SEARCH · Engineering Papers

Results for “automated and autonomous experiments”

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 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Reimagining metal-organic framework discovery: Integrating experiment, computation, and artificial intelligence

The traditional development of novel metal–organic frameworks (MOFs) is often hindered by challenges such as synthetic accessibility and time- and resource-intensive experimentation. High-throughput, automated experimental and computational techniques have enabled rapid chemical space exploration and theoretical MOF design. When combined with artificial intelligence (AI), these methods can be used to lead autonomous laboratories to new frontiers for MOF discovery, where these materials can be designed for a specific application, efficiently synthesized, characterized, and evaluated. Here, this perspective highlights the role of AI in advancing automated MOF synthesis and characterization, computational MOF design and screening, and the integration of these approaches within autonomous workflows to ultimately enable the MOF laboratories of the future.

Gaidimas, Madeleine A. [Northwestern University, E↗

DOE OSTI2025

AI Applications to Physics Experiments at Jefferson Lab

We survey how AI/ML is being deployed across Jefferson Lab's experimental and accelerator programs. In EPSCI, Hydra applies computer vision to automate real-time data-quality monitoring across all four experimental halls, replacing manual inspection of hundreds to thousands of histograms per shift. AIEC (AI Experiment Controls) uses ML to stabilize drift chamber gains and is now part of standard CEBAF production running, while AI Optimized Polarization (AIOP) targets autonomous control of polarized targets and photon beam angular alignment. In CASA, cavity fault classification models identify faulted cavities and trip types from waveform data with ~85% and ~78% agreement to labeled data, respectively, and are deployed in production; a separate effort applies LLMs and hybrid search to make the CEBAF operations logbook AI-ready. QCD-focused work includes transformer- and GAN-based generative models for particle-level event simulation, with distributed GAN training scaling studies on Polaris. Additional efforts span ML-on-FPGA for the EIC and a new Data Science Department coordinating anomaly detection, uncertainty quantification, and HPC-scalable ML lab-wide. Collectively, these projects illustrate AI's growing role in improving efficiency across JLab's nuclear physics mission.

Mei, Xinxin [Thomas Jefferson National Accelerator↗

NASA NTRS1998

Autonomous Satellite Command and Control through the World Wide Web: Phase 3

NASA's New Millenium Program (NMP) has identified a variety of revolutionary technologies that will support orders of magnitude improvements in the capabilities of spacecraft missions. This program's Autonomy team has focused on science and engineering automation technologies. In doing so, it has established a clear development roadmap specifying the experiments and demonstrations required to mature these technologies. The primary developmental thrusts of this roadmap are in the areas of remote agents, PI/operator interface, planning/scheduling fault management, and smart execution architectures. Phases 1 and 2 of the ASSET Project (previously known as the WebSat project) have focused on establishing World Wide Web-based commanding and telemetry services as an advanced means of interfacing a spacecraft system with the PI and operators. Current automated capabilities include Web-based command submission, limited contact scheduling, command list generation and transfer to the ground station, spacecraft support for demonstrations experiments, data transfer from the ground station back to the ASSET system, data archiving, and Web-based telemetry distribution. Phase 2 was finished in December 1996. During January-December 1997 work was commenced on Phase 3 of the ASSET Project. Phase 3 is the subject of this report. This phase permitted SSDL and its project partners to expand the ASSET system in a variety of ways. These added capabilities included the advancement of ground station capabilities, the adaptation of spacecraft on-board software, and the expansion of capabilities of the ASSET management algorithms. Specific goals of Phase 3 were: (1) Extend Web-based goal-level commanding for both the payload PI and the spacecraft engineer; (2) Support prioritized handling of multiple PIs as well as associated payload experimenters; (3) Expand the number and types of experiments supported by the ASSET system and its associated spacecraft; (4) Implement more advanced resource management, modeling and fault management capabilities that integrate the space and ground segments of the space system hardware; (5) Implement a beacon monitoring test; (6) Implement an experimental blackboard controller for space system management; (7) Further define typical ground station developments required for Internet-based remote control and for full system automation of the PI-to-spacecraft link. Each of those goals is examined in the next section. Significant sections of this report were also published as a conference paper.

