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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Instructable autonomous agents

In contrast to current intelligent systems, which must be laboriously programmed for each task they are meant to perform, instructable agents can be taught new tasks and associated knowledge. This thesis presents a general theory of learning from tutorial instruction and its use to produce an instructable agent. Tutorial instruction is a particularly powerful form of instruction, because it allows the instructor to communicate whatever kind of knowledge a student needs at whatever point it is needed. To exploit this broad flexibility, however, a tutorable agent must support a full range of interaction with its instructor to learn a full range of knowledge. Thus, unlike most machine learning tasks, which target deep learning of a single kind of knowledge from a single kind of input, tutorability requires a breadth of learning from a broad range of instructional interactions. The theory of learning from tutorial instruction presented here has two parts. First, a computational model of an intelligent agent, the problem space computational model, indicates the types of knowledge that determine an agent's performance, and thus, that should be acquirable via instruction. Second, a learning technique, called situated explanation specifies how the agent learns general knowledge from instruction. The theory is embodied by an implemented agent, Instructo-Soar, built within the Soar architecture. Instructo-Soar is able to learn hierarchies of completely new tasks, to extend task knowledge to apply in new situations, and in fact to acquire every type of knowledge it uses during task performance - control knowledge, knowledge of operators' effects, state inferences, etc. - from interactive natural language instructions. This variety of learning occurs by applying the situated explanation technique to a variety of instructional interactions involving a variety of types of instructions (commands, statements, conditionals, etc.). By taking seriously the requirements of flexible tutorial instruction, Instructo-Soar demonstrates a breadth of interaction and learning capabilities that goes beyond previous instructable systems, such as learning apprentice systems. Instructo-Soar's techniques could form the basis for future 'instructable technologies' that come equipped with basic capabilities, and can be taught by novice users to perform any number of desired tasks.

Huffman, Scott Bradley↗
NASA NTRS2020

Medics: Medical Decision Support System for Long-Duration Space Exploration

The Autonomous Medical Operations (AMO) group at NASA Ames is developing a “medical decision support system” to enable astronauts on long-duration exploration missions to operate autonomously. The system will support clinical actions by providing medical interpretation advice and procedural recommendations during emergent care and clinical work performed by crew. The current state of development of the system, called MedICS (Medical Interpretation Classification and Segmentation) includes two separate aspects: a set of machine learning diagnostic models trained to analyze organ images and patient health records, and an interface to ultrasound diagnostic hardware and to medical repositories. Three sets of images of different organs and medical records were utilized for training machine learning models for various analyses, as follows: 1. Pneumothorax condition (collapsed lung). The trained model provides a positive or negative diagnosis of the condition. 2. Carotid artery occlusion. The trained model produces a diagnosis of 5 different occlusion levels (including “normal”). 3. Ocular retinal images. The model extracts optic disc pixels (image segmentation). This is a precursor step for advanced autonomous fundus clinical evaluation algorithms to be implemented in FY20. 4. Medical health records. The model produces a differential diagnosis for any particular individual, based on symptoms and other health and demographic information. A probability is calculated for each of 25 most common conditions. The same model provides the likelihood of survival. All results are provided with a confidence level. Item 1 images were provided by the US Army and were part of a data set for the clinical treatment of injured battlefield soldiers. This condition is relevant to possible space mishaps, due to pressure management issues. Item 2 images were provided by Houston Methodist Hospital, and item 3 health records were acquired from the MIT laboratory of computational physiology. The machine learning technology utilized is deep multilayer networks (Deep Learning), and new models will continue to be produced, as relevant data is made available and specific health needs of astronaut crews are identified. The interfacing aspects of the system include a GUI for running the different models, and retrieving and storing data, as well as support for integration with an augmented reality (AR) system deployed at JSC by Tietronix Software Inc. (HoloLens). The AR system provides guidance for the placement of an ultrasound transducer that captures images to be sent to the MedICS system for diagnosis. The image captured and the associated diagnosis appear in the technician’s AR visual display.

Colombano, Silvano↗
NASA NTRSDate not supplied

Autonomous Spacecraft Attitude Control Using Deep Reinforcement Learning

While machine learning and spacecraft autonomy continue to gain research interest, significant work remains to be done in efficiently applying modern machine learning techniques to problems in space ight. This study presents a framework for deriving a discrete neural spacecraft attitude controller using reinforcement learning, a paradigm of machine learning, without the need for high-performance computing. The developed attitude controller is an approximately time-optimal solution to a highly constrained control problem, able to achieve well above industry-standard pointing accuracies. Control examples are also presented of the agent performing large-angle spacecraft slews in the developed simulation environment and future extensions of this work are discussed.

ATAP↗
NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

To support sustainable infrastructure on the Moon, NASA needs to leverage lunar resources for in-situ processing and construction. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for these tasks. To reliably perform these operations on the lunar surface, RASSOR's sensors and control systems need to be robust and maximize information extracted from a reduced sensor payload. Herein, we present our findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments in which we applied reinforcement learning algorithms to learn autonomous trenching controllers and produced state estimation architectures. We developed two simulations: a 2D excavation simulation used to facilitate parameter selection, and a 3D simulation developed using a game physics engine to simulate simplified soil interactions and incorporate robotic agents parameterized by dynamic models. Within these simulations, we learned autonomous excavation routines that exceed excavation efficiency measures as compared against RASSOR's existing control and teleoperation-based methods.

RASSOR↗
NASA NTRSDate not supplied

Towards Autonomous Lunar Resource Excavation via Deep Reinforcement Learning

To support sustainable infrastructure on the Moon, NASA needs to leverage lunar resources for in-situ processing and construction. NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for these tasks. To reliably perform these operations on the lunar surface, RASSOR's sensors and control systems need to be robust and maximize information extracted from a reduced sensor payload. Herein, we present our findings from the Intelligent Capabilities Enhanced RASSOR project. We created reduced-order simulation environments in which we applied reinforcement learning algorithms to learn autonomous trenching controllers and produced state estimation architectures. We developed two simulations: a 2D excavation simulation used to facilitate parameter selection, and a 3D simulation developed using a game physics engine to simulate simplified soil interactions and incorporate robotic agents parameterized by dynamic models. Within these simulations, we learned autonomous excavation routines that exceed excavation efficiency measures as compared against RASSOR's existing control and teleoperation-based methods.

RASSOR↗
NASA NTRS2022

Spatial Grid-Based Object Localization from A Single Passive Sensor: A Deep Learning-Integrated Approach

Ongoing efforts at NASA’s Langley Research Center have produced a single passive sensor system for detecting ground objects and pinpointing their real-world location to a desired level of precision. The Langley center serves as a test range for unmanned aerial systems (UAS) and real-time knowledge about the location of people on campus is needed to inform least-risk UAS flight operations. The proposed system provides this knowledge through a camera combined with a convolutional neural network and an algorithm that projects an imaginary grid of square cells from the ground plane onto the perspective view of the camera. The position of detected objects on the camera’s projected grid determines their location in the real-world. The imaginary grid is easily mapped to a universal coordinate system, such as longitude and latitude, to provide both relative and absolute positional information of the detected objects. This simple system is shown to be accurate and effective, with decisive advantages over alternative multi-sensor and active sensor approaches. Extensions to the system are described to allow adaptation to a variety of other use cases.

object localization↗
NASA NTRS2022

Machine learning for Deep Space Network antenna motions detection

Highly stable frequency and timing standards are essential for deep-space missions and radio science. At the NASA Deep Space Network (DSN), these standards are distributed through a network of underground fiber cables to support several Goldstone antennas. Independently developed frequency-measuring instruments generate tremendous quantities of data to monitor and validate the antennas’ stringent frequency requirements. In this paper, we propose a lightweight processing tool capable of detecting disturbances on the frequency signal caused by DSN antenna motions. Our training data is sampled from the movement log of the antenna of interest and the generated data from the fiber optic metrology instrument linked to the antenna. We demonstrate that a convolutional neural network (CNN) model can achieve high accuracies on classifying instances of antenna movements and is an effective predictor when used iteratively on longer, variable stretches of metrology data. The simplicity, low training cost, and high accuracies of our model strongly suggest its efficacy in identifying and troubleshooting frequency disturbances caused by the antenna.

Yi, Lin↗
DOE OSTI2025

Rapid wavefield forecasting for earthquake early warning via deep sequence to sequence learning

We propose a deep learning model, WaveCastNet, to forecast high-dimensional wavefields. WaveCastNet integrates a convolutional long expressive memory architecture into a sequence-to-sequence forecasting framework, enabling it to model long-term dependencies and multiscale patterns in both space and time. By sharing weights across spatial and temporal dimensions, WaveCastNet requires significantly fewer parameters than more resource-intensive models such as transformers, resulting in faster inference times. Crucially, WaveCastNet also generalizes better than transformers to rare and critical seismic scenarios, such as high-magnitude earthquakes. Here, we show the ability of the model to predict the intensity and timing of destructive ground motions in real time, using simulated data from the San Francisco Bay Area. Furthermore, we demonstrate its zero-shot capabilities by evaluating WaveCastNet on real earthquake data. Our approach does not require estimating earthquake magnitudes and epicenters, steps that are prone to error in conventional methods, nor does it rely on empirical ground-motion models, which often fail to capture strongly heterogeneous wave propagation effects.

Geophysics↗