SEARCH · Search NASA

Results for “agent safety”

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.

SourceResearch connectionFrom yearThrough year

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

At least 19 records

All sources NASA NTRS DOE OSTI

NASA NTRS2003

Validating the Autonomous Science Agent

This paper describes the validation process for the Autonomous Science Agent, a software agent that will fly onboard the EO-1 spacecraft from 2003-2004. This agent will recognize science events, retarget the spacecraft to respond to the science events, and reduce data downlink to only the highest value science data. The autonomous science agent has been designed using a layered architectural approach with specific redundant safeguards to reduce the risk of an agent malfunction to the EO-1 spacecraft. This 'safe' design is also in the process of being thoroughly validated by informal validation methods and extensive testing. This paper describes the analysis used to define agent safety, elements of the design that increase the safety of the agent, and the process being used to validate agent safety prior to the agent software controlling the spacecraft.

agent safety↗

NASA NTRS2004

Validating the autonomous EO-1 science agent

This paper describes the validation process for the Autonomous Science Agent, a software agent that is currently flying onboard NASA EO-1 spacecraft. The agent autonomously collects, analyzes, and reacts to onboard science data. The Autonomous Science Agent has been designed using a layered architectural approach with specific redundant safeguards to reduce the risk of an agent malfunction to the EO-1 spacecraft. This safe design has been thoroughly validated by informal validation methods supplemented by sub-system and system-level testing. This paper describes the analysis used to define agent safety, elements of the design that increase the safety of the agent, and the process used to validate agent safety.

software↗

DOE OSTI2026

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗

NASA NTRS2002

CATS-based Agents That Err

This report describes preliminary research on intelligent agents that make errors. Such agents are crucial to the development of novel agent-based techniques for assessing system safety. The agents extend an agent architecture derived from the Crew Activity Tracking System that has been used as the basis for air traffic controller agents. The report first reviews several error taxonomies. Next, it presents an overview of the air traffic controller agents, then details several mechanisms for causing the agents to err in realistic ways. The report presents a performance assessment of the error-generating agents, and identifies directions for further research. The research was supported by the System-Wide Accident Prevention element of the FAA/NASA Aviation Safety Program.

Callantine, Todd J.↗

DOE OSTI2025

Three‐trophic level food webs support the safety of a biocontrol agent 3 years after release

Biological control (biocontrol) is a powerful tool for managing invasive alien species and assisting the restoration of native ecosystems. Rigorous post‐release monitoring of biocontrol agents is critical to evaluate the success of biocontrol programs; however, this is still rarely implemented. Here, we combined the use of species interaction networks with a Before‐After Control‐Impact design to evaluate the target and non‐target, direct and indirect effects of the Australian gall wasp Trichilogaster acaciaelongifoliae , released to control the invasive plant Acacia longifolia in Portugal. We compared the structure of plant‐galling insect‐parasitoid food webs before and 3 years after the release of the biocontrol agent. Exhaustive sampling did not detect any non‐target effects, either direct (on non‐target plants) or indirect (on other galling insects via shared plants). Additionally, no significant changes were detected in network structure that could be related to the establishment of the biocontrol agent. This study shows that monitoring biocontrol at the community level is possible and that, when carefully planned, biocontrol poses minimal risk of non‐target effects.

López‐Núñez, Francisco A. [Centre for Functional E↗

NASA NTRS1991

Who or what saved the day? A comparison of traditional and glass cockpits

This study examined incidents reported to NASAs Aviation Safety Reporting System from a different perspective: rather than focusing on the factors contributing to or causing incidents, this study concentrated on who and what (subsystems and information) enabled the recovery from an anomaly. Incident reports describing altitude deviations were classified as to cockpit type (glass or traditional), flight phase, agent restoring safety, and cockpit subsystems providing specific information that helped restore safety. The data revealed and quantified the agents, information, and factors that 'saved the day'. The flight crews used many sources of information to detect the altitude deviations: altimeter, outside scene, altitude alert, kinesthesia, attitude and communications monitoring. In the glass cockpits the crews also used the map display and autothrottles to detect deviations from assigned altitudes. There was an interaction between the person detecting the anomaly (controller/flight crew) and the type of cockpit. Glass cockpit flight crews detect proportionally more deviations than their counterparts in traditional cockpits, while controllers tend to detect more deviations involving traditional cockpits. There was no effect of cockpit position (captain/first officer). A model that details the flow of altitude information between air traffic control, flight crews, and cockpit subsystems, was developed and validated. This model identifies strengths and weaknesses in the flow of altitude information within the current ground/air system.

Degani, Asaf↗

NASA NTRS2005

Safe Agents in Space: Preventing and Responding to Anomalies in the Autonomous Sciencecraft Experiment

This paper describes the design of the Autonomous Sciencecraft Experiment, a software agent that has been running on-board the EO-I spacecraft since 2003. The agent recognizes science events, retargets the spacecraft to respond to the science events, and reduces data downlink to only the highest value science data. The autonomous science agent was designed using a layered architectural approach with specific redundant safeguards to reduce the risk of an agent malfUnction to the EO-I spacecraft. The agent was designed to be "safe" by first preventing anomalies, then by automatically detecting and responding to them when possible. This paper describes elements of the design that increase the safety of the agent, the anomalies that occurred during the experiment, and how the agent responded to these anomalies.

autonomous science agent↗

NASA NTRS2024

An On-Board Off-Board Framework for Online Replanning: Applied to UAVs in Urban Environments

Autonomous systems are being used in a multitude of areas at an increasing rate and require a high level of adaptivity and intelligence to operate safely, especially under faulty conditions. This paper introduces a novel genetic algorithm tailored for UAV trajectory replanning, with an improved execution time via search space reduction based on the operating conditions of the UAV and its remaining mission. A unique characteristic of the replanning agent is its fast-start and adaptive properties, pre-seeding candidates with partial solutions and dynamically tuning elitism, crossover, and mutation rates in correspondence to the average fitness and diversity of the population. A population restart mechanism and early stopping mechanism are evaluated as well to assess their effect on solution quality and runtime. Previous work on genetic algorithms for UAV replanning were conducted with short trajectories in a small state space. Our UAV operates in a 56,000 square meter simulated urban environment, with static obstacles and a total of 53 possible waypoints. The agent increases the safety and reliability of UAV autonomy when operating under faulty conditions and when replanning is required.

Machine Learning↗

NASA NTRS2001

Suppression of Low Strain Rate Nonpremixed Flames by an Agent

The agent concentration required to achieve the suppression of low strain rate nonpremixed flames is an important consideration for fire protection in a microgravity environment such as a space platform. Currently, there is a lack of understanding of the structure and extinction of low strain rate (<20 s(exp -1)) nonpremixed flames. The exception to this statement is the study by Maruta et al., who reported measurements of low strain rate suppression of methane-air diffusion flames with N2 added to the fuel stream under microgravity conditions. They found that the nitrogen concentration required to achieve extinction increased as the strain rate decreased until a critical value was obtained. As the strain rate was further decreased, the required N2 concentration decreased. This phenomenon was termed "turning point" behavior and was attributed to radiation-induced nonpremixed flame extinction. In terms of fire safety, a critical agent concentration assuring suppression under all flow conditions represents a fundamental limit for nonpremixed flames. Counterflow flames are a convenient configuration for control of the flame strain rate. In high and moderately strained near-extinction nonpremixed flames, analysis of flame structure typically neglects radiant energy loss because the flames are nonluminous and the hot gas species are confined to a thin reaction zone. In counterflowing CH4-air flames, for example, radiative heat loss fractions ranging from 1 to 6 percent have been predicted and measured. The objective of this study is to investigate the impact of radiative emission, flame strain, agent addition, and buoyancy on the structure and extinction of low strain rate nonpremixed flames through measurements and comparison with flame simulations. The suppression effectiveness of a number of suppressants (N2, CO2, or CF3Br) was considered as they were added to either the fuel or oxidizer streams of low strain rate methane-air diffusion flames.

Hamins, A.↗

NASA NTRS2003

Error Generation in CATS-Based Agents

This research presents a methodology for generating errors from a model of nominally preferred correct operator activities, given a particular operational context, and maintaining an explicit link to the erroneous contextual information to support analyses. It uses the Crew Activity Tracking System (CATS) model as the basis for error generation. This report describes how the process works, and how it may be useful for supporting agent-based system safety analyses. The report presents results obtained by applying the error-generation process and discusses implementation issues. The research is supported by the System-Wide Accident Prevention Element of the NASA Aviation Safety Program.

Callantine, Todd↗

DOE OSTI2026

Optimal CO 2 storage management considering safety constraints in multi-stakeholder multi-site GCS projects: A Markov game perspective

Geological carbon storage (GCS) projects could involve a diverse array of stakeholders or players from public, private, and regulatory sectors, each with different objectives and responsibilities. Given the complexity, scale, and long-term nature of GCS operations, determining whether individual stakeholders can independently optimize their interests — or whether collaborative coalition agreements are needed — remains a central question for effective GCS project planning and management. To access large, high-quality storage resources, future GCS deployment may increasingly occur in geologically connected sites, where shared geological features such as pressure space and reservoir pore capacity can lead to competitive behavior among stakeholders. In this work, we propose a paradigm based on Markov games to quantitatively investigate how different coalition structures affect the goals of stakeholders. We frame this multi-stakeholder multi-site problem as a multi-agent reinforcement learning problem with safety constraints. Our approach enables agents to learn optimal strategies while complying with safety regulations. We present an example where multiple operators are injecting CO 2 into their respective project areas in a geologically connected basin. To address the high computational cost of repeated simulations of high fidelity models, a previously developed surrogate model based on the Embed-to-Control (E2C) framework is employed. Our results demonstrate the effectiveness of the proposed framework in addressing optimal management of CO 2 storage when multiple stakeholders with different objectives and goals are involved.

58 GEOSCIENCES↗

DOE OSTI2026

A Physics-Informed Reinforcement Learning Framework for Economic-Thermal Co-Optimization of Crypto Mining Data Centers: Preprint

The rapid expansion of cryptocurrency mining has created a new class of high-density data centers characterized by extreme thermal flux and high sensitivity to volatile economic markets. Traditional thermal management strategies, typically reliant on rule-based control, maintain static setpoints that fail to account for fluctuating electricity prices and cryptocurrency values - factors critical to mining profitability. To address this, we present a physics-informed reinforcement learning (PIRL) framework for economic-thermal co-optimization in crypto mining data centers. This framework consists of a proximal policy optimization (PPO) agent, a virtual testbed powered by high-fidelity physics-based models, and an interactive frontend dashboard. The PPO agent is trained using the virtual testbed and strict hardware safety limits. This physics-informed approach allows the agent to learn a stochastic policy that dynamically balances mining revenue against operational costs by co-optimizing HVAC cooling setpoints and IT computational hashrate. The simulation results demonstrate that the integrated framework achieved an 8.62% increase in net operational profit compared to traditional baseline strategies while strictly adhering to safety-critical temperature constraints (coolant supply temperature < 32 degrees C). This work provides a scalable template for the deployment of reinforcement learning in mission critical facilities where economic volatility and physical safety must be managed simultaneously.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRS1992

Occupational safety considerations with hydrazine

Hydrazine is a reducing agent that is most commonly used as a propellant and as an oxygen scavenger in boilers. Hydrazine is extremely irritating and has been demonstrated to produce both acute and chronic toxicity. As a result, the established permissible inhalation exposure limits are very low, and respiration protection is required whenever vapors are present. Liquid hydrazine penetrates the skin and produces a chemical burn; therefore, some protective measures must also be taken to protect the skin from liquid contact. Often, however, a cumbersome, whole-body protective suit is worn to protect against skin contact with vapor as well. To what extent it is actually necessary to protect skin from vapor penetration had not previously been demonstrated. In an attempt to answer this question, we conducted a study with rats to compare the dermal penetration of hydrazine vapor with inhalation. Pharmacokinetic modeling was used to compare body burdens resulting from these different routes of exposure. The analysis concluded that the vapor concentration during a skin-only exposure would have to be at least 200 times higher than that during inhalation to achieve the same body burden. This type of estimation illustrates the use of predictive toxicology in occupational exposures.

Clewell, Harvey J., III↗

NASA NTRS1990

Critical safety assurance factors for manned spacecraft - A fire safety perspective

Safety assurance factors for manned spacecraft are discussed with a focus on the Space Station Freedom. A hazard scenario is provided to demonstrate a process commonly used by safety engineers and other analysts to identify onboard safety risks. Fire strategies are described, including a review of fire extinguishing agents being considered for the Space Station. Lessons learned about fire safety technology in other areas are also noted. NASA and industry research on fire safety applications is discussed. NASA's approach to ensuring safety for manned spacecraft is addressed in the context of its multidiscipline program.

Rodney, George A.↗

NASA NTRS2001

The Conference Proceedings of the 2001 Air Transport Research Society (ATRS) of the WCTR Society

The ATRS held its Annual conference at Jeju Island, Korea in July 2001. The conference was a success with nearly 140 participants including 70 presenters. This report contains presentations from Volume 1 on the following: Airline and Travel Agent Relationships in Asia;Benchmarking Aviation Safety in the Commercial Airline Industry;Impact of Frequent Flyer Program on the Demand for Air Travel; Application of Genetic Algorithm on Airline Schedule;The Effects of Dual Carrier Designation and Partial Liberalization: The Case of Canada;Defense of Air Carriers and Air Agencies in FAA Enforcement proceedin gs - Damage Control Before the Case Arises; Cost Incentives for Airline Mergers? - An examination on the cost impact of U.S. airline mergers and acquisitions;Airport Regulation, Airline Competition and Canada's Airport System; Airline Competition: The Case of Israel's Domestic Doupoly; Non-Financial Indicators of Airline Distress: A Conceptual Approach;and Airport Privatization: An Empirical Analysis of Financial and Operational Efficiency.

Lee, Yeong-Heok↗

NASA NTRSDate not supplied

Human Factors Research Considerations for Terminal Area Urban Air Mobility Operations

In this presentation, we discuss the human factors research challenges from introducing greater levels of automation in a future air transportation concept called Urban Air Mobility (UAM). UAM is an air transportation concept that aims to provide air transportation services to the daily commuter, as well as emergency response and package delivery. The principal innovation over current day large air transport system is the greater distribution of important safety functions to automated and human agents; these functions include air traffic management, traditionally an air traffic controller responsibility. A central aspect of UAM is the development of an automated air traffic manager, whose primary responsibility is to approve airspace access for vehicle operators. Vehicle operator roles may include onboard and remote pilots, as well as a human manager who will supervise an entire fleet. Alternatively, both fleet manager and vehicle operators can be merged into a single role – a feasible option if UAM aircraft are autonomous. In lieu of tower controllers, vertiport managers, with the assistance of automation, will manage arrival and departure schedules between vertiports, as well as supervise surface operations. Our approach here will be to introduce use cases currently being developed by NASA, and then provide preliminary definitions for each of the roles introduced above and how coordination between them can be configured to support the operations within the use cases described. Subsequently, we review the tools and interfaces being developed to support the various roles. To conclude, we present current human factors work related to defining the roles above and suggest future work to advance the UAM concept.

trial planning↗

DOE OSTI2026

Optimization and stabilization of Fermilab Booster using hybrid Bayesian/RL framework

PIPII project will raise Fermilab Booster intensity and ramp rate. Beam losses will limit average power and are hard to simulate. Presently, Booster uses operator-guided empirical tuning. This task is challenging due to high dimensionality, multiple objectives, critical safety constraints, and drifts. We developed a synergistic suite of Bayesian optimization (BO) and reinforcement learning (RL) tools to optimize and stabilize beam losses. First, active learning was used to build a rough model. Data was collected parasitically using two novel safety constraint types – nonlinear input space restrictions (based on optics model), and uncertainty constraints (to stop bad steps/beam aborts). We then applied online multi-objective BO with scalarized objectives and fitting to improve/rebalance losses, increasing safety margins by 25%. Using BO model as a safety veto, we tried several on/off-policy RL agents for long term stabilization; SAC had best performance. We found that adding contextual (state) information further improved performance, eventually integrating key knobs like linac phase and temperature into the parameter space. Long term testing is ongoing to enable operational use.

Kuklev, Nikita [Fermilab]↗

NASA NTRS2004

Fire Suppression in Low Gravity Using a Cup Burner

Longer duration missions to the moon, to Mars, and on the International Space Station increase the likelihood of accidental fires. The goal of the present investigation is to: (1) understand the physical and chemical processes of fire suppression in various gravity and O2 levels simulating spacecraft, Mars, and moon missions; (2) provide rigorous testing of numerical models, which include detailed combustion-suppression chemistry and radiation sub-models; and (3) provide basic research results useful for advances in space fire safety technology, including new fire-extinguishing agents and approaches.The structure and extinguishment of enclosed, laminar, methane-air co-flow diffusion flames formed on a cup burner have been studied experimentally and numerically using various fire-extinguishing agents (CO2, N2, He, Ar, CF3H, and Fe(CO)5). The experiments involve both 1g laboratory testing and low-g testing (in drop towers and the KC-135 aircraft). The computation uses a direct numerical simulation with detailed chemistry and radiative heat-loss models. An agent was introduced into a low-speed coflowing oxidizing stream until extinguishment occurred under a fixed minimal fuel velocity, and thus, the extinguishing agent concentrations were determined. The extinguishment of cup-burner flames, which resemble real fires, occurred via a blowoff process (in which the flame base drifted downstream) rather than the global extinction phenomenon typical of counterflow diffusion flames. The computation revealed that the peak reactivity spot (the reaction kernel) formed in the flame base was responsible for attachment and blowoff of the trailing diffusion flame. Furthermore, the buoyancy-induced flame flickering in 1g and thermal and transport properties of the agents affected the flame extinguishment limits.

Takahashi, Fumiaki↗