Cantwell, Brian↗

DOE OSTI2025

Development and flight-testing of modular autonomous cultivation systems for biological plastics upcycling aboard the ISS

Cultivation of microorganisms in space has enormous potential to enable in-situ resource utilization (ISRU) Here, we develop an autonomous payload with fully programmable serial passaging and sample preservation, termed the Modular Open Biological Platform (MOBP), and flight-test the MOBP aboard the International Space Station (ISS) by conducting enzymatic and microbial plastics upcycling experiments. The MOBP is a compact, modular bioreactor system that allows for sustained microbial growth via automated media transfers, such as those for sample collection and storage for terrestrial analyses, and precise data monitoring from integrated sensors. The MOBP was flight-tested with two experiments designed to evaluate biological upcycling of the plastic poly(ethylene terephthalate) (PET). The bioproduct βKA can be polymerized into a nylon-6,6 analog with improved properties for use in the production of a variety of materials. We posit the MOBP will aid in democratizing the execution of synthetic biology in spaceflight towards enabling ISRU.

09 BIOMASS FUELS↗

DOE OSTI2023

Moving-horizon false data injection attack design against cyber–physical systems

Systematic attack design is essential to understanding the vulnerabilities of cyber–physical systems (CPSs), to better design for resiliency. In particular, false data injection attacks (FDIAs) are well-known and have been shown to be capable of bypassing bad data detection (BDD) while causing targeted biases in resulting state estimates. However, their effectiveness against moving horizon estimators (MHE) is not well understood. In fact, this paper shows that conventional FDIAs are generally ineffective against MHE. One of the main reasons is that the moving window renders the static FDIA recursively infeasible. Here, this paper proposes a new attack methodology, moving-horizon FDIA (MH-FDIA), by considering both the performance of historical attacks and the current system’s status. Theoretical guarantees for successful attack generation and recursive feasibility are given. Numerical simulations on the IEEE-14 bus system further validate the theoretical claims and show that the proposed MH-FDIA outperforms state-of-the-art counterparts in both stealthiness and effectiveness. In addition, an experiment on a path-tracking control system of an autonomous vehicle shows the feasibility of the MH-FDIA in real-world nonlinear systems.

42 ENGINEERING↗

DOE OSTI2023

AutoTG: Reinforcement Learning-Based Symbolic Optimization for AI-Assisted Power Converter Design

Power converters are pervasive in modern electronic component design. They can be found in all electronic devices from household appliances and cellphone chargers to vehicles. Currently, designing new circuit topologies is hard because it requires human expertise based on experience and is difficult to automate. However, artificial-intelligence-assisted design can significantly facilitate the development of new power converters and/or improve the final result. Intelligently designed highly efficient power converters can have a significant effect on many important attributes, such as power efficiency, layout size, cost, heat dissemination, energy requirements, etc. We propose Autonomous Topology Generator (AutoTG), a reinforcement-learning-based framework that generates power converter topology candidates based on user specifications, optimized for user preferences. By modeling power converter design as a symbolic optimization problem, we sequentially sample components in an autoregressive manner until new topologies are formed, providing both the topology specification and the sizing (magnitude of each component parameter) of the proposed power converter. Here, we provide an empirical evaluation and show that AutoTG is able to generate varied high-efficiency topologies within component restrictions based on user input and show that previously unknown topologies can be found for further evaluation.

