Results for “generative machine learning” — Page 14

NASA NTRSDate not supplied

Artificial Neural Networks to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.

machine learning↗

NASA NTRSDate not supplied

Machine Learning Models to Predict Cognitive Impairment of Rodents Subjected to Space Radiation

INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.

machine learning↗

NASA NTRSDate not supplied

Toward Design Assurance of Machine-Learning Airborne Systems

In recent years, Artificial Intelligence (AI) systems, enabled by Machine Learning (ML)technology, have demonstrated impressive progress and provides historic opportunities for the aviation industry. However, several key aspects of ML technology are not compatible with existing design assurance standards and make certification problematic. In this paper, we present a case study of a visual system with a Deep Neural Network (DNN) intended to detect and identify airport runway signs. Different use cases and variants of this system exhibit different levels of criticality ranging from design assurance level (DAL) D to B. We use the case study to illustrate the challenges of certification according to the current standards, such asDO-178C. We present the system design, data generation, training, and verification in detail and describe how the design assurance objectives can be met for a DAL D variant of the system. We also discuss gaps and potential approaches for the higher design assurance levels.

Avionics↗

NASA NTRS2023

Diagnosis of Antarctic Blowing Snow Properties Using MERRA-2 Reanalysis with a Machine Learning Model

This paper presents the work on using a machine learning model to diagnose Antarctic blowing snow (BLSN) properties with the Modern Era Retrospective analysis for Research and Applications v2 (MERRA-2) data. We adopt the random forest classifier for BLSN identification and the random forest regressor for BLSN optical depth and height diagnosis. BLSN properties observed from the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) are used as the truth for training the model. Using MERRA-2 fields such as snow age, surface elevation and pressure, temperature, specific humidity, and temperature gradient at the 2m level, and wind speed at the 10m level as input, reasonable results are achieved. Hourly blowing snow property diagnostics are generated with the trained model. Using the year 2010 as an example, it is shown that the Antarctic BLSN frequency is much higher over East than West Antarctica. High frequency months are from April to September, during which BLSN frequency exceeds 20% over East Antarctica. For May 2010, the BLSN snow frequency in the region is as high as 37%. Due to the suppression by strong surface-based inversions, larger values of BLSN height and optical depth are usually limited to the coastal regions, wherein the strength of surface-based inversions is weaker.

Antarctic↗

NASA NTRS2023

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As the space economy continues to expand through increasingly easy access to advanced and inexpensive technology, space missions themselves have become more ambitious with exploration targets growing ever distant while simultaneously requiring larger guidance and communication budgets. These conflicting desires of distance and control drive the need for advanced on-board intelligent decision making to reduce communication and control limitations by automating as many mission functions as possible in-situ. While the amount of research on such Artificial Intelligence and Machine Learning (AI/ML) software modules has grown exponentially, the capacity to experimentally validate such software modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available bleeding-edge computational platforms via what is programmatically referred to as the BrainStack on the TechEdSat (TES-n) flight series. This on-orbit computational platform provides an evaluation laboratory where advanced software experiments are pre-loaded into memory prior to launch, then executed as payloads during mission operations with results reported back and program tweaks or new training sets uploaded as needed. Processors selected as part of the BrainStack are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and, more recently, neuromorphic processors, in LEO operations. Neuromorphic processors are of particular interest due to their superior power efficiency over GPUs in intelligent automation applications. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on TES-13, January 13, 2022, and continues to operate in orbit despite no significant modifications to harden the processor against the space environment. The Intel Loihi Gen-1 on TES-13 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. The processor is packaged in the Kapoho Bay USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by an Intel Pentium single-board computer to handle scheduling of the software application payloads and communications with the satellite’s primary computer. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the continually evolving BrainStack in the upcoming three TES-n/NOW flights. The Kapoho Point unit will incorporate eight Loihi-2 processors, enabling neural networks of up to one million neurons and one billion synapsis. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space automation applications may be initially tested.

