Search NASA⌕ Search

SEARCH · Search NASA

Results for “trustworthy systems”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

“Frequency” and the PMU standard

The Phasor Measurement Unit (PMU) has revolutionized power system management by providing high-resolution, time-stamped, spatial, and temporal measure¬ments of the state of power systems. However, the standards defining the measured quantities have ambiguities that cause uncertainty, irreproducibility, and loss of interoperability during periods of change where the measurements should have the greatest value. This paper examines PMU frequency measurement to highlight the problems. It develops some suggestions for the scope and the next evolutionary improvements to the documentary standards. The aim is to improve the meaningfulness and trustworthiness of dynamic power system measurements.

Frequency, rate of change of frequency, definition↗
NASA NTRSDate not supplied

Autonomy Technologies for Systems of a Moon Base

The aim of the workshop is to “explore emerging autonomy technologies that could enable or enhance mission capabilities, reduce mission risk, and reduce mission cost.” Enhancing mission capabilities will depend on how capable and trustworthy the autonomy implemented is. As systems increase in complexity, and also with multiple interdependent/interacting systems, current autonomy capability and trustworthiness is very low. A paradigm and technology from NASA that addresses this shortcoming will be discussed, the NASA Platform for Autonomous Systems (NPAS). NPAS also happens to address reduction of mission risk and cost. NPAS will be discussed as a capability that is reaching readiness for space use, but also serves as a reference to develop technologies suitable for integrated autonomous operations of lunar systems; encompassing autonomous systems, situational awareness, and reasoning and acting.

Autonomous systems↗
NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight frameworks is paramount for establishing an effective architecture for autonomous systems. Hardware test flights are time-consuming and cost prohibitive during early system design and development. Simulation environments can be useful tools to accelerate algorithm development and testing. However, transitions from simulation to flight (sim-to-flight) can be challenging, unless systems are designed with this transition in mind and with the necessary capabilities built into the architecture and framework. One of the objectives of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. ATTRACTOR’s objective was to construct computational concepts of trustworthiness and justifiable trust in multi-agent autonomous teams, to inform future certification of safety-critical and time-critical autonomous systems in aviation. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation (ModSim) environment for test and evaluation of autonomous systems. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single-and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. The Autonomous Entity Operational Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications, enabling sim-to-flight with minimal configuration changes. Using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗
DOE OSTI2025

ADEPT: A Pedagogical Framework for Integrating Agentic AI with Deterministic Scientific Workflows

The integration of Large Language Models (LLMs) into scientific research promises to accelerate discovery, yet a significant gap remains between the dynamic reasoning of Artificial Intelligence (AI) agents and the static, deterministic nature of canonical scientific workflows. This paper introduces ADEPT (Agentic Discovery and Exploration Platform for Tools), a reference architecture and pedagogical framework explicitly designed to bridge this gap. ADEPT's primary mission is to provide a transparent, "glass-box" environment where researchers and engineers can learn to effectively wrap established scientific software (e.g., BLAST, Nextflow pipelines) and compose it into reliable, agent-driven workflows. We describe its modular, multi-server architecture, which leverages the Model Context Protocol (MCP) for tool serving, LangGraph for robust agentic orchestration, and a secure nsjail-based sandbox for safe code execution. By prioritizing architectural clarity, safety, and modularity, ADEPT serves as an extensible blueprint for building trustworthy AI-augmented systems and fosters the collaborative development necessary to responsibly employ agentic AI for science. We provide practical examples of how to adapt and extend this framework, highlighting its utility in workforce development and AI-readiness capabilities across research and development projects.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2009

Deriving Safety Cases for the Formal Safety Certification of Automatically Generated Code

We present an approach to systematically derive safety cases for automatically generated code from information collected during a formal, Hoare-style safety certification of the code. This safety case makes explicit the formal and informal reasoning principles, and reveals the top-level assumptions and external dependencies that must be taken into account; however, the evidence still comes from the formal safety proofs. It uses a generic goal-based argument that is instantiated with respect to the certified safety property (i.e., safety claims) and the program. This will be combined with a complementary safety case that argues the safety of the framework itself, in particular the correctness of the Hoare rules with respect to the safety property and the trustworthiness of the certification system and its individual components. Keywords: Automated code generation, Hoare logic, formal code certification, safety case, Goal Structuring Notation.

Basir, Nurlida↗
NASA NTRS2018

Towards Informing an Intuitive Mission Planning Interface for Autonomous Multi-Asset Teams via Image Descriptions

Establishing a basis for certification of autonomous systems using trust and trustworthiness is the focus of Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR). The Human-Machine Interface (HMI) team is working to capture and utilize the multitude of ways in which humans are already comfortable communicating mission goals and translate that into an intuitive mission planning interface. Several input/output modalities (speech/audio, typing/text, touch, and gesture) are being considered and investigated in the context human-machine teaming for the ATTRACTOR design reference mission (DRM) of Search and Rescue or (more generally) intelligence, surveillance, and reconnaissance (ISR). The first of these investigations, the Human Informed Natural-language GANs Evaluation (HINGE) data collection effort, is aimed at building an image description database to train a Generative Adversarial Network (GAN). In addition to building an image description database, the HMI team was interested if, and how, modality (spoken vs. written) affects different aspects of the image description given. The results will be analyzed to better inform the designing of an interface for mission planning.

Generative Adversarial Network (GAN)↗
DOE OSTI2025

Deep Cyber-Physical Situational Awareness for Energy Systems: A Secure Foundation for Next-Generation Energy Management

This document provides the final report for the CYPRES project. The purpose is (1) to highlight and summarize its major accomplishments and (2) to provide guidance on how its outcomes have informed and can inform important additional research and technology transfer. The goal of CYPRES was the research, development, and demonstration of a security-oriented next generation cyber-physical EMS for electric power systems that detects malicious and abnormal events through the fusion of cyber and physical data. To achieve this, the CYPRES project team researched, developed, and built a prototype of the solution, referred to as the CYPRES EMS. The CYPRES EMS is a proof-of-concept cyber-physical platform that demonstrates the management of the energy system, communications, security, and cyber-physical grid modeling and analytics. As part of the capabilities of the CYPRES EMS, the team designed and developed a suite of power system applications for monitoring, risk analyses, detection, and control that are inherently cyberaware. At its core, the project aimed to research, develop, and demonstrate a security-oriented next-generation cyber-physical Energy Management System (EMS) capable of detecting malicious and abnormal events through the innovative fusion of cyber and physical data. This approach represents a fundamental shift from traditional EMS, reimagining how critical infrastructure can be protected through unified cyber-aware and physics-aware secure data flow pipelines. The project’s cornerstone deliverable, the CYPRES EMS, serves as a proof-of-concept cyber-physical platform that revolutionizes the management of energy systems, communications, security, and cyber-physical grid modeling and analytics. This prototype implements a comprehensive suite of power system applications for monitoring, risk analyses, detection, and control, all designed with inherent cyber awareness. The system’s architecture extends from end-devices in the field through to control center applications, establishing a secure and resilient control framework that addresses the challenges posed by diverse devices of unknown trustworthiness connecting to modern power systems. Through this innovative approach to deep cyber-physical situational awareness, the CYPRES project not only advances the state-of-the-art in energy infrastructure protection but also establishes a new paradigm for how EMS can be designed, deployed, and operated in an increasingly complex threat landscape. The findings and developments from this project provide crucial insights for stakeholders across the energy sector, offering a blueprint for enhancing the reliability and resilience of our nation’s critical energy infrastructure in the face of evolving cyber threats.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A Blockchain-Enabled Sustainable Safety Management Framework for Connected Vehicles

The notion of an intelligent transportation system (ITS) aims to boost the performance of transportation networks, which has gained more and more traction in both academic and commercial circles. ITS is a constantly evolving vision that combines cutting-edge transportation approaches with new information, communication, computers, and other technology. ITS should discover consequence routes to enhance the sustainability, safety, and trustworthiness of the entire transportation system utilizing emerging technologies. In this paper, a sustainable safety management framework for connected vehicles is proposed by integrating blockchain. It introduces smart transportation equipment called an AI-enabled vehicle smart device (AVSD) for vehicular communications. AVSD can reduce energy consumption by decreasing the computational costs in vehicular communications. Smart contracts are used to identify vehicles automatically and establish secure communication among vehicles and emergency service stations (ESSs) like hospitals, police stations, and fire stations. The experiment results show that the proposed framework provides a communication environment for sustainable safety and security using the introduced smart transportation device. In conclusion, the proposed blockchain-enabled sustainable safety management framework has the potential to improve safety and sustainability in the transportation industry by creating a secure, decentralized, and transparent platform for managing safety data and promoting safe and sustainable driving behaviors.

42 ENGINEERING↗
DOE OSTI2025

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

Despite its significant benefits in enhancing the transparency and trustworthiness of artificial intelligence (AI) systems, explainable AI (XAI) can unintentionally provide adversaries with insights into blackbox models, increasing their vulnerability to various attacks. In this paper, we develop a novel explanation-driven adversarial attack against blackbox classifiers based on feature substitution, called XSub. The key idea of XSub is to strategically replace important features (identified via XAI) in the original sample with corresponding important features of a different label, thereby increasing the likelihood of the model misclassifying the perturbed sample. XSub only requires a minimal number of queries and can be easily extended to launch backdoor attacks in case the attacker has access to the model's training data. Our evaluation shows that XSub is not only effective and stealthy but also low-cost, showcasing its feasibility across a wide range of AI applications.

adversarial attack↗
NASA NTRS2016

An Investigation of Proposed Techniques for Quantifying Confidence in Assurance Arguments

The use of safety cases in certification raises the question of assurance argument sufficiency and the issue of confidence (or uncertainty) in the argument's claims. Some researchers propose to model confidence quantitatively and to calculate confidence in argument conclusions. We know of little evidence to suggest that any proposed technique would deliver trustworthy results when implemented by system safety practitioners. Proponents do not usually assess the efficacy of their techniques through controlled experiment or historical study. Instead, they present an illustrative example where the calculation delivers a plausible result. In this paper, we review current proposals, claims made about them, and evidence advanced in favor of them. We then show that proposed techniques can deliver implausible results in some cases. We conclude that quantitative confidence techniques require further validation before they should be recommended as part of the basis for deciding whether an assurance argument justifies fielding a critical system.

Graydon, Patrick J.↗
NASA NTRSDate not supplied

Enhancing Neural Network Decision-Making with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. This explainability encourages people to be more inclined to justifiably trust machine decision-making.

Loc Tran↗
NASA NTRSDate not supplied

Spatial and Temporal Deconfliction of Trajectories in the Presence of Uncertainties

Demonstration of conflict-free movement for multi-agent teams in challenging scenarios is crucial in developing trust and trustworthiness in an autonomous transport system. Tolerance verification queries are explored as a mechanism to enforce spatial and temporal deconfliction for a cooperating team of Unmanned Aerial Systems (UAS) with prescribed heterogeneous path-following performance. Obstacles in the environment are modelled as set of polyhedra, whereas each vehicle’s trajectory is represented as a sequence of polynomial curves with C2 continuity, expressed in a Bernstein basis. Each vehicle is modelled as a point mass and a safety distance, informed by the geometry of the UAS and the worst-case path-following error. This defines a tube around the trajectories where each UAS is most likely to fly through. In addition, obstacles in the environment have an associated safety buffer around them to account for the uncertainty in their location and geometric description. The tolerance verification queries explored in this paper combine the safety distance information from each UAS and environmental hazard to compute trajectories that are contained within the safe configuration space. Tolerance verification is also compared with other proximity queries to determine the suitability of each method along the different steps of the trajectory generation algorithm. This paper analyzes the fitness and performance of three proximity queries – collision, tolerance verification, and distance computations – between polyhedral and polynomial curves to ensure deconfliction between obstacles and vehicles, but also between polynomial curves to guarantee safe separation among cooperating UAS.

trajectory generation↗
NASA NTRSDate not supplied

Bootstrapping Multi-Agent Unmanned Aerial Vehicle (UAV) System Integration Using Ground-Based Assets: Lessons Learned

The highly dynamic nature of UAVs imposes significant challenges when conducting initial testing ranging from safety risks posed by high-capacity lithium batteries and spinning propellers to rigorous timing demands on controllers and the consequences of failures mid-air. Flight testing of a single vehicle is time and labor intensive due to these challenges and more, and the complexity increases exponentially with the number of vehicles. While simulations and hardware-in-the-loop bench testing can provide adequate environments for preliminary validation, differences in system deployment architecture, software interfaces, and hardware infrastructure between simulation and a fleet of real UAVs create a sizable gap that must be navigated carefully during system integration. In support of the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project, which had the goal of establishing a basis of certification of trust and trustworthiness in multi-agent autonomous systems, this gap was tackled from two directions. First, a novel mixed-reality simulation environment was engineered to blur the transition from simulation to flight hardware. Second, a fleet of Unmanned Surface Vehicles (USVs) was developed as a test and evaluation platform that more closely represented the final aerial fleet while eliminating many of the risks associated with air vehicles. This paper delves into the second element, analyzing the efficacy of the USV platform in performing system integration testing for the UAV system. In this paper we present the USV fleet and its role in reducing the aforementioned gaps in deployment architecture, software interfaces, and hardware infrastructure when moving from simulation to flight. An overview of the hardware and software onboard the vehicles will be provided along with supporting infrastructure. The system integration process will be documented including results in supporting both the overarching design reference mission (DRM) of ATTRACTOR and individual research efforts conducted during the project. Finally, we will discuss some of the practical lessons learned regarding the testing, deployment, and operation of multi-agent autonomous systems.

Matthew P Vaughan↗
NASA NTRSDate not supplied

Enhancing Neural Network Explainability with Variational Autoencoders

Machine intelligence has been used to tackle increasingly complex problems and deep learning solutions are at the forefront of tackling these problems. In general, these architectures have a great number of parameters that are methodically updated in training. The vast number and complexity of deep neural networks makes it very difficult to decipher the inner workings of the neurons and layers that make up the network. This paper posits that trustworthiness and trust in autonomous systems are increased through eXplainable Artificial Intelligence (XAI) and presents a method that enhances the explainability and understanding of a neural network decision. We leverage variational autoencoders to produce human interpretable features from complex data sets. We show that the explainable features can then be used for machine learning applications. Explainability inspires trust in autonomous systems that use deep learning, which is necessary for safety critical systems.

Loc Tran↗
NASA NTRSDate not supplied

Bootstrapping Multi-Agent Unmanned Aerial Vehicle (UAV) System Integration Using Ground-Based Assets: Lessons Learned

In support of the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project, a fleet of unmanned ground vehicles (UGVs) was developed as a test and evaluation (T\&E) platform to reduce system integration gaps between simulation and live flight hardware. While simulation and hardware-in-the-loop bench testing provide adequate environments for preliminary validation, differences in system deployment architecture, software interfaces, and hardware infrastructure increase the risks to safety, property, and the project. Given ATTRACTOR’s goal of establishing a basis of certification of trust and trustworthiness in multi-agent autonomous systems, bridging these gaps was critical to successful project execution and feasibility assessment. In this paper we present the UGV fleet and its role in speeding up system integration, smoothing the transition from simulation to flight, and providing researchers an easy-to-use hardware test bed. An overview of the hardware and software on-board the vehicles is provided along with supporting infrastructure. The system integration process is documented including results in supporting both the overarching design reference mission (DRM) of ATTRACTOR and individual research efforts conducted since the creation of the fleet. Finally, we discuss the practical lessons learned regarding the testing, deployment, and operation of multi-agent autonomous systems.

Matthew P. Vaughan↗
DOE OSTI2024

Generative AI for Power Grid Operations

Generative artificial intelligence (AI) has captured into the mainstream, demonstrating capabilities that once belonged solely to the realm of human cognition. From defeating world champions in complex games to generating human-quality text and images, Generative AI has proven its potential to revolutionize countless industries. The electric power grid is no exception. Generative AI's ability to process vast amounts of data rapidly, assist decision support and identify patterns could significantly enhance power grid operations. For example, Generative AI could improve state estimation where measurements are not available or integrate renewable energy sources more efficiently with probabilistic forecasting. The key contributions of this whitepaper are outlined below: (1) Comprehensive overview of Generative AI's applications in power grid operations: It highlights the opportunities in areas such as forecasting, state estimation, and demonstrating the potential for enhancing efficiency, reliability, and resilience. (2) Expanding Generative AI's impact through synergies with emerging technologies: The paper introduce NREL developed eGridGPT and explores how AI orchestration, multi-agent systems, and Digital Twins can collaborate to optimize grid operations, addressing the complexities of a decarbonized and electrified future. (3) In-depth analysis of challenges in implementing Generative AI: This includes considerations like data availability and quality, model validation, certification, and ethical concerns, ensuring responsible AI deployment. (4) Emphasizing human-AI collaboration: The whitepaper underscores the importance of trustworthy, transparency, and explainability in AI systems to promote seamless interaction between human operators and AI, ultimately improving decision-making. (5) Exploring future research and development: It identifies critical areas for further advancement to fully realize Generative AI's potential in power grid operations. This whitepaper serves as a valuable resource for researchers, practitioners, and policymakers looking to harness Generative AI for a more reliable, stable, and cost-effective power grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Secure Time Synchronization in Power Grids and Network HIL Synchrophasor Testing

Reliable and secure time synchronization underpins the monitoring and control functions of modern power grids. As GPS-based timing infrastructures grow more susceptible to spoofing and jamming, their vulnerabilities pose escalating risks to grid stability. This work investigates a secure, resilient timing framework that can serve as an alternative or redundant source for power grids, with a particular focus on synchrophasorbased applications. A candidate timing system architecture is evaluated to guarantee trustworthy time dissemination, even in degraded conditions. A network hardware-in-the-loop testing of two synchrophasors validates the concepts, demonstrating enhanced timing integrity, improved detection of timing anomalies, and sustained observability during adverse timing events.

Wu, Ori [ORNL] (ORCID:0000000326723410)↗
DOE OSTI2025

Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science

This report summarizes insights from the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science, which convened more than 40 experts from national laboratories, academia, industry, and community organizations to chart a path toward more powerful, sustainable, and collaborative scientific software ecosystems. To address urgent challenges at the intersection of high-performance computing (HPC), AI, and scientific software, participants envisioned agile, robust ecosystems built through socio-technical co-design—the intentional integration of social and technical components as interdependent parts of a unified strategy. This approach combines advances in AI, HPC, and software with new models for cross-disciplinary collaboration, training, and workforce development. Key recommendations include building modular, trustworthy AI-enabled scientific software systems; enabling scientific teams to integrate AI systems into their workflows while preserving human creativity, trust, and scientific rigor; and creating innovative training pipelines that keep pace with rapid technological change. Pilot projects were identified as near-term catalysts, with initial priorities focused on hybrid AI/HPC infrastructure, cross-disciplinary collaboration and pedagogy, responsible AI guidelines, and prototyping of public-private partnerships. This report presents a vision of next-generation ecosystems for scientific computing where AI, software, hardware, and human expertise are interwoven to drive discovery, expand access, strengthen the workforce, and accelerate scientific progress.

97 MATHEMATICS AND COMPUTING↗