(AI)-based design↗

NASA NTRS2018

Human-Automation Allocations for Current Robotic Space Operations

Within the Human Research Program, one risk delineates the uncertainty surrounding crew working with automation and robotics in spaceflight. The Risk of Inadequate Design of Human and Automation/Robotic Integration (HARI) is concerned with the detrimental effects on crew performance due to ineffective user interfaces, system designs and/or functional task allocation, potentially compromising mission success and safety. Risk arises because we have limited experience with complex automation and robotics. One key gap within HARI, is the gap related to functional allocation. The gap states: We need to evaluate, develop, and validate methods and guidelines for identifying human-automation/robot task information needs, function allocation, and team composition for future long duration, long distance space missions. Allocations determine the human-system performance as it identifies the functions and performance levels required by the automation/robotic system, and in turn, what work the crew is expected to perform and the necessary human performance requirements. Allocations must take into account each of the human, automation, and robotic systems capabilities and limitations. Some functions may be intuitively assigned to the human versus the robot, but to optimize efficiency and effectiveness, purposeful role assignments will be required. The role of automation and robotics will significantly change in future exploration missions, particularly as crew becomes more autonomous from ground controllers. Thus, we must understand the suitability of existing function allocation methods within NASA as well as the existing allocations established by the few robotic systems that are operational in spaceflight. In order to evaluate future methods of robotic allocations, we must first benchmark the allocations and allocation methods that have been used. We will present 1) documentation of human-automation-robotic allocations in existing, operational spaceflight systems; and 2) To gather existing lessons learned and best practices in these role assignments, from spaceflight operational experience of crew and ground teams that may be used to guide development for future systems. NASA and other space agencies have operational spaceflight experience with two key Human-Automation-Robotic (HAR) systems: heavy lift robotic arms and planetary robotic explorers. Additionally, NASA has invested in high-fidelity rover systems that can carry crew, building beyond Apollo's lunar rover. The heavy lift robotic arms reviewed are: Space Station Remote Manipulator System (SSRMS), Japanese Remote Manipulator System (JEMRMS), and the European Robotic Arm (ERA, designed but not deployed in space). The robotic rover systems reviewed are: Mars Exploration Rovers, Mars Science Laboratory rover, and the high-fidelity K10 rovers. Much of the design and operational feedback for these systems have been communicated to flight controllers and robotic design teams. As part of the mitigating the HARI risk for future human spaceflight operations, we must document function allocations between robots and humans that have worked well in practice.

robotic allocation↗

DOE OSTI2023

Approaches for Synthesis and Deployment of Controller Models on Automated Vehicles for Car-following in Mixed Autonomy

This paper describes the software design patterns and vehicle interfaces that were employed to transition vehicle controllers from simulation environments to open-road field experiments. The approach relies on a life cycle that utilizes model-based design and code generation, along with agile software development, and both software and hardware-in-the-loop testing, with additional safety margins. Autonomous designs should consider the dynamics of mixed autonomy in traffic to safely operate among humans. The software that provides a vehicle’s behavior intelligence is often developed through simulation, which may have a mismatch between dynamics, or as a result of a reinforcement learning workflow, which may be a black box with challenges to analyze. In each of these cases, it is important to have research interfaces that provide strongly typed data streams accessible to researchers who are not software experts while continuing to satisfy safety and liveness constraints. This paper describes how we design the hardware platform interfaces and software design process for a mixed autonomy traffic experiment with a leader-follower scenario. Controller synthesis for these vehicles requires clearly articulated vehicle interfaces and software design patterns for successful onboard deployment. Testing strategies for such controllers are also described before algorithms are transitioned to full-scale field experiments with safety operators for the vehicles. Testing strategies include software-in-the-loop simulation testing, hardware-in-the-loop simulation, ghost-car testing, and read-only testing in live traffic. With our approach, we were not only able to validate our controller synthesized in scripts and simulation, but also able to scale deployment to multiple vehicles.