Artificial Intelligence↗

NASA NTRSDate not supplied

Citizen Science Approach for Searching and Curating Literature of the Effects of Spaceflight on Cardiovascular Outcomes in Rodents and Humans

The spaceflight environment causes significant changes to the structure and function of the cardiovascular system, including fluid redistribution, alterations in blood pressure, and changes in cardiac output. The goal of this project is to quantitatively summarize the data on the effects of actual or simulated microgravity and radiation exposure resulting from spaceflight on the cardiovascular system. As the first step, a group of investigators approached through a collaboration of the Ames Life Science Data Archive (ALSDA) Analysis Working Group developed a list of relevant cardiovascular search terms. Based on these, medical librarians generated and executed the search strategy in Medline, CINAHL, Embase and NASA repositories. In parallel, we recruited students and young professionals from various space industry-affiliated organizations, resulting in ~100 individuals joining. With this program we aimed to reach students and young people underrepresented in STEM, including first-generation, female, minorities, disadvantaged backgrounds, fostered individuals, etc. These individuals completed a virtual training course on the nature and methodologies of the project. Following this, the participants were structured into teams with more senior/experienced individuals designated as team leaders. Currently, the teams are screening approximately 15,000 studies using the systematic review tool, Covidence. Teams will be extracting and curating data for meta-analysis of the cardiovascular spaceflight literature, but also extracting, submitting, and curating appropriate datasets into the new ALSDA submission portal and repository. This effort will result in collaborative publications based upon the literature meta-analyses, and a number of publicly accessible datasets for reuse, modeling, machine learning, and knowledge graph-type approaches. This approach reduces the length of time to complete title/abstract screening time from 1-2 years needed for this volume of studies, to 3-4 months, while also providing a unique, open-access educational experience to space research and training in knowledge synthesis tools to interested individuals.

space biology↗

NASA NTRSDate not supplied

Pushing the Limits of Aquatic Remote Sensing: Synthetic Data and Deep Learning for Fast Inverse Emulation of A Coupled Ocean-Atmosphere Radiative Transfer Model

The inversion of electromagnetic information to physical and biological properties of the water column is a notoriously difficult problem, yet fundamental to our ability of understanding aquatic processes on large time and space scales. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will discuss research integrating advanced biological and radiative modeling, high-end computation, and machine learning to develop a portable global processor for simultaneous retrieval of atmosphere and water optics for diverse aquatic systems from the open and coastal ocean to optically extreme inland waters and harmful algal blooms. We will discuss some of the basic concepts behind the forward modeling approach including DEAP, the novel Distributed Equivalent Algal Populations model, for developing large spectral libraries of aquatic particle optics to aid in our ability to distinguish phytoplankton functional types (PFTs) and inorganic material, as well as other factors which enable comprehensive modeling from the benthos to top-of-atmosphere (TOA). This information is being used to understand how we can leverage next-generation deep learning methods for maximum information retrieval and rapid image processing, while also providing capabilities to identify minimum sensor spectral requirements necessary for certain aquatic applications. Further, I will touch on how we envision this research to enable the aquatic community for science discovery and how we are moving closer towards the capability for high-fidelity global analysis of aquatic ecosystems.

Jeremy Alan Kravitz↗

NASA NTRSDate not supplied

FloodPlanet: High-Resolution Commercial Imagery for Training and Validation of Deep Learning-Based Models of Inundation Extent

Flooding events are becoming increasingly frequent worldwide and are known to cause extensive damage. Public optical and radar satellite imagery can be used to detect large areas of inundation in rural areas, however, long revisit times and coarse spatial resolution limit applications for short-lived events and urban areas. Commercial constellations such as those operated by Planet offer increased spatial and temporal resolution and can supplement mapping efforts to provide more information to disaster response, relief, and mitigation efforts. Deep learning requires high quality labeled data for training across coincident sensors. The FloodPlanet dataset presented here contains labeled surface water for 18 events across the world based on Planetscope imagery with coincident Harmonized Landsat Sentinel-2 ( HLS) or Sentinel-1 and builds upon the previously existing Sen1Floods11, xBD, and NASA Sentinel-1 datasets. Sen1Floods11 includes 4,831 512x512 pixel overlapping tiles of coincident Sentinel-1 and Sentinel-2 data observing 11 flood events across the world from 2017-2019. The dataset contains a combination of automated and hand-labeled surface water for use in training and validation of inundation modeling efforts. The xBD dataset identifies flood-damaged buildings and indicates the scale of damage to each (none, minor, moderate, and major) from four flood events which occurred in the United States, India, Nepal, and Bangladesh from the same time period. The NASA dataset contains hand-labeled water bodies observed in Sentinel-1 imagery during five flood events within the 2017-2019 period. The effort presented here utilizes observations from these previously investigated flood events to generate labels of surface water at the 3-5m spatial resolution provided by Planetscope and facilitate the comparison between public and commercial data. A data pipeline was built which uses clustering algorithms to pick the most suitable overlapping chips between the public data and PlanetScope data for manual labeling. Labels were created manually using NASA’s ImageLabeler tool and include areas of high- and low-confidence water. The high confidence designation is reserved for areas of open, unobstructed water while low confidence is used for areas of suspected water beneath vegetation, clouds, or cloud shadows. Expected to be released in late 2022, the FloodPlanet dataset will include tiled imagery with a unique ID for each 1024x1024 pixel tile, 7 bands of HLS data, and high- and low-confidence flood labels in both shapefile and tiff formats. The authors will follow Spatial Temporal Access Catalog (STAC) guidelines to release FloodPlanet on the Radiant Earth ML hub, which hosts public datasets for machine learning.

Alexander Melancon↗

NASA NTRSDate not supplied

NASA's Small Spacecraft and Distributed Systems: Development and Demonstration of Technologies Enabling Swarms and New Spacecraft Platforms with AI and Edge Computing

NASA’s Small Spacecraft & Distributed Systems (SSDS) within the Research and Technology Mission Directorate (RTMD) expands U.S. capability to execute unique missions through targeted investment, rapid development, and flight demonstration of small spacecraft technologies applicable to exploration, science and the commercial space sector. SSDS strategically invests in technology development and on-orbit demonstrations executed across NASA, other government agencies, industry, and academia. The program’s University SmallSat Technology Partnerships initiative awards academic researchers with the opportunity to collaborate with NASA to mature innovative technology. Capabilities aligned with RTMD’s technology shortfalls and interests - power, processing, propulsion, sensors, communications, autonomous navigation, architectures, and advanced applications like artificial intelligence (AI), machine learning, and edge computing - are prioritized in SSDS investments. These investments enable distributed, autonomous, and cooperative small spacecraft systems that support swarm missions extending beyond low Earth orbit into cislunar and deep space. This paper highlights representative SSDS flight demonstrations that mature these capabilities to enable a future operational infrastructure needed to support sustained exploration of the Moon and beyond. SSDS’s investment strategy emphasizes rapid development and on-orbit demonstration to validate spacecraft technologies required for swarms and distributed mission architectures. The Starling swarm technology demonstration mission exemplifies this approach by advancing distributed spacecraft autonomy, cooperative operations, and space situational awareness. Extended flight testing and ongoing studies of next generation swarm configurations and on-orbit space traffic monitoring and management continue to inform future swarm designs. DiskSat’s four-spacecraft demonstration mission represents SSDS’s strategic vision to expand the design space for future small spacecraft through its commitment to advance novel platform concepts that can impact how science is performed on orbit. Continuing to invest in future platforms, the notional PY12 concept is a 12-spacecraft swarm hosting neuromorphic processors and is envisioned as an on-orbit testbed for AI, edge computing, and positioning, navigation and timing technologies. SSDS also invests in single-spacecraft technology demonstrations that underpin the success of future swarm missions and accelerate the availability of validated technologies across the small spacecraft ecosystem. Examples of such demonstrations include Pathfinder Technology Demonstrator-3 (PTD-3), which performed high-rate optical communications; PTD-R, which demonstrated a camera capable of simultaneous ultraviolet and short-wave infrared optical sensing; and CAPSTONE, the Cislunar Autonomous Positioning System Technology and Operations Navigation Experiment, which validated autonomous navigation in cislunar space. Collectively, SSDS-funded demonstrations advance capabilities across swarms and illustrate a coordinated investment strategy to mature high-impact technologies required for autonomous, distributed, and cooperative small spacecraft systems for low Earth orbit, cislunar, and deep space applications. Technology demonstrations strengthen SSDS partnerships with industry, academia, and other government agencies, and promote small spacecraft community adoption of capabilities required to close technical gaps for swarm missions.

Jan Stupl↗

NASA NTRSDate not supplied

NASA's Small Spacecraft and Distributed Systems: Development and Demonstration of Technologies Enabling Swarms and New Spacecraft Platforms with AI and Edge Computing

NASA’s Small Spacecraft & Distributed Systems (SSDS) within the Research and Technology Mission Directorate (RTMD) expands U.S. capability to execute unique missions through targeted investment, rapid development, and flight demonstration of small spacecraft technologies applicable to exploration, science and the commercial space sector. SSDS strategically invests in technology development and on-orbit demonstrations executed across NASA, other government agencies, industry, and academia. The program’s University SmallSat Technology Partnerships initiative awards academic researchers with the opportunity to collaborate with NASA to mature innovative technology. Capabilities aligned with RTMD’s technology shortfalls and interests - power, processing, propulsion, sensors, communications, autonomous navigation, architectures, and advanced applications like artificial intelligence (AI), machine learning, and edge computing - are prioritized in SSDS investments. These investments enable distributed, autonomous, and cooperative small spacecraft systems that support swarm missions extending beyond low Earth orbit into cislunar and deep space. This paper highlights representative SSDS flight demonstrations that mature these capabilities to enable a future operational infrastructure needed to support sustained exploration of the Moon and beyond. SSDS’s investment strategy emphasizes rapid development and on-orbit demonstration to validate spacecraft technologies required for swarms and distributed mission architectures. The Starling swarm technology demonstration mission exemplifies this approach by advancing distributed spacecraft autonomy, cooperative operations, and space situational awareness. Extended flight testing and ongoing studies of next generation swarm configurations and on-orbit space traffic monitoring and management continue to inform future swarm designs. DiskSat’s four-spacecraft demonstration mission represents SSDS’s strategic vision to expand the design space for future small spacecraft through its commitment to advance novel platform concepts that can impact how science is performed on orbit. Continuing to invest in future platforms, the notional PY12 concept is a 12-spacecraft swarm hosting neuromorphic processors and is envisioned as an on-orbit testbed for AI, edge computing, and positioning, navigation and timing technologies. SSDS also invests in single-spacecraft technology demonstrations that underpin the success of future swarm missions and accelerate the availability of validated technologies across the small spacecraft ecosystem. Examples of such demonstrations include Pathfinder Technology Demonstrator-3 (PTD-3), which performed high-rate optical communications; PTD-R, which demonstrated a camera capable of simultaneous ultraviolet and short-wave infrared optical sensing; and CAPSTONE, the Cislunar Autonomous Positioning System Technology and Operations Navigation Experiment, which validated autonomous navigation in cislunar space. Collectively, SSDS-funded demonstrations advance capabilities across swarms and illustrate a coordinated investment strategy to mature high-impact technologies required for autonomous, distributed, and cooperative small spacecraft systems for low Earth orbit, cislunar, and deep space applications. Technology demonstrations strengthen SSDS partnerships with industry, academia, and other government agencies, and promote small spacecraft community adoption of capabilities required to close technical gaps for swarm missions.

Jan Stupl↗

NASA NTRS2010

Understanding the Scalability of Bayesian Network Inference Using Clique Tree Growth Curves

One of the main approaches to performing computation in Bayesian networks (BNs) is clique tree clustering and propagation. The clique tree approach consists of propagation in a clique tree compiled from a Bayesian network, and while it was introduced in the 1980s, there is still a lack of understanding of how clique tree computation time depends on variations in BN size and structure. In this article, we improve this understanding by developing an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, specifically: (i) the ratio of the number of a BN s non-root nodes to the number of root nodes, and (ii) the expected number of moral edges in their moral graphs. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for the total size of each set. For the special case of bipartite BNs, there are two sets and two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, where random bipartite BNs generated using the BPART algorithm are studied, we systematically increase the out-degree of the root nodes in bipartite Bayesian networks, by increasing the number of leaf nodes. Surprisingly, root clique growth is well-approximated by Gompertz growth curves, an S-shaped family of curves that has previously been used to describe growth processes in biology, medicine, and neuroscience. We believe that this research improves the understanding of the scaling behavior of clique tree clustering for a certain class of Bayesian networks; presents an aid for trade-off studies of clique tree clustering using growth curves; and ultimately provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms.

Mengshoel, Ole J.↗

NASA NTRS2018

Learning Model Structural Uncertainty with Gaussian Processes

The advent of commercially available quantum computers has marked the beginning of quantum computing as a reality. Both quantum gate and annealing computers have been released by major computer hardware companies. In this work, the D-Wave 2XTM quantum annealing computer housed at the NASA Advanced Systems computational facility is investigated to accelerate Machine Learning (ML) for image registration. NASA collects large amounts of images over the globe remotely using space-based monitoring. Images of a fixed areas of the land surface are taken over time. Due to the orbit of the sensors, the viewing angles deviate slightly, and it is necessary to align or register the images precisely to create image time series over the land surface. Unaligned images can lead to substantial analysis errors. These time-series are then used in modeling Earth Systems models such as hydrological, weather, and carbon monitoring models. In this work, we consider the Moderate Resolution Image Spectrometer (MODIS) data collected by the NASA's terra satellite. Artificial Neural Networks (ANNs) is a natural fit for ML modelling of images. Several successes have been reported using machine learning related to image processing. We investigate the use of ML to register MODIS images. ANNs are investigated in combination with a Restricted Boltzmann Machines (RBM) as an auto-encoder. We will present results showing the accuracy and efficiency of this approach.The D-Wave 2XTM quantum annealer samples the ground-state wave-function of a spin-Ising systems with quadratic interactions between qubits and a Chimera connectivity. The system sits in a ~15 mK thermal bath. One can think of the system as being placed in the ground state initially and subject to thermal excitations governed by Boltzmann statistics. If this is assumed true, one can use the statistics from the D-Wave 2XTM to train RBMs. Generating statistics for training Boltzmann machines is an NP-hard problem and constitutes the largest compute cost. We investigate the use of the D-Wave 2XTM to accelerate the training of the RBMs in our ANNs and report on the results.

Kouatchou, Jules↗

NASA NTRS2024

Recommendations on Evidence and Process for Certification of Learning-enabled Components in Aerospace Systems

This report primarily identifies a collection of relevant and necessary evidence for assurance of machine learnt components (MLCs)—also known as learning-enabled components—integrated into aircraft systems, and gives preliminary suggestions on the elements of a certification process that invoke the identified evidence. The main focus is on feedforward neural networks that are static and trained offline through supervised learning. A brief background on the generic elements of the lifecycle of an MLC is given to contextualize the assurance considerations and, consequently, the evidence that is relevant and necessary to support certification. At the level of an MLC, those considerations relate to: (i) the consistency and correctness of MLC contributions to system functions in the context of a validated functional intent; and (ii) the absence of MLC contributions to aircraft-level failure conditions. At an ML model level, confidence in model and data properties contribute to assurance of the containing MLC, in particular: (a) generalizability and robustness of models, in the presence of inputs not previously seen during training, disturbances to inputs, and unexpected inputs; and (b) valid data, i.e., data that are at least representative, relevant, complete, and accurate. Evidence for the above span the elements of the ML lifecycle, and includes, at a minimum, lifecycle artifacts that pertain to: (1) properties of requirements capturing functional intent, safety constraints, and aspects of the intended use and operating environment; (2) model performance, model complexity and design, and algorithm choice; (3) achievement of required performance at the levels of a trained model during model development, a trained model after model development is complete, and a trained model that is transformed into an executable equivalent; (4) model implementation aspects necessary for transforming a trained model into the executable equivalent; (5) integration of the executable trained model into the containing MLC, and eventually the larger system; and, (6) lastly, the verification and validation (V&V) of each of the above. Such V&V lifecycle artifacts themselves include: aspects of coverage, e.g., of various levels of requirements by the input space of the model and the data; traceability (where applicable); application of formal methods for property specification, analysis, and checking. Examples of evidence generation methods and tools further ground the discussion on what constitutes evidence, and the contribution to assurance during certification. The identified assurance considerations and supporting evidence is not a comprehensive set. Additionally, neither what should be considered as sufficient evidence relative to the assigned criticality of an MLC, nor how criticality ought to be determined and adjusted, have been considered in this report. However, suggestions are made for potential activities of the ML lifecycle that are aimed at providing confidence that an MLC can be relied upon when integrated into its containing (aircraft) system. Those activities are proposed as candidate elements of a certification process for MLCs. The main purpose of this report to inform regulatory guidance and consensus standards that may be used to meet the safety intent of the applicable regulations.

Aviation safety↗

NASA NTRS2015

Model Generation to Support Model-Based Testing Applied on NASA DAT - An Experience Report

Model-based Testing (MBT), where a model of the system under tests (SUT) behavior is used to automatically generate executable test cases, is a promising and versatile testing technology. Nevertheless, adoption of MBT technologies in industry is slow and many testing tasks are performed via manually created executable test cases (i.e. test programs such as JUnit). In order to adopt MBT, testers must learn how to construct models and use these models to generate test cases, which might be a hurdle. An interesting observation in our previous work is that the existing manually created test cases often provided invaluable insights for the manual creation of the testing models of the system. In this paper we present an approach that allows the tester to first create and debug a set of test cases. When the tester is happy with the test cases, the next step is to automatically generate a model from the test cases. The generated model is derived from the test cases, which are actions that the system can perform (e.g. a button clicks) and their expected outputs in form of assert statements (e.g. assert data entered). The model is a Finite State Machine (FSM) model that can be employed with little or no manual changes to generate additional test cases for the SUT. We successfully applied the approach in a feasibility study to the NASA Data Access Toolkit (DAT), which is a web-based GUI. One compelling finding is that the test cases that were generated from the automatically generated models were able to detect issues that were not detected by the original set of manually created test cases. We present the findings from the case study and discuss best practices for incorporating model generation techniques into an existing testing process.

State Machines↗

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.↗

NASA NTRS1994

A New Generation of Intelligent Trainable Tools for Analyzing Large Scientific Image Databases

In a variety of scientific disciplines two-dimensional digital image data is now relied on as a basic component of routine scientific investigation. The proliferation of image acquisition hardware such as multi-spectral remote-sensing platforms, medical imaging sensors, and high-resolution cameras have led to the widespread use of image data in fields such as atmospheric studies, planetary geology, ecology, agriculture, glacielogy, forestry, astronomy, diagnostic medicine, to name but a few.

machine↗

NASA NTRS2022

Robust Semantic Mapping and Localization on a Free-Flying Robot in Microgravity

We propose a system that uses semantic object detections to localize a microgravity free-flyer. Many applications require absolute localization in a known reference frame, such as the execution of waypoint trajectories defined by human operators. Classical geometric methods build a map of point features, which may not be able to be associated after lighting or environmental changes. By contrast, semantics remain invariant to changes up to the robustness of the detection algorithm and motion of the semantic objects. In this work, we describe our approaches for both offline semantic map generation as well as online localization against a semantic map, intended to run in real-time on the robot. We additionally demonstrate how our semantic localizer outperforms image-feature matching in some cases, and show the robustness of the algorithm to environmental changes. Crucially, we show in our experiments that when semantics are used to supplement point features, localization is always improved. To our knowledge, these experiments demonstrate the first use of learned semantics for localization on a free-flying robot in microgravity.

Localization↗

NASA NTRS2022

Coevolution of Machine Learning and Process-Based Modelling to Revolutionize Earth and Environmental Sciences: A Perspective

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.

Saman Razavi↗