Search NASA⌕ Search

SEARCH · Search NASA

Results for “operator 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRS2018

Cognitive Anti-Jamming Satellite-To-Ground Communications on NASA's SCaN Testbed

Machine learning aided cognitive anti-jamming communications is designed, developed and demonstrated on a live satellite-to-ground link. A wideband autonomous cognitive radio (WACR) is designed and implemented as a hardware-in-the- loop (HITL) prototype. The cognitive engine (CE) of the WACR is implemented on a PC while the software-defined radio (SDR) platform utilized two different radios for spectrum sensing and actual communications. The cognitive engine performs spectrum knowledge acquisition over the complete spectrum range available for the SATCOM system operation and learns an anti-jamming communications protocol to avoid both intentional jammers and inadvertent interferers using reinforcement learning. When the current satellite-to-ground link is jammed, the cognitive engine of the ground receiver directs the satellite transmitter to switch to a new channel that is predicted to be jammer-free for the longest possible duration. The end-to-end, closed-loop system was tested on the NASA Space Communications and Navigation (SCaN) Testbed on the International Space Station (ISS). The experimental results demonstrated the feasibility of satellite-to-ground cognitive anti-jamming communications along with excellent anti-jamming capability of machine learning aided cognitive protocols against several different types of jammers.

Jayaweera, Sudharman K.↗
NASA NTRS2018

Cognitive Anti-jamming Satellite-to-Ground Communications on NASA's SCaN Testbed

Machine learning aided cognitive anti-jamming communications is designed, developed and demonstrated on an experimental satellite-to-ground link. A wideband autonomous cognitive radio (WACR) is designed and implemented as a hardware-in the-loop (HITL) prototype. The cognitive engine (CE) of the WACR is implemented on a PC while the software-defined radio (SDR) platform utilized two different radios for spectrum sensing and actual communications. The cognitive engine performs spectrum knowledge acquisition over the complete spectrum range available for the SATCOM system operation and learns an anti-jamming communications protocol to avoid both intentional jammers and inadvertent interferers using reinforcement learning. When the current satellite-to-ground link is jammed, the cognitive engine of the ground receiver directs the satellite transmitter to switch to a new channel that is predicted to be jammer-free for the longest possible duration. The end-to-end, closed-loop system was tested with the NASA's Space Communications and Networking (SCaN) testbed on the International Space Station (ISS). The experimental results demonstrated the feasibility of satellite-to-ground cognitive anti-jamming communications along with excellent anti-jamming capability of machine-learning aided cognitive protocols against several different types of jammers.

Jayaweera, Sudharman K.↗
NASA NTRSDate not supplied

Using Artificial Intelligence and Machine Learning to Enhance Mission Design and Operations of the Habitable Worlds Observatory (HWO)

One key aspect in the development of HWO is the early deployment of artificial intelligence (AI) and machine learning (ML) to enhance mission science and operations. Our subtask group is part of the HWO AI/ML working group and focuses on AI and ML for mission operations. Our task group seeks to educate other HWO working groups about AI and ML capabilities for mission operations, investigate how to bridge technology gaps, and enable new capabilities particularly in the areas of observational scheduling, instrument health monitoring, and downlink operations. We focus on mission tasking / scheduling both for mission analysis in development and operations. AI and ML for mission scheduling includes: tools to support proposal calls and review, ensuring fairness in calls for proposals, community peer reviews and ease workloads, as well as in-flight and ground software development (e.g., using natural language processing (NLP) to support process automation from requirements). AI and ML for the mission’s development and operations include 1) anomaly detection and prediction (from onboard and ground based tools) to monitor the spacecraft’s health, 2) ground-based automated scheduling for mission operations including long-term and short-term planning and maintenance, and 3) flight system flexible execution (as flight proven for Spitzer and JWST) to enable robust execution despite execution variations, and 4) data analysis for prioritization (e.g., real-time data evaluation leading to autonomous actions and adjustments, high-priority identification, onboard data compression, etc.). Incorporation of ML and AI will enable HWO to address the major science questions related to exoplanet characterization, general astrophysics, and solar system exploration and also extend the boundaries of space mission technologies.

Mark Moussa↗
NASA NTRSDate not supplied

ICE-RASSOR: Intelligent Capabilities Enhanced Regolith Advanced Surface Systems Operations Robot

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU)processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from a reduced sensor payload. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and prototype state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗
NASA NTRSDate not supplied

ICE-RASSOR: Intelligent Capabilities Enhanced Regolith Advanced Surface Systems Operations Robot

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RASSOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar surface, RASSOR software and sensory systems need to be robust and maximize the information extracted from on-board sensory. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and proto-type state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗
NASA NTRS2014

First Results from the Mojave Volatiles Prospector (MVP) Field Campaign, a Lunar Polar Rover Mission Analog

The Mojave Volatiles Prospector (MVP) project is a science-driven field program with the goal to produce critical knowledge for conducting robotic exploration of the Moon. MVP will feed science, payload, and operational lessons learned to the development of a real-time, short-duration lunar polar volatiles prospecting mission. MVP achieves these goals through a simulated lunar rover mission to investigate the composition and distribution of surface and subsurface volatiles in a natural and a priori unknown environment within the Mojave Desert, improving our understanding of how to find, characterize, and access volatiles on the Moon. The MVP field site is the Mojave Desert, selected for its low, naturally occurring water abundance. The Mojave typically has on the order of 2-6% water, making it a suitable lunar analog for this field test. MVP uses the Near Infrared and Visible Spectrometer Subsystem (NIRVSS), Neutron Spectrometer Subsystem (NSS), and a downward facing GroundCam camera on the KREX-2 rover to investigate the relationship between the distribution of volatiles and soil crust variation. Through this investigation, we mature robotic in situ instruments and concepts of instrument operations, improve ground software tools for real time science, and carry out publishable research on the water cycle and its connection to geomorphology and mineralogy in desert environments. A lunar polar rover mission is unlike prior space missions and requires a new concept of operations. The rover must navigate 3-5 km of terrain and examine multiple sites in in just ~6 days. Operational decisions must be made in real time, requiring constant situational awareness, data analysis and rapid turnaround decision support tools. This presentation will focus on the first science results and operational architecture findings from the MVP field deployment relevant to a lunar polar rover mission.

Heldmann, Jennifer L.↗
NASA NTRSDate not supplied

ICE-RASSOR: Intelligent Capabilities Enhanced

NASA’s Regolith Advanced Surface Systems Operations Robot (RASSOR) is principally designed to mine and deliver regolith for In-Situ Resource Utilization (ISRU) processing. RAS-SOR’s design enables it to efficiently collect and deposit regolith, return collected material for processing, and myriad related ISRU activities. To reliably perform these operations on the lunar sur-face, RASSOR software and sensory systems need to be robust and maximize the information extracted from on-board sensing. Herein, we present preliminary findings from the Intelligent Capabilities Enhanced RASSOR project. We apply supervised learning using real data to estimate the soil mass collected without the need for mass flow rate monitors or other explicate sensing techniques. We also create a reduced-order simulation environment to develop autonomous trenching controllers via reinforcement learning and proto-type state estimation architectures. Our initial results suggest that excavated regolith mass can be inferred within 2.9% RMS error of full scale, and reinforcement learning for autonomous operations has learned viable trenching strategies and helped identify desirable sensing capabilities, arrangements, and considerations. Future work includes regolith mass estimation during dynamic operation, expanding our simulation to more complex environments, and transfer learning from simulation to hardware.

machine learning↗
NASA NTRS2018

Initial Operations Experience and Results from the Juno Gravity Experiment

Radio communications between the Juno spacecraft, in orbit around Jupiter, and the Earth-based observing stations of NASA’s Deep Space Network enable measurements of the Doppler shift induced on the radio signals by Juno’s motion in the Jovian environment. This measurement of the Doppler shift improves the knowledge of Jupiter’s gravitational field. As a radio science instrument, Juno’s gravity science instrument utilizes a ground component at the Deep Space Network’s DSS-25 antenna, equipped with simultaneous dual X- and Ka-band transmitters and receivers, and a spacecraft component, which includes X- and Ka-band transponders to relay the transmitted signal back to Earth. Originally planned to be in 14-day orbits around Jupiter, a risk identified in the propulsion system led to the decision to stay in the 53-day orbit period. Rapid turnaround of observation planning led to successful near-term perijove passes. Although maintaining a 53-day orbit period provides a scientific benefit to the gravity science investigation, the longer orbit period further increases the large dynamic range in Doppler shift and pointing angles induced by the geometry of each perijove. Between entering orbit at Jupiter on July 5, 2016 and September 2017, the Juno spacecraft has executed eight closest approach periods every 53 days where science data was collected. The first five perijove passes were conducted in different telecom configurations, each presenting unique challenges in data collection and processing. Perijoves PJ-01, PJ-02, PJ-03, and PJ-06 utilized the high-gain antenna and various configurations of the X- and Ka-bands. Perijoves PJ-04 and PJ-05 utilized the medium-gain antenna at X-band only while the spacecraft was off-Earth point. Additional perijoves are planned every 53-days, with an additional five by March 2018. Lessons learned from operating and collecting data at each perijove are documented and will be utilized in future perijoves. Analysis of the first two gravity science perijoves has improved the precision of Jupiter’s gravity field by a factor of five, providing crucial constraints on the interior structure of Jupiter.

Buccino, Dustin↗
NASA NTRS1998

Lessons Learned During Implementation and Early Operations of the DS1 Beacon Monitor Experiment

A new approach to mission operations will be flight validated on NASA's New Millennium Program Deep Space One (DS1) mission which launched in October 1998. The Beacon Monitor Operations Technology is aimed at decreasing the total volume of downlinked engineering telemetry by reducing the frequency of downlink and the volume of data received per pass. Cost savings are achieved by reducing the amount of routine telemetry processing and analysis performed by ground staff. The technology is required for upcoming NASA missions to Pluto, Europa, and possibly some other missions. With beacon monitoring, the spacecraft will assess its own health and will transmit one of four beacon messages each representing a unique frequency tone to inform the ground how urgent it is to track the spacecraft for telemetry. If all conditions are nominal, the tone provides periodic assurance to ground personnel that the mission is proceeding as planned without having to receive and analyze downlinked telemetry. If there is a problem, the tone will indicate that tracking is required and the resulting telemetry will contain a concise summary of what has occurred since the last telemetry pass. The primary components of the technology are a tone monitoring technology, AI-based software for onboard engineering data summarization, and a ground response system. In addition, there is a ground visualization system for telemetry summaries. This paper includes a description of the Beacon monitor concept, the trade-offs with adapting that concept as a technology experiment, the current state of the resulting implementation on DS1, and our lessons learned during the initial checkout phase of the mission. Applicability to future missions is also included.

Sherwood, Rob↗
DOE OSTI2025

Improving the prediction of daily reservoir releases over the CONUS using conditioned LSTM

Reservoirs play a vital role in regulating streamflow timing and variability for hydroelectricity, flood control, water supply, irrigation, and recreation. Despite their importance, many reservoirs lack comprehensive operational guidelines, making their management complex due to conflicting operational objectives. Hence traditional policy-based reservoir models often fail to capture real-world conditions accurately and they depend on perfect streamflow predictions, which are not always available. In contrast, data-driven models like Long Short-Term Memory (LSTM) networks offer a robust alternative. This study introduces an approach that integrates reservoir characteristics—such as main use, climate, and maximum capacity—into the LSTM model to enhance reservoir release predictions. Using data from nearly 200 reservoirs in the contiguous United States (CONUS), our conditioned LSTM model (LSTM_cond) was compared with both the vanila LSTM and a traditional policy-based approach. Furthermore, our results show that while both LSTM_cond and LSTM perfoms better than the policy-based approach, LSTM_cond consistently outperforms LSTM for hydroelectric, water supply, irrigation, and recreation reservoirs. The KGE median values for LSTM_cond for out-sample reservoirs are 0.764, 0.565, 0.821, and 0.779, respectively, for the aforementioned reservoir types, which are consistently higher that the corresponding KGE values of 0.737, 0.413, 0.775, and 0.713 of LSTM, demonstrating its advantages in improving generalizability.

CONUS↗
DOE OSTI2026

Optimization of the FRIB beam dump: a hybrid genetic algorithm and reinforcement learning approach

The operational envelope of high-power-density systems, such as particle accelerators and advanced nuclear energy systems, is critically constrained by the need to manage extreme thermal loads. To address this, we present a novel hybrid optimization framework combining a genetic algorithm (GA) with a soft actor-critic (SAC) deep reinforcement learning agent. This framework was applied to a practical high-heat-flux problem: redesigning the beam dump at the Facility for Rare Isotope Beams (FRIB) for a power upgrade from 20 kW to 50 kW. The resulting design, validated by three-dimensional conjugate heat transfer simulations, suppresses hazardous hot spots and yields a markedly more uniform temperature distribution. This provides a robust operating margin, increasing the average power-handling capability by 72% relative to the current design, demonstrating the framework’s potential to solve complex thermal management challenges in both accelerator technology and advanced nuclear systems.

Accelerator↗
NASA NTRS2015

Lessons Learned from Optical Payload for Lasercomm Science (OPALS) Mission Operations

This paper provides an overview of Optical Payload for Lasercomm Science (OPALS) activities and lessons learned during mission operations. Activities described cover the periods of commissioning, prime, and extended mission operations, during which primary and secondary mission objectives were achieved for demonstrating space-to-ground optical communications. Lessons learned cover Mission Operations System topics in areas of: architecture verification and validation, staffing, mission support area, workstations, workstation tools, interfaces with support services, supporting ground stations, team training, procedures, flight software upgrades, post-processing tools, and public outreach.

Sindiy, Oleg V.↗
DOE OSTI2025

Optimizing inference of segmentation on high-resolution images in MLExchange

MLExchange is a machine learning (ML) operations platform providing web user-interfaces (UIs) for data visualization and analysis pipelines at synchrotron facilities. Among these UIs is the segmentation app which helps synchrotron users utilize ML algorithms to automatically segment high-resolution scientific images with minimal manual annotation effort. In this work, we share code optimizations that significantly speed up the segmentation inference workflow of large data in short time. By optimizing the sequence of CPU-GPU data transfers and introducing CPU parallelization to key operations, we improve the per-device, per-image frame computational efficiency and observe close to 3×$$\times$$ speedup over the original segmentation inference workflow run time when utilizing a single GPU. Further adaptations enabling multi-GPU inference yield more than 40×$$\times$$ speedup with 100 GPUs compared to the optimized single GPU inference workflow. This acceleration of the segmentation inference workflow will provide MLExchange users with easy access to segmentation results with little wait time.

Lu, Shizhao↗
DOE OSTI2025

Lessons learned from the design and operation of a small-scale cross-flow tidal turbine

In 2023, a first-generation prototype of a small-scale marine current turbine was operated in Sequim Bay, Washington (USA) for 141 days. The system, referred to as the Turbine Lander, was the product of a laboratory-to-field effort to develop a system that enables enhanced ocean sensing or vehicle recharge in remote, energetic settings. The turbine consists of a vertical-axis, cantilevered rotor (1.19 m x 0.85 m) with four foils installed on a gravity foundation. A broader range of constraints including the deployment strategy, site characteristics, and estimated loads, drove the system’s design. This work presents the design, characterization, operation, and post-recovery engineering assessment of the Turbine Lander. Pre-deployment characterization efforts yielded a peak power coefficient of approximately 0.3 for the rotor, although system losses resulted in much lower water-to-wire efficiencies under most operating conditions. The results demonstrate the importance of co-design among key components of the powertrain and control systems to achieve acceptable system efficiency across operating conditions.

Co-design↗
DOE OSTI2025

Temporally-consistent koopman autoencoders for forecasting dynamical systems

Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the dimension reduction capabilities of autoencoders, and the spectral properties of the Koopman operator to learn a reduced-order feature space with simpler, linear dynamics. However, the effectiveness of KAEs is hindered by limited and noisy training datasets, leading to poor generalizability. To address this, we introduce the Temporally-Consistent Koopman Autoencoder (tcKAE), designed to generate accurate long-term predictions even with limited and noisy training data. This is achieved through a consistency regularization term that enforces prediction coherence across different time steps, thus enhancing the robustness and generalizability of tcKAE over existing models. We provide analytical justification for this approach based on Koopman spectral theory and empirically demonstrate tcKAE’s superior performance over state-of-the-art KAE models across a variety of test cases, including simple pendulum oscillations, kinetic plasma, and fluid flow data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Online Electron Reconstruction at CLAS12

Online reconstruction plays a crucial role in monitoring and in real-time analysis of high energy and nuclear physics experiments. A vital aspect of reconstruction algorithms is particle identification, which combines information from various detector components to determine the type of particle. Electron identification is particularly significant in electro-production nuclear physics experiments like the CLAS12 spectrometer at Jefferson Laboratory as it is essential in data recording. A machine learning approach has been developed for CLAS12 experiments to reconstruct and identify electrons by combining raw signals from multiple detector components at the data acquisition level. This method achieves high electron identification purity while maintaining nearly 100% efficiency. Furthermore, the machine learning tools operate at rates exceeding data acquisition speed, enabling the real-time electron reconstruction. This advancement significantly improves online analyses and monitoring capabilities for CLAS12 experiments.

Tyson,, Richard [Thomas Jefferson National Acceler↗
DOE OSTI2026

Multiscale Neural Networks for Approximating Green’s Functions

Neural networks (NNs) have been widely used to solve partial differential equations (PDEs) in the applications of physics, biology, and engineering. One effective approach for solving PDEs with a fixed differential operator is learning Green’s functions. However, Green’s functions are notoriously difficult to learn due to their poor regularity, which typically requires larger NNs and longer training times. In this work, we address these challenges by leveraging multiscale NNs to learn Green’s functions. Through theoretical analysis using multiscale Barron space methods and experimental validation, we show that the multiscale approach significantly reduces the necessary NN size and accelerates training.

97 MATHEMATICS AND COMPUTING↗