Bhadani, Rahul↗

DOE OSTI2026

A Smart Vision-Aided RICH (Robotic Interface Control and Handling) System for VULCAN

High-flux neutron beams and high-efficiency detectors enable rapid neutron diffraction measurements at the Engineering Materials Diffractometer (VULCAN) at the Spallation Neutron Source (SNS), Oak Ridge National Laboratory (ORNL). To optimize beam time utilization, efficient sample exchange, alignment, and automated measurements are essential. Recent advances in artificial intelligence (AI) have expanded the capabilities of robotic systems. Here, we report the development of a Robotic Interactive Control and Handling (RICH) system for sample handling at VULCAN, designed to support high-throughput experiments and reduce overhead time. The RICH system employs a six-axis desktop robot integrated with AI-based computer vision models capable of recognizing and localizing samples in real time from instrument and depth-resolving cameras. Vision algorithms combine these detections to align samples with designated measurement positions or place them within complex sample environments such as furnaces. This integration of machine learning-assisted vision with robotic handling demonstrates the feasibility of autonomous sample detection and preparation, offering a pathway toward fully unmanned neutron scattering experiments.

automation↗

NASA NTRS2008

Automated Generation and Assessment of Autonomous Systems Test Cases

This slide presentation reviews some of the issues concerning verification and validation testing of autonomous spacecraft routinely culminates in the exploration of anomalous or faulted mission-like scenarios using the work involved during the Dawn mission's tests as examples. Prioritizing which scenarios to develop usually comes down to focusing on the most vulnerable areas and ensuring the best return on investment of test time. Rules-of-thumb strategies often come into play, such as injecting applicable anomalies prior to, during, and after system state changes; or, creating cases that ensure good safety-net algorithm coverage. Although experience and judgment in test selection can lead to high levels of confidence about the majority of a system's autonomy, it's likely that important test cases are overlooked. One method to fill in potential test coverage gaps is to automatically generate and execute test cases using algorithms that ensure desirable properties about the coverage. For example, generate cases for all possible fault monitors, and across all state change boundaries. Of course, the scope of coverage is determined by the test environment capabilities, where a faster-than-real-time, high-fidelity, software-only simulation would allow the broadest coverage. Even real-time systems that can be replicated and run in parallel, and that have reliable set-up and operations features provide an excellent resource for automated testing. Making detailed predictions for the outcome of such tests can be difficult, and when algorithmic means are employed to produce hundreds or even thousands of cases, generating predicts individually is impractical, and generating predicts with tools requires executable models of the design and environment that themselves require a complete test program. Therefore, evaluating the results of large number of mission scenario tests poses special challenges. A good approach to address this problem is to automatically score the results based on a range of metrics. Although the specific means of scoring depends highly on the application, the use of formal scoring - metrics has high value in identifying and prioritizing anomalies, and in presenting an overall picture of the state of the test program. In this paper we present a case study based on automatic generation and assessment of faulted test runs for the Dawn mission, and discuss its role in optimizing the allocation of resources for completing the test program.

Testing challenges↗

DOE OSTI2026

Operating advanced scientific instruments with AI agents that learn on the job

Advanced scientific user facilities, such as next generation X-ray light sources and self-driving laboratories, are revolutionizing scientific discovery by automating routine tasks and enabling rapid experimentation and characterizations. However, these facilities must continuously evolve to support new experimental workflows, adapt to diverse user projects, and meet growing demands for more intricate instruments and experiments. This continuous development introduces significant operational complexity, necessitating a focus on usability, reproducibility, and intuitive human-instrument interaction. In this work, we explore the integration of agentic AI, powered by Large Language Models (LLMs), as a transformative tool to achieve this goal. We present our approach to developing a human-in-the-loop pipeline for operating advanced instruments including an X-ray nanoprobe beamline and an autonomous robotic station dedicated to the design and characterization of materials. Specifically, we evaluate the potential of various LLMs as trainable scientific assistants for orchestrating complex, multi-task workflows, which also include multimodal data, optimizing their performance through optional human input and iterative learning. We demonstrate the ability of AI agents to bridge the gap between advanced automation and user-friendly operation, paving the way for more adaptable and intelligent scientific facilities.

Large Language Models↗

DOE OSTI2020

Autonomous materials discovery driven by Gaussian process regression with inhomogeneous measurement noise and anisotropic kernels

Abstract A majority of experimental disciplines face the challenge of exploring large and high-dimensional parameter spaces in search of new scientific discoveries. Materials science is no exception; the wide variety of synthesis, processing, and environmental conditions that influence material properties gives rise to particularly vast parameter spaces. Recent advances have led to an increase in the efficiency of materials discovery by increasingly automating the exploration processes. Methods for autonomous experimentation have become more sophisticated recently, allowing for multi-dimensional parameter spaces to be explored efficiently and with minimal human intervention, thereby liberating the scientists to focus on interpretations and big-picture decisions. Gaussian process regression (GPR) techniques have emerged as the method of choice for steering many classes of experiments. We have recently demonstrated the positive impact of GPR-driven decision-making algorithms on autonomously-steered experiments at a synchrotron beamline. However, due to the complexity of the experiments, GPR often cannot be used in its most basic form, but rather has to be tuned to account for the special requirements of the experiments. Two requirements seem to be of particular importance, namely inhomogeneous measurement noise (input-dependent or non-i.i.d.) and anisotropic kernel functions, which are the two concepts that we tackle in this paper. Our synthetic and experimental tests demonstrate the importance of both concepts for experiments in materials science and the benefits that result from including them in the autonomous decision-making process.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Autonomous Molecular Structure Imaging with High-Resolution Atomic Force Microscopy for Molecular Mixture Discovery

Due to its single-molecule sensitivity, high-resolution atomic force microscopy (HR-AFM) has proved to be a valuable and uniquely advantageous tool to study complex molecular mixtures, which hold promise for developing clean energy and achieving environmental sustainability. However, significant challenges remain to achieve the full potential of the sophisticated and time-consuming experiments. Automation combined with machine learning (ML) and artificial intelligence (AI) is key to overcoming these challenges. Here we present Auto-HR-AFM, an AI tool to automatically collect HR-AFM images of petroleum-based mixtures. In this study, we trained an instance segmentation model to teach Auto-HR-AFM how to recognize features in HR-AFM images. Auto-HR-AFM then uses that information to optimize the imaging by adjusting the probe-molecule distance for each molecule in the run. Auto-HR-AFM is the initial tool that will lead to fully automated scanning probe microscopy (SPM) experiments, from start to finish. This automation will allow SPM to become a mainstream characterization technique for complex mixtures, an otherwise unattainable target.

36 MATERIALS SCIENCE↗

NASA NTRS2006

Application of the H-Mode, a Design and Interaction Concept for Highly Automated Vehicles, to Aircraft

Driven by increased safety, efficiency, and airspace capacity, automation is playing an increasing role in aircraft operations. As aircraft become increasingly able to autonomously respond to a range of situations with performance surpassing human operators, we are compelled to look for new methods that help us understand their use and guide their design using new forms of automation and interaction. We propose a novel design metaphor to aid the conceptualization, design, and operation of highly-automated aircraft. Design metaphors transfer meaning from common experiences to less familiar applications or functions. A notable example is the "Desktop metaphor" for manipulating files on a computer. This paper describes a metaphor for highly automated vehicles known as the H-metaphor and a specific embodiment of the metaphor known as the H-mode as applied to aircraft. The fundamentals of the H-metaphor are reviewed followed by an overview of an exploratory usability study investigating human-automation interaction issues for a simple H-mode implementation. The envisioned application of the H-mode concept to aircraft is then described as are two planned evaluations.

Goodrich, Kenneth H.↗

NASA NTRS1986

Artificial intelligence planning applications for space exploration and space robotics

Mission sequencing involves the plan for actuation of the experiments to be conducted aboard a spacecraft; automation is under study by NASA as a means to reduce time and manpower costs in mission planning and in robotic implementation. The development of a mission sequence is conditioned by the limited duration of advantageous spacecraft encounters with objects of study, more research requests than can be satisfied, and requested changes in objectives. Autonomous robot development is hampered by the absence of task-level programming