sup 2) systems studied for this report were the biocular AN/PVS-7(NVG) and the binocular AN/AVS-6(ANVIS). Both are quite impressive for purposes of revealing the structure of the environment in a fairly straightforward way in extremely low-light conditions. But these systems represent an unusual viewing medium. The perceptual information available through I sup 2 systems is different in a variety of ways from the typical input of everyday vision, and extensive training and practice is required for optimal use. Using this sort of system involves a kind of perceptual skill learning, but is may also involve visual adaptations that are not simply an extension of normal vision. For example, the visual noise evident in the goggles in very low-light conditions results in unusual statistical properties in visual input. Because we had recently discovered a strong and enduring aftereffect of perceived texture density which seemed to be sensitive to precisely the sorts of statistical distortions introduced by I sup 2 systems, it occurred to use that visual noise of this sort might be a very adapting stimulus for texture density and produce an aftereffect that extended into normal vision once the goggles were removed. We have not found any experimental evidence that I sup 2 systems produce texture density aftereffects. The nature of the texture density aftereffect is briefly explained, followed by an accounting of our studies of I sup 2 systems and our most recent work on the texture density aftereffect. A test for spatial frequency adaptation after exposure to NVG's is also reported, as is a study of perceived depth from motion (motion parallax) while wearing the biocular goggles. We conclude with a summary of our findings.

Durgin, Frank H.↗

Biologically Inspired Technology Using Electroactive Polymers (EAP)

Evolution allowed nature to introduce highly effective biological mechanisms that are incredible inspiration for innovation. Humans have always made efforts to imitate nature's inventions and we are increasingly making advances that it becomes significantly easier to imitate, copy, and adapt biological methods, processes and systems. This brought us to the ability to create technology that is far beyond the simple mimicking of nature. Having better tools to understand and to implement nature's principles we are now equipped like never before to be inspired by nature and to employ our tools in far superior ways. Effectively, by bio-inspiration we can have a better view and value of nature capability while studying its models to learn what can be extracted, copied or adapted. Using electroactive polymers (EAP) as artificial muscles is adding an important element to the development of biologically inspired technologies.

robotics↗

Adaptive Sampling Algorithms for Probabilistic Risk Assessment of Nuclear Simulations

Nuclear simulations are often computationally expensive, time-consuming, and high-dimensional with respect to the number of input parameters. Thus exploring the space of all possible simulation outcomes is infeasible using finite computing resources. During simulation-based probabilistic risk analysis, it is important to discover the relationship between a potentially large number of input parameters and the output of a simulation using as few simulation trials as possible. This is a typical context for performing adaptive sampling where a few observations are obtained from the simulation, a surrogate model is built to represent the simulation space, and new samples are selected based on the model constructed. The surrogate model is then updated based on the simulation results of the sampled points. In this way, we attempt to gain the most information possible with a small number of carefully selected sampled points, limiting the number of expensive trials needed to understand features of the simulation space. We analyze the specific use case of identifying the limit surface, i.e., the boundaries in the simulation space between system failure and system success. In this study, we explore several techniques for adaptively sampling the parameter space in order to reconstruct the limit surface. We focus on several adaptive sampling schemes. First, we seek to learn a global model of the entire simulation space using prediction models or neighborhood graphs and extract the limit surface as an iso-surface of the global model. Second, we estimate the limit surface by sampling in the neighborhood of the current estimate based on topological segmentations obtained locally. Our techniques draw inspirations from topological structure known as the Morse-Smale complex. We highlight the advantages and disadvantages of using a global prediction model versus local topological view of the simulation space, comparing several different strategies for adaptive sampling in both contexts. One of the most interesting models we propose attempt to marry the two by obtaining a coarse global representation using prediction models, and a detailed local representation based on topology. Our methods are validated on several analytical test functions as well as a small nuclear simulation dataset modeled after a simplified Pressurized Water Reactor.

97 MATHEMATICS AND COMPUTING↗

Video Game Adapts To Brain Waves

Electronic training system based on video game developed to help children afflicted with attention-deficit disorder (ADD) learn to prolong their attention spans. Uses combination of electroencephalography (EEG) and adaptive control to encourage attentiveness. Monitors trainee's brain-wave activity: if EEG signal indicates attention is waning, system increases difficulty of game, forcing trainee to devote more attention to it. Game designed to make trainees want to win and, in so doing, learn to pay attention for longer times.

Pope, Alan T.↗

A core lighting curriculum for university students and lighting professionals

Here, in collaboration with a group of lighting professionals, learning outcomes were defined, prioritized, organized and mapped to a three-course sequence of lighting courses within a Bachelor of Science in Architectural Engineering degree programme. Syllabi and educational exercises were developed to support the learning outcomes – including classroom activities, homework assignments and design projects. The learning exercises balance the technical foundations of applied illuminating engineering with the artistic aspects of applied lighting design and are intended to promote significant and lasting learning by providing students with education that is useful and relevant to current lighting practice. The process for identifying and prioritizing lighting content is described, a process that could be adapted by other lighting educators to other pedagogical contexts. The syllabi and learning exercises are disseminated for reuse or adaptation, or for self-study by independent learners.

42 ENGINEERING↗

Adaptive PV Frequency Control Strategy Based on Real-time Inertia Estimation

The declining cost of solar Photovoltaics (PV) generation is driving its worldwide deployment. As conventional generation with large rotating masses is being replaced by renewable energy such as PV, the power system’s inertia will be affected. As a result, the system’s frequency may vary more dramatically in the case of a disturbance, and the frequency nadir may be low enough to trigger protection relays such as under-frequency load shedding. The existing frequency-watt function mandated in power inverters cannot provide grid frequency support in a loss-of-generation event, as PV plants usually do not have power reserves. Here, a novel adaptive PV frequency control strategy is proposed to reserve the minimum power required for grid frequency support. A machine learning model is trained to predict system frequency response under varying system conditions, and an adaptive allocation of PV headroom reserves is made based on the machine learning model as well as real-time system conditions including inertia. Case studies show the proposed control method meets the frequency nadir requirements using minimal power reserves compared to a fixed headroom control approach.

14 SOLAR ENERGY↗

Neurosymbolic Hybrid Approach to Driver Collision Warning

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.

Wang, Pei↗

Development of neural network force fields for corrosion studies

To fully understand the chemistry and physics of corrosion, novel methods of simulation must be developed. One approach is designing machine learning (ML) algorithms integrated with density functional theory to develop adaptive force fields to gain insight into corrosion behavior namely at the surface of metal oxides. Current methods of modeling corrosion are slow due to the computational cost of resolving both reaction mechanics and mass transport processes. Machine learning methods can be implemented to obtain structure-activity relationships at both the molecular and bulk scale while still retaining the accuracy of density functional theory (DFT) and significantly decreasing the time needed for simulations of complex chemical processes in the various environments of corrosion. Multiscale models are needed for corrosion studies to fully understand its processes not only at the atomic length scale (chemical bonding, energies, and forces), but also at the nano and meso length scales (solid-state physics and material science processes). Current methods of study include DFT, molecular dynamics, and Monte Carlo. The limitation of DFT is that only a small number of atoms or molecules can be simulated at that level of theory. Density functional theory is used to study the electronic structure of atoms and molecules, and calculate the force component of each atom. However, these calculations are limited to about 1000 atoms. Custom periodic boundary conditions (PBC) can be used to describe the various environments and defects that affect the atomic forces to produce a large data set from which a training set can be derived. Machine learning can be utilized to overcome the barrier of modeling macroscopic and multi-scale processes from ab initio calculations through the development of adaptive force fields. Local environments determine the atomic forces of a given system, therefore adaptive force fields must be created to produce reliable quantum mechanical calculations. This can be achieved by developing a learning algorithm that uses the mapped atomic forces or fingerprint as an input to produce energies and magnetic moments as output. A systematic approach was used to begin to build a data set in order to accurately describe the atomic forces in various environments. In Figure 4 below, a simple PBC cell of Fe{sub 2}O{sub 3} was first optimized. A surface optimization was performed next, followed by a hydroxylated surface optimization. Once this calculation has converged, the adsorption of halide species to the hydroxylated surface will be investigated. TensorFlow is an open source platform for machine learning developed by Google. Using a high level application program interface (API) such as Keras allows for building and training ML models easily in a number of different environments and languages. For this project, a neural network was developed within Anaconda in Python. Future Work: Further development of reference data set; Refining neural network and learning algorithm; Fingerprinting atomic environment to enable mapping of atomic force components; Choosing appropriate training set from reference data; Learning from training set and enabling non-linear mapping of training set fingerprints and the atomic forces; Estimation of uncertainty to identify ranges of outside applicability; Testing and analysis of molecular dynamic simulations.

36 MATERIALS SCIENCE↗

Fusing TensorFlow with building energy simulation for intelligent energy management in smart cities

Buildings account for 35% of the global final energy demand. Efficiency improvements and advanced control strategies have a significant impact in the reduction of energy costs and CO2 emissions. Building energy simulation is widely used to help planners, contractors, and building owners analyse diverse options regarding the planning and management of energy consumption in buildings. Furthermore, recent advances in data processing and computing have led to the development of sophisticated machine learning algorithms that can learn from large datasets, e.g., sensor data from buildings, and use them to develop building-specific adaptive and automatic energy controllers. Control algorithms, such as deep reinforcement learning can tune themselves, are model-free, and economical to implement. In this paper, we introduce an integrated simulation environment that combines CitySim, a fast building energy simulator, and TensorFlow, a platform for efficient implementation of advanced machine learning algorithms. The integration is achieved via Keras - an API for TensorFlow - and a set of text and csv files for data transfer between the applications. This new environment will allow researchers to investigate novel learning control algorithms, and demonstrate their robustness and potential for diverse applications in the built environment. We present two case studies for energy savings and demand response, respectively.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