Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep 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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
NASA NTRS2016

Proving Ground Potential Mission and Flight Test Objectives and Near Term Architectures

NASA is developing a Pioneering Space Strategy to expand human and robotic presence further into the solar system, not just to explore and visit, but to stay. NASA's strategy is designed to meet technical and non-technical challenges, leverage current and near-term activities, and lead to a future where humans can work, learn, operate, and thrive safely in space for an extended, and eventually indefinite, period of time. An important aspect of this strategy is the implementation of proving ground activities needed to ensure confidence in both Mars systems and deep space operations prior to embarking on the journey to the Mars. As part of the proving ground development, NASA is assessing potential mission concepts that could validate the required capabilities needed to expand human presence into the solar system. The first step identified in the proving ground is to establish human presence in the cis-lunar vicinity to enable development and testing of systems and operations required to land humans on Mars and to reach other deep space destinations. These capabilities may also be leveraged to support potential commercial and international objectives for Lunar Surface missions. This paper will discuss a series of potential proving ground mission and flight test objectives that support NASA's journey to Mars and can be leveraged for commercial and international goals. The paper will discuss how early missions will begin to satisfy these objectives, including extensibility and applicability to Mars. The initial capability provided by the launch vehicle will be described as well as planned upgrades required to support longer and more complex missions. Potential architectures and mission concepts will be examined as options to satisfy proving ground objectives. In addition, these architectures will be assessed on commercial and international participation opportunities and on how well they develop capabilities and operations applicable to Mars vicinity missions.

Smith, R. Marshall↗
NASA NTRS2003

Flight Experience from Space Photovoltaic Concentrator Arrays and its Implication on Terrestrial Concentrator Systems

Nearly all photovoltaic solar arrays flown in space have used a planar (non- concentrating) design. However, there have been a few notable exceptions where photovoltaic concentrators have been tested and used as the mission s primary power source. Among these are the success experienced by the SCARLET (Solar Concentrator Array with Refractive Linear Element Technology) concept used to power NASA's Deep Space 1 mission and the problems encountered by the original Boeing 702 reflective trough concentrator design. This presentation will give a brief overview of past photovoltaic concentrator systems that have flown in space, specifically addressing the valuable lessons learned from flight experience, and other viable concentrator concepts that are being proposed for the future. The general trends of this flight experience will be noted and discussed with regard to its implications on terrestrial photovoltaic concentrator designs.

Piszczor, Michael F., Jr.↗
NASA NTRSDate not supplied

QuantifyML: How Good is My Machine Learning Model?

We present QuantifyML, which applies model counting to assess the learn ability, safety, and robustness of machine learning models. Typically, the efficacy of machine learning models is determined by computing their accuracy statistically on test datasets. However, this may be misleading, if the test data is not representative of the problem that is being studied. With QuantifyML we aim to precisely quantify the extent to which machine learning models have learned and generalized from the given data. In QuantifyML, a trained model is translated into aC program, which is fed to the CBMC model checking tool to produce a formula in Conjunctive Normal Form (CNF), which in turn is analyzed with state-of-the-art model counters to efficiently obtain precise countsw.r.t different outputs. QuantifyML enables i) evaluating the learnability of models by comparing the counts for the outputs to ground truth, ex-pressed as logical predicates (if available), ii) comparing the performance of different models that may be built with different machine learning algorithms (e.g., decision-trees vs. neural networks), and iii) quantifying the safety and robustness of trained models.

Deep Neural Networks↗
NASA NTRS2019

"Sensor Web Evolution - Webs of Webs for NASA Science - Focus on small Uninhabited Aerial Systems (sUAS)"

This paper will describe the evolution of information collection, derivation and delivery mechanisms in webs of NASA sensor webs, with a focus on recent advancements in small Uninhabited Aerial Systems (sUAS). I will discuss the movement to "Fog Computing", also known as Edge Computing. Fog Computing facilitates the distribution of common operations and networking between edge devices and cloud computing facilities, optimizing the production of actionable intelligence. Initially, sUASs utilized onboard data collection as standard, with minimal data downloaded directly. Information products were derived in conventional computational environments, generally desk top computers, and information products made available to the Science Community in weeks or months. With the increased availability, and increasingly lower costs, of beyond line of sight (BLOS) satellite based communication, transmission rates and data volumes increased, and processing migrated to Cloud based services. Contemporary sUASs are moving some of that information product derivation to on vehicle services, and are creating a distributed Cloud/Fog environment. I will describe the technological advances that have made this possible, including low power multi-core Central Processing Units (CPU), and, more recently, the availability of high end Graphical Processing Units (GPU) that consume only a few watts. Intelligent system software, leveraging these hardware advances, finally allows for information product generation on-board, rather than simple data collection. Additionally, intelligent flight control systems now support mutual vehicle to vehicle collaboration, allowing sUASs to create ad-hoc sensor webs on demand, as required. Also discussed will be the lessons learned by the Authors' development of data systems for NASA's large High Altitude Long Endurance (HALE) UASs like Predator and Global Hawk, and how those lessons are being applied to sUAS development. This paper will focus on application, rather a deep dive into the technology, and will highlight improving data management through these new technologies.

Sensor Web↗
NASA NTRSDate not supplied

UASs in the VOG/Edge/FOG Sensor Web Environment

This paper will describe the evolution of information collection, derivation and delivery mechanisms in sensor webs utilizing Uninhabited Aerial Systems (UAS).We will discuss the movement to "Fog Computing", also known as Edge Computing. Fog Computing facilitates the distribution of common operations and networking between edge devices and cloud computing facilities, optimizing the production of actionable intelligence. Initially, UASs utilized onboard data collection as standard, with minimal data downloaded directly. Information products were derived in conventional computational environments, generally desk top computers, and information products made available to the Science Community in weeks or months. With the increased availability, and increasingly lower costs, of beyond line of sight (BLOS) satellite based communication, transmission rates and data volumes increased, and processing migrated to Cloud based services. Contemporary UASs are moving some of that information product derivation to on vehicle services, and are creating a distributed Cloud/Fog environment. The Author will describe the technological advances that have made this possible, including low power multi-core Central Processing Units (CPU), and, more recently, the availability of high end Graphical Processing Units (GPU) that consume only a few watts. Intelligent system software, leveraging these hardware advances, finally allows for information product generation on-board, rather than simple data collection. Additionally, intelligent flight control systems now support mutual vehicle to vehicle collaboration, allowing UASs to create ad-hoc sensor webs on demand, as required. Also discussed will be the lessons learned by the Authors' development of data systems for NASA's large High Altitude Long Endurance (HALE) UASs like Predator and Global Hawk, and how those lessons are being applied to other UAS development This paper will focus on applications, rather a deep dive into the technology, and will highlight improving data management through these new technologies.

UAS↗
NASA NTRS2002

FIP, FIT or MAD? Analysis of High Signal-to-Noise ASCA Spectra of Coronal Stars

ASCA (Advanced Satellite for Cosmology and Astrophysics) and EUVE (Extreme Ultraviolet Explorer) spectra of active late-type stars imply that Fe and other medium-Z elements may be 2-10 times less abundant in the coronae of these stars than in their photo-spheres (the MAD effect). These deficiencies may be related to the solar FIP (First Ionization Potential) effect, in which Fe and other low First Ionization Potential elements appear enriched in the solar corona over their photospheric values. The FIP effect is time variable. As part of this proposal, the K0-2 III star, 29 Draconis, was observed in X rays with the ASCA spacecraft in order to measure the coronal abundances of this star at three different stellar longitudes over its 31-day rotation cycle. The goal of the observations was to learn whether coronal abundances, and hence coronal magnetic structure, vary across the surface of 29 Draconis in phase with the motion of dark star-spots across its disk. A second task included in this project was a systematic reanalysis of 18-20 deep exposures of active coronal stars, which were extracted from the ASCA public archives. New thermal models were computed for each spectrum in order to derive coronal metal abundances for each star. The goal of this survey was to search for possible trends in coronal abundance with various stellar parameters such as rotation, chromospheric activity levels at ultraviolet and optical wavelengths, or evolutionary stage.

Simon, Theodore↗
NASA NTRS2018

An Integrated Science Glovebox for the Gateway Habitat

Next generation habitats for deep space exploration of cislunar space, the Moon, and ultimately Mars will benefit from on-board glovebox capability. Such a glovebox facility will maintain sample integrity for a variety of scientific endeavors whether for life science, materials science, or astromaterials. Glovebox lessons learned from decades of astromaterials curation, ISS on-board sample handling, and robust analog missions provide key design and operational factors for inclusion in on-going habitat development.

Calaway, M. J.↗
NASA NTRSDate not supplied

Harnessing Artificial Intelligence for Medical Diagnosis and Treatment During Space Exploration Missions

From May 8th to June 9th, 2023, I had the opportunity to participate in an experiential learning experience at Johnson Space Center in Houston, TX with Exploration Medical Capability (ExMC), an element of the NASA Human Research Program. During this research experience, I was not only able to work on the above titled research project, but also gain an immense exposure to the field of aerospace medicine, make numerous connections within the field, tour NASA facilities, as well as travel to the Aerospace Medical Association Annual Conference (AsMA) in New Orleans. To briefly introduce my project, it is well understood that the medical capabilities available to crew medical officers (CMOs) on the International Space Station will be different than the capabilities available and needed during deep space exploration missions to the Moon, Mars, and beyond. Ground support is particularly limited due to distance, communication delays (or lack of communication), and lack of resupply. Therefore, to support medical care by CMOs on these missions, robust clinical decision support systems (CDSSs) must be designed. The recent publication and public launch of generative artificial intelligence (AI) tools based upon large language models (LLM) such as ChatGPT provides the opportunity to create a smart assistant for onboard triage, diagnosis, and treatment of medical conditions. Ultimately, the overall purpose of the project was to research what AI tools currently exist or are in development, and to see how they might be implemented onboard during exploration class spaceflights of the future. The ExMC element is actively developing several tools to be used in preparation for and during deep space exploration missions. One of those tools, known as IMPACT, is a probabilistic risk assessment model which can be used to propose a desired medical system (based on mass and volume) and suggest the clinical outcomes likely to occur for a design reference mission (DRM). The group recently presented the IMPACT model and a DRM of interest titled “Modified Long Duration Lunar Orbital and Lunar Surface” (mLDLOLS) at the recent AsMA conference. The mLDLOLS mock mission is a 9 month and 6-day deep space exploration mission consisting of time in Moon’s orbit (3 months on the Gateway space station), on the lunar surface (3 months within habitat), and another 3 months on Gateway before return to Earth. For this DRM, IMPACT ultimately outlined a preferred medical system that was then associated with medical conditions considered to be most likely based on frequency, most likely to cause astronaut task time loss (TTL), most likely to cause return to definitive care (RTDC), and most likely cause loss of crew life (LOCL). IMPACT also highlighted the medical capabilities/skills that would be required to care for those medical conditions, such as performing a history of present illness or musculoskeletal exam with ultrasound. The primary objective of the project was to perform a survey of the AI tools and systems applicable to the conditions outlined for the proposed mLDLOLS mission. Using PubMed (including most relevant MeSH terms) and Google Scholar, we then created a robust annotated bibliography organized by condition. The 56-page and over 500 reference annotated bibliography was subsequently used to create a review outline that would become the basis for drafting of a future publication. For the review outline, we took those medical conditions researched within the annotated bibliography (condition-based approach) and deployed a systems-based approach, combining those medical conditions and related tools into ten categories. These categories included general/all-purpose CDSSs, tools to diagnose or manage respiratory, dermatologic, neurologic, auditory and vestibular, ophthalmic, musculoskeletal, infection-associated, and gynecologic conditions, as well as tools that could be deployed in the setting of trauma/emergency. With the completion of the 30-page outline, we then began drafting the review paper. To conclude the research experience, I presented the findings from our survey to the ExMC Clinical and Science team. With these objectives, I ultimately learned about the number of AI tools that exist today to assist medical professionals with the triage, diagnosis, and management of several medical conditions. These tools can span from chatbot assistants to help triage knee pain to vision transformer models that can identify ophthalmic conditions based on ocular surface images captured with a cell phone. We also highlighted the current gaps that exist in the literature alongside the advancements that are needed to make the desired CDSS for deep space exploration missions. With this experience, I certainly confirmed an existing career goal and identified several additional skills needed to become an aerospace medical doctor including knowledge of critical care in an extreme medicine setting, aerospace engineering and human integration systems, artificial intelligence, machine learning, and risk models. I also identified numerous transferable skills for this career goal including the basic knowledge of medicine (MD), deployment of the scientific method for critical thought about new scientific questions (PhD), review of published literature, including creating an annotated bibliography (PhD), as well as detailed scientific writing (PhD). The results of my research will likely guide the design of an all-encompassing onboard medical assistant for use during deep space exploration missions of the future. I plan on sharing the outcomes from this experience with my peers at a student seminar in the Fall semester on August 30th. During the seminar, I will detail the project, my experience at NASA and AsMA, as well as offer best practice guidelines for students entertaining similar experiences or careers. In conclusion, I would like to thank the WVU School of Medicine, Research and Graduate Education office, as well as NASA ExMC for the unwavering support of this life-changing experience.

Ryan A. Lacinski↗
NASA NTRS2009

How Spreadsheets Get Us to Mars and Beyond

Spreadsheets, spreadsheets everywhere and nary a page of documentation. JPL is NASA's prime center for deep space missions. In all of our missions, spreadsheets have played a major role in managing parts lists, managing requirements, monitoring progress, planning budgets, developing the initial concept designs, and providing the backbone of our infrastructure. In this paper we will share our lessons learned in building various spreadsheet intensive systems and applications. Based on our experience in developing and using these various systems we will propose a number of exploratory ideas as to the dimensions of spreadsheet system complexity. In addition, we will share our approaches to documentation, review, and verification of these types of systems.

testing↗
NASA NTRSDate not supplied

Eleven Countries, an Integrated Spacecraft: the Story of International Collaboration that Built the Orion Spacecraft and Powered the Success of the Artemis I Mission

The quest to return humans to the Moon in the next step towards humanity's exploration of space is more alive than ever. After a great deal of achievements, failures, and lessons learned, the Artemis I mission set o to the Moon on November 16, 2022, with the goal of testing a new rocket, the Space Launch System, and a new spacecraft, Orion: designed, assembled, and tested across two continents, and 11 countries. Behind this mission, decades of experience with the International Space Station, Autonomous Transfer Vehicle operations, and many other program collaborations built the know-how on how to succeed together in the toughest environment | deep space. The Artemis I mission proved to be an incredible success, meeting 161 total mission objectives, including 21 developed during the flight based on outperforming spacecraft. It was also a case-study in international collaboration, given that ESA, NASA, and industry partners Airbus and Lockheed Martin for the first time had to design, build, test, and fly a fully integrated human-rated spacecraft, with most critical functions dependent and interconnected across U.S. and European systems. The U.S.-built Orion Crew Module and Crew Module Adapter and European-built European Service Module (ESM) shared critical interfaces and commodities, from propulsion, avionics, active/passive thermal, electrical power generation, storage and distribution to the software that managed it all. In this paper, we will describe relevant aspects of the integrated spacecraft design, providing context for the challenges that the team faced in all phases required to get Orion ready to fly, and provide a direct account of how the joint team formed, trained, and supported the operations of the successful Artemis I mission. We will also explore the evolution of the partnerships, given that these allow a multi-national e ort to sustain the program production, share costs, leverage a broader base of engineering expertise, and build more diverse capabilities over the long haul to support the Artemis goals and objectives. Lastly, we will cover critical lessons learned and how the Orion Program has implemented these in preparation of the next Artemis missions to repeat the success of Artemis I. The purpose of this paper is to document knowledge we gained and lessons we learned through the development of an integrated Orion spacecraft, since it is imperative we build on this now, at the dawn of the Artemis Program, an international endeavor to push human space exploration.

Deep Space Exploration↗
NASA NTRS2007

Processing Satellite Imagery To Detect Waste Tire Piles

A methodology for processing commercially available satellite spectral imagery has been developed to enable identification and mapping of waste tire piles in California. The California Integrated Waste Management Board initiated the project and provided funding for the method s development. The methodology includes the use of a combination of previously commercially available image-processing and georeferencing software used to develop a model that specifically distinguishes between tire piles and other objects. The methodology reduces the time that must be spent to initially survey a region for tire sites, thereby increasing inspectors and managers time available for remediation of the sites. Remediation is needed because millions of used tires are discarded every year, waste tire piles pose fire hazards, and mosquitoes often breed in water trapped in tires. It should be possible to adapt the methodology to regions outside California by modifying some of the algorithms implemented in the software to account for geographic differences in spectral characteristics associated with terrain and climate. The task of identifying tire piles in satellite imagery is uniquely challenging because of their low reflectance levels: Tires tend to be spectrally confused with shadows and deep water, both of which reflect little light to satellite-borne imaging systems. In this methodology, the challenge is met, in part, by use of software that implements the Tire Identification from Reflectance (TIRe) model. The development of the TIRe model included incorporation of lessons learned in previous research on the detection and mapping of tire piles by use of manual/ visual and/or computational analysis of aerial and satellite imagery. The TIRe model is a computational model for identifying tire piles and discriminating between tire piles and other objects. The input to the TIRe model is the georeferenced but otherwise raw satellite spectral images of a geographic region to be surveyed. The TIRe model identifies the darkest objects in the images and, on the basis of spatial and spectral image characteristics, discriminates against other dark objects, which can include vegetation, some bodies of water, and dark soils. The TIRe model can identify piles of as few as 100 tires. The output of the TIRe model is a binary mask showing areas containing suspected tire piles and spectrally similar features. This mask is overlaid on the original satellite imagery and examined by a trained image analyst, who strives to further discriminate against non-tire objects that the TIRe model tentatively identified as tire piles. After the analyst has made adjustments, the mask is used to create a synoptic, geographically accurate tire-pile survey map, which can be overlaid with a road map and/or any other map or set of georeferenced data, according to a customer s preferences.

Skiles, Joseph↗
NASA NTRS2019

Soil Displacement Terramechanics for Wheel-Based Trenching with a Planetary Rover

Planetary exploration rovers are expensive, weight constrained, and cannot be serviced once deployed. Here, we explore one way to increase their capabilities while avoiding the cost, mass, and complexity leading to these issues. We propose to re-use the large wheel actuators for trenching and other digging operations, which will enable a range of missions such as sampling deeper layers of soil. We present a new, closed-form model of the soil displaced by an angled, spinning wheel to analyze the trenching potential of a driving strategy and inform the control of the wheel. The model is demonstrated with single wheel experiments under different driving conditions. The model suggests: that a deep trench does not require large tractive efforts; that the shape of the trench can be controlled; and that a rear wheel has a lower risk of entrapment when trenching than a front wheel. Ultimately this model could be used in a nonprehensile manipulation planning or learning algorithm to enable autonomous trenching.

Wheels↗
NASA NTRS1998

Integration of the Remote Agent for the NASA Deep Space One Autonomy Experiment

This paper describes the integration of the Remote Agent (RA), a spacecraft autonomy system which is scheduled to control the Deep Space 1 spacecraft during a flight experiment in 1999. The RA is a reusable, model-based autonomy system that is quite different from software typically used to control an aerospace system. We describe the integration challenges we faced, how we addressed them, and the lessons learned. We focus on those aspects of integrating the RA that were either easier or more difficult than integrating a more traditional large software application because the RA is a model-based autonomous system. A number of characteristics of the RA made integration process easier. One example is the model-based nature of RA. Since the RA is model-based, most of its behavior is not hard coded into procedural program code. Instead, engineers specify high level models of the spacecraft's components from which the Remote Agent automatically derives correct system-wide behavior on the fly. This high level, modular, and declarative software description allowed some interfaces between RA components and between RA and the flight software to be automatically generated and tested for completeness against the Remote Agent's models. In addition, the Remote Agent's model-based diagnosis system automatically diagnoses when the RA models are not consistent with the behavior of the spacecraft. In flight, this feature is used to diagnose failures in the spacecraft hardware. During integration, it proved valuable in finding problems in the spacecraft simulator or flight software. In addition, when modifications are made to the spacecraft hardware or flight software, the RA models are easily changed because they only capture a description of the spacecraft. one does not have to maintain procedural code that implements the correct behavior for every expected situation. On the other hand, several features of the RA made it more difficult to integrate than typical flight software. For example, the definition of correct behavior is more difficult to specify for a system that is expected to reason about and flexibly react to its environment than for a traditional flight software system. Consequently, whenever a change is made to the RA it is more time consuming to determine if the resulting behavior is correct. We conclude the paper with a discussion of future work on the Remote Agent as well as recommendations to ease integration of similar autonomy projects.

Dorais, Gregory A.↗
NASA NTRS2017

From Prototype to Flight: Qualifying a Ka-Band Parabolic Deployable Antenna (KaPDA) for CubeSats

CubeSats have experienced a number of exciting technological advancements in the past several years. However, until recently, there has been very limited development in the area of high gain CubeSat antennas, which are critical for both high data rate communications and radar science. A Ka-band high gain antenna would provide a 10,000 times increase in data communication rates over an X-band patch antenna and a 100 times increase over state-of-the-art S-band parabolic antennas. Because of this, three years ago the Jet Propulsion Laboratory (JPL) initiated a research and technology development effort to advance CubeSat communication capabilities, with one of the key thrusts being the Ka-band parabolic deployable antenna (KaPDA). This antenna started with the ambitious goal of fitting a 42 dB, 0.5 meter, 35 Ghz antenna in a 1.5U (10 cm x 10 cm x 17 cm) canister. This paper discusses the process of taking the antenna from a first prototype to the flight design, which is flying on the RainCube mission, and earth science CubeSat. The prototype antenna was constructed in early 2015, and then upgraded to an engineering model at the end of 2016 to compensate for lessons learned. The flight version is currently under construction, and scheduled to be finished in 2016. KaPDA is the second deployable parabolic antenna to fly on a CubeSat, and the first of its kind to operate at Ka-band enabling a number of opportunities for high rate deep space antenna communications and radar science.

Sauder, Jonathan↗
NASA NTRS2012

What Have We Learned from MERRA about Reanalyses of the Stratosphere?

The Modern-Era Retrospective analysis for Research and Applications (MERRA) reanalysis includes a well-resolved middle atmosphere. The upper boundary of the underlying model is in the mesosphere, near 80km, and the input data streams include the Stratospheric Sounding Unit (SSU) and Advanced Microwave Sounding Unit (AMSU) radiance observations. These two datasets provide observational constraints on the deep-layer thermal structure in approximately the 10-2hPa region, the middle to upper stratosphere, which is above the highest range of most radiosonde ascents. This analysis will focus on the difficulties of producing realistic analyses in the middle to upper stratosphere: these arise largely because of vertical averaging inherent in the AMSU and SSU observations, the sensitivity to model biases in this region, the relative biases among the same channels on different instruments, and the orbital sampling of the satellites (morning or afternoon orbits). These issues will be illustrated with examples from MERRA and enhanced by discussions of potential ways of improving the middle atmosphere in future reanalyses.

Pawson, Steven↗
NASA NTRSDate not supplied

Cislunar Trajectory Design and Maneuver Autonomy for NASA's Moon to Mars Architecture

NASA’s Moon to Mars architecture is an ambitious roadmap of manned cislunar and deep space exploration. The extensive amount of orbital assets required will place a significant burden on ground-based resources, such as communication networks and operations facilities. Spacecraft autonomy is essential for maintaining a vast number of complex missions beyond Earth orbit. To achieve full autonomy, spacecraft must be able to employ methods of robust maneuver design without an explicit dependence on commands sent from the ground. This level of autonomy is needed not only for stationkeeping, but also for outbound transfers. To address the need of spacecraft maneuver design autonomy, this work investigates the use of neural networks (NNs) in a supervised learning environment. A supervised learning approach for NNs allows for a curated training data set, consisting exclusively of perturbations applied to a desired mission concept of operations (ConOps). The proposed approach allows humans on the ground to design a specific mission ConOps before flight, then employ NNs to fly the mission robustly and autonomously. This investigation numerically tests maneuver autonomy in four highly sensitive regions of flight: orbit raising, translunar injection burns, powered lunar flybys, and invariant manifold insertion burns. These straining cases are contextualized by testing them in a demonstration mission, targeting an Earth-Moon L3 orbit. The study first establishes feasibility by automating impulsive burn maneuvers. However, some guidance algorithms will need more intensive commands, such as inertial pointing and angular rates. To validate this method, NN maneuver autonomy is applied to a finite burn model of the demonstration mission. The use of sequential, mission specific maneuvers provide an appropriate testbed to demonstrate the robustness of a NN trained on feasible perturbed states. Moreover, these scenarios provide preliminary proof-of-concept for fully autonomous missions that execute maneuvers without dependence upon explicit command uplinks. As a result, the technological advancement proposed in this work may significantly ease the strain on ground-based mission operations. This would enable complex and autonomous mission execution in cislunar and deep space regimes, filling a technology gap required to support future manned missions.

NASA↗
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 NTRS2014

Deep Space Habitat Wireless Smart Plug

NASA has been interested in technology development for deep space exploration, and one avenue of developing these technologies is via the eXploration Habitat (X-Hab) Academic Innovation Challenge. In 2013, NASA's Deep Space Habitat (DSH) project was in need of sensors that could monitor the power consumption of various devices in the habitat with added capability to control the power to these devices for load shedding in emergency situations. Texas A&M University's Electronic Systems Engineering Technology Program (ESET) in conjunction with their Mobile Integrated Solutions Laboratory (MISL) accepted this challenge, and over the course of 2013, several undergraduate students in a Capstone design course developed five wireless DC Smart Plugs for NASA. The wireless DC Smart Plugs developed by Texas A&M in conjunction with NASA's Deep Space Habitat team is a first step in developing wireless instrumentation for future flight hardware. This paper will further discuss the X-Hab challenge and requirements set out by NASA, the detailed design and testing performed by Texas A&M, challenges faced by the team and lessons learned, and potential future work on this design.

Morgan, Joseph A.↗