Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learned”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 1,783 records · Page 99

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↗

Machine Learning for Extravehicular Mobility Unit (EMU) Glove Inspections

The Extravehicular Mobility Unit (EMU) Glove Machine Learning Inspection project utilizes machine learning to expedite the inspection, analysis, and recommendation for continued use of space suit gloves post spacewalks. Today, ISS glove photos are individually reviewed by a team of experts to determine the conditions of space suit gloves. For this project the Microsoft Azure platform is used to perform Automated Machine Learning (AutoML) to detect issues with tagged images from previous Extravehicular Activities (EVA’s) to build a predictive model. The model analyzes a test image and deems the glove GO or NO-GO for additional EVA’s. The goal for this ML project is to decrease the time spent reviewing images by ground personnel and crewmembers in high frequency EVA locations such as the Moon and Mars. For destinations such as the Moon and Mars the goal is to give crew autonomy in determining glove conditions with limited support from Earth. This paper will outline the results to date and future work needed to expand the capability for in-situ recommendations.

EVA↗

Collision Avoidance Approach Using Deep Reinforcement Learning

A method to enable autonomous robots moving in a 2D space collision free motivates the purposed approach for collision avoidance for autonomous UAM vehicles. Challenges of autonomous collision free navigation for both problems are similar. Agents in each environment do not know the intent, or goal, of the other. Finding the time efficient paths require some level of anticipation with neighboring agents which is computationally expensive. In the original work, these obstacles were overcome with a novel application of deep reinforcement learning which offloads the online computation to an offline learning algorithm. A value network that encodes the estimated time to the goal given the agent’s state and the observable portion of the other agent’s state is trained on a baseline policy and further refined with reinforcement learning to promote time efficient collision free navigation. Online, the value network efficiently informs the agent’s decision making in the face of uncertainty of the other agent’s next move. In this paper, challenges extending this methodology to the 3D environment of autonomous UAM vehicles with kinematic constraints are discussed and initial results shown.

Collision Avoidance↗

Collision Avoidance Approach Using Deep Reinforcement Learning

A method to enable autonomous robots moving in a 2D space collision free motivates the purposed approach for collision avoidance for autonomous UAM vehicles. Challenges of autonomous collision free navigation for both problems are similar. Agents in each environment do not know the intent, or goal, of the other. Finding the time efficient paths require some level of anticipation with neighboring agents which is computationally expensive. In the original work, these obstacles were overcome with a novel application of deep reinforcement learning which offloads the online computation to an offline learning algorithm. A value network that encodes the estimated time to the goal given the agent’s state and the observable portion of the other agent’s state is trained on a baseline policy and further refined with reinforcement learning to promote time efficient collision free navigation. Online, the value network efficiently informs the agent’s decision making in the face of uncertainty of the other agent’s next move. In this paper, challenges extending this methodology to the 3D environment of autonomous UAM vehicles with kinematic constraints are discussed and initial results shown.

Collision Avoidance↗

MLtool: Universal Supervised Machine Learning Tool to Model Tabulated Data

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine learning↗

Advancements in Blowing Dust Detection at Night via Machine Learning

This presentation introduces operational users to a machine-learning based Dust Probability product developed by the NASA SPoRT program for the application of detecting and monitoring blowing dust plumes at night. Advances in earth observing satellites has improved monitoring and detection of dust both day and night through derived imagery such as the Dust RGB. However, limitations of the RGB at night result in less contrast between dust and land surface features, as seen by the user. A Machine Learning (ML) model has been developed and applied to GOES-16 ABI to overcome this limitation and improve nighttime dust detection. The ML capability is a subset of Artificial Intelligence methods. In this case the Dust ML model was developed using a simple Random Forest (RF) model, typically used to solve classification challenges (or to provide regression type output). The goal was to leverage the strengths of the RF model to learn how to identify blowing dust, and hence, overcome the limitation of a user trying to detect blowing dust within the satellite imagery by eye alone. A brief description of the ML model development will be provided. However, the focus of the presentation will be on the initial user feedback from the assessment of this tool for the 2022 blowing dust events of March through April. During this time several users across the U.S. Southwest collaborated to apply this Dust ML product at night as a complement to the existing Dust RGB in order to determine if it provided greater operational efficiency and value.

Machine Learning↗

Comparisons of Performance Metrics and Machine Learning Methods on an Entry Descent and Landing Database

This work focuses on evaluating machine learning methods and their applicability to the generation of an aerodynamic database, particularly for trajectory analysis of a capsule during entry, descent, and landing with a focus on uncertainty quantification. The source data to be used is the wind tunnel and computational data for the Integrated Design Assessment Team (IDAT) configuration of the Orion project, which has been publicly released. The methods used to generate the proposed databases are designed to naturally include a prediction interval, which will be evaluated both for their mean response as well as how well the prediction interval performs. These machine learning methods are compared to a traditionally generated database used by the Orion team as a baseline. It is found that while these machine learning methods perform well, the Orion database tends to still outperform them showing that engineering experience is still needed to make the best database possible. However, these methods still provide comparable results with significantly less effort.

Orion↗

Using Machine Learning for Timely Estimates of Ocean Color Information From Hyperspectral Satellite Measurements in the Presence of Clouds, Aerosols, and Sunglint

Retrievals of ocean color from space are important for better understanding of the ocean ecosystem but can be limited under conditions such as clouds, aerosols, and sunglint. Many ocean color algorithms use a few selected spectral bands to perform an atmospheric correction and then derive the upwelling radiance from the ocean. The limitations in the atmospheric correction under certain conditions lead to many gaps in daily spatial coverage of ocean color retrievals. To address these limitations, we introduce a new approach that uses machine learning to estimate ocean color from top of atmosphere radiances or reflectance measurements. In this approach, a principal component analysis is used to decompose the hyperspectral measurements into spectral features that describe the scattering and absorption of the atmosphere and the underlying surface. The coefficients of the principal components are then used to train a neural network to predict ocean color properties derived from the MODIS atmospheric correction algorithm. This machine learning approach is independent of a priori information and does not rely on any radiative transfer modeling. We apply the approach to two hyperspectral UV/VIS instruments, the ozone monitoring instrument (OMI) and the TROPOspheric Monitoring Instrument (TROPOMI), using measurements from 320–500 nm to show that it can be used to reproduce ocean color properties in less-than-ideal conditions. This machine learning approach complements the current atmospheric correction ocean color retrievals by filling in the gaps resulting from cloud, aerosol, and sunglint contamination. This method can be applied to the future hyperspectral Ocean Color Instrument (OCI), which will be onboard NASA’s Plankton, Aerosol Cloud, ocean Ecosystem (PACE) ocean color satellite set to launch in 2024.

Ocean color↗

Comparisons of Performance Metrics and Machine Learning Methods on an Entry, Descent, and Landing Database

This work focuses on evaluating machine learning methods and their applicability to the generation of an aerodynamic database, particularly for trajectory analysis of a capsule during entry, descent, and landing with a focus on uncertainty quantification. The source data to be used is the wind tunnel and computational data for the Integrated Design Assessment Team (IDAT) configuration of the Orion project, which has been publicly released. The methods used to generate the proposed databases are designed to naturally include a prediction interval, which will be evaluated both for their mean response as well as how well the prediction interval performs. These machine learning methods are compared to a traditionally generated database used by the Orion team as a baseline. It is found that while these machine learning methods perform well, the Orion database tends to still outperform them showing that engineering experience is still needed to make the best database possible. However, these methods still provide comparable results with significantly less effort.

Orion↗

A Machine Learning Model for Solar Sail Shape Reconstruction Using Flight Data

Solar sail deformation leads to disturbance torques from solar radiation pressure, driving performance requirements for momentum management systems. For the Solar Cruiser technology demonstrator mission, we have developed a model leveraging neural network-based machine learning to derive sail shape characteristics. The model uses torque and attitude telemetry simulated from a reduced-order tensor model of the deformed sail mesh over a characterization sequence. The machine learning model predicts sail boom deflection with comparable accuracy to that of an onboard context camera. This model can discover sail shape with no additional mass or data downlink requirements, allowing for validation of sail force modeling assumptions using in flight data. The results from the project hold promise for the further implementation of machine learning techniques in solar sail telemetry analysis and control.

solar sail↗

A Machine Learning Model for Solar Sail Shape Reconstruction Using Flight Data

Solar sail deformation leads to disturbance torques from solar radiation pressure, driving performance requirements for momentum management systems. For the Solar Cruiser technology demonstrator mission, we have developed a model leveraging neural network-based machine learning to derive sail shape characteristics. The model uses torque and attitude telemetry simulated from a reduced-order tensor model of the deformed sail mesh over a characterization sequence. The machine learning model predicts sail boom deflection with comparable accuracy to that of an onboard context camera. This model can discover sail shape with no additional mass or data downlink requirements, allowing for validation of sail force modeling assumptions using in flight data. The results from the project hold promise for the further implementation of machine learning techniques in solar sail telemetry analysis and control.

solar sail↗

Machine Learning for the Validation of Expert-Elicited Causal Risk Diagrams

Exposure to spaceflight poses risk to human health in complex ways. To help manage this risk, the Human Systems Risk Board (HSRB) at the National Aeronautics and Space Administration (NASA) maintains a set of causal diagrams that attempt to explain how spaceflight hazards generate health risks and lead to adverse outcomes both in-mission, immediately post-mission, and over the long term. These causal risk diagrams are formulated as directed acyclic graphs (DAGs) and can function as knowledge graphs of connected risks and outcomes. These DAGs have proven useful for communication, and, through network analysis, have allowed for the identification of structurally important factors in the risk network. However, the utility these DAGs provide is directly proportional to their verisimilitude, making assessment of this trait using empirical data – whether from actual human spaceflight or various spaceflight analogue exposures and model organisms – a high priority. In this research we explore the use of machine learning algorithms to learn DAG structure from empirical data as a means of evaluating human-elicited DAG structures. To do so, we test several different graph structure-learning algorithms on data concerning changes in the bones of rats and mice after exposure to either spaceflight or a spaceflight analogue. We explore potential methods for indexing the similarity between each algorithm’s output DAG with all the others and with that of the expert-elicited DAG. We discuss next steps in this ongoing line of research and open science initiatives underway to complete them.

directed acyclic graphs↗

Evaluating Machine Learning Approaches to Plume Tracking

On July 15, 2022, the Hunga Tonga-Hunga Ha’apai (HTHH) submarine volcano erupted, propelling trace gasses and ash through the troposphere and up into the stratosphere. Previous studies manually tracked the aerosol and trace gas plumes over time across different positions in the southern hemisphere. Using imagery from NASA’s Earth Observing System, including MODIS aerosol products and OMI sulfur dioxide products, this research demonstrates how open-source machine learning (ML) models, like Meta’s Segment Anything Model (SAM), can perform automatic plume tracking following the Hunga Tonga eruption. This extensible methodology, and modular data processing and modeling pipeline, establishes a framework for systematically and rapidly studying natural disasters, including additional volcanic eruptions and large-scale wildfires. By combining advanced machine learning techniques, such as SAM’s zero-shot learning, with large volumes of NASA’s Earth Observation and remote sensing data, this work shows how AI and open science can accelerate research and generate actionable results, even for unprecedented events. The tools and technologies presented here can help translate earth science to action from NASA’s current and future Earth observing satellite missions, and assist researchers and stakeholders in understanding, mapping, and responding to natural disasters in a changing world.

machine learning↗

Energy-Optimized Path Planning for Uas in Varying Winds Via Reinforcement Learning

In this paper we propose a reinforcement learning (RL) algorithm for path planning of Unmanned Aviation Vehicles (UAVs) under varying wind conditions. Solutions to UAV path planning problems are becoming increasingly necessary as autonomous UAVs continue to enter commercial and government spaces. Path-planning is inherently challenging, as UAVs need to account for dynamically changing flying conditions such as weather, obstacle or no-fly zones, degraded vehicle health, and off-nominal battery power consumption. Machine learning methods such as reinforcement learning (RL) have the potential to revolutionize how vehicles navigate in such uncertain environments. In this study, we compute UAV trajectories from a pre-determined starting position to a target cell within a 7X7 grid environment by optimizing parameters for mission assurance and safety limits in addition to the energy consumption and operation time. The UAV navigates the grid by taking actions to move in any of the eight cardinal and inter-cardinal directions, under constant thrust profile. The resultant UAV state is sampled from a probability distribution which accounts for the UAV’s action, local wind velocity, and the presence of obstacles or boundaries. As the unmanned airspace gets more complex due to multiple vehicles and environmental uncertainties, trade-offs between energy consumption, operation time, risk tolerance, and mission assurance need to be made. Our Markov Decision Process (MDP) environment model can capture any combination of these in the optimization objective, making it novel compared to other work in the field.

trajectory planning↗

Using Machine Learning to Estimate Surface-Level SO2 Concentrations from Satellite-Based Measurements

Sulfur dioxide (SO2) is a criteria air pollutant due to its contributions to aerosol formation, rainfall acidification, and harm to human health. The placement of air quality monitoring sites is typically biased towards urban areas, leaving large areas with very limited monitoring data. The Ozone Monitoring Instrument (OMI) has been used to provide estimates of SO2 vertical column densities (VCDs) globally at spatial resolution of 10s of kms once per day. OMI SO2 VCDs have been previously used to estimate surface SO2 concentrations using chemical transport model (CTM) simulations. The CTMs use estimated emissions and assimilated meteorological data, and simulate the chemical and physical processes that determine the vertical profile of SO2, which can be used to derive a ratio between the surface concentrations and VCDs. These models are complex, computationally expensive, and have large uncertainties in the simulated surface-to-VCD ratio due to biases in emissions and relatively coarse resolution. Machine learning techniques are comparatively easier to use, much less computationally expensive to use after training, and can produce more accurate estimations of surface concentrations than the CTM-based method. The interpretation of machine learning models often poses challenges, and in some cases, non-physical variables unrelated to SO2 are used as predictors. In this work, we create an artificial neural network (ANN) to relate OMI retrievals and archived GEOS-FP boundary layer heights to surface SO2 concentrations from the ChinaHighAirPollutants ChinaHighSO2 dataset (CHAP; Wei et al., 2023) on a seasonal average timescale from 2013-2018. Our model only utilizes five variables that are directly relevant to the satellite retrieval, lifetime, and spatial distribution of SO2. The model was trained on 16 seasons (four of each) with independent validation (one of each season) and testing datasets (one of each season) to avoid overfitting. Our ANN generates surface SO2 concentrations that are sensitive (slope = 0.51) and consistent (r = 0.74) with the CHAP data, but are underpredicted by an average of 1.2 ppbv with a mean absolute error of 2.2 ppbv. These results are better than recent studies utilizing the CTM method. To our knowledge, this is the best performing machine learning model that only uses physical variables to predict surface SO2. Our work demonstrates that a carefully constructed, simple ML model can accurately estimate surface-based SO2 concentrations from satellite VCD measurements, and this technique has future promise to expend to newer, higher resolution satellites and other air pollutants.

SO2, air quality, OMI, machine learning↗

The Development and Deployment of Machine Learning Models for Aircraft Engine Concept Assessment

In today's competitive landscape, the effective development and utilization of machine-learning (ML) applications have become crucial across diverse economic sectors. This study presents an outline of the procedure involved in creating and implementing ML models for conceptualizing and evaluating aircraft engines. These models leverage supervised deep-learning algorithms to analyze patterns within an open-source repository containing data on both production and research conventional turbofan engines. The main areas of focus encompass crucial engine parameters like thrust-specific fuel consumption (TSFC), engine weight, engine diameter, and turbomachinery stage counts. While the creation of ML models is fundamental for their utilization, ensuring their seamless deployment holds equal significance. To address this aspect, a conversational AI chatbot that specifically focuses on propulsion has been developed. Leveraging natural language processing (NLP) techniques, this chatbot simplifies the deployment of machine learning (ML) models. The comprehensive workflow encompasses several key stages: gathering and enhancing engine data, training and cross validating the ML models, testing and evaluating their performance, and finally, deploying, monitoring, and updating the ML models. By following this systematic approach, the aim is to streamline the development and deployment process of ML models tailored for aircraft engine assessment.

AI Chatbot↗

Lunar Browser Utilization of Machine Learning for Trajectory Solution Production

This paper describes the application of machine learning tools to produce Earth-Moon spacecraft trajectories with applications to NASA’s Commercial Lunar Payload Services (CLPS) and Artemis Human Landing System (HLS) programs. Existing trajectory solutions are used to train and test machine learning models to predict essential details of a trajectory sequence from Earth-launch to Low-Lunar Orbit, populating a database of solutions with future launch dates. The machine learning model will implement hyperparameter optimization for further re-training to improve model performance. Accurate predictive models decrease the time required to produce solutions and are readily implemented in the Lunar Browser tool.

Trajectory Design↗

A Frank Discussion on Lessons Learned From Adopting and Applying NASA-STD-6030 for Spaceflight Systems

With the advancement and adoption of Additive Manufacturing (AM) for spaceflight systems, numerous lessons have been learned during the qualification and certification of AM components. The lessons learned covered in this presentation will provide an overview of the challenges faced by NASA centers and commercial partners working to design AM hardware that complies with NASA-STD-6030 Additive Manufacturing Requirements (AMR). Topics of interest include tailoring of requirements for specific projects, documentation requirements, and addressing conservative approaches towards mechanical property development and analysis. In addition to that, this presentation aims to impress that these lessons learned will influence the future revisions of the NASA technical standard to facilitate and advance AM technology adoption on NASA projects.

Additive Manufacturing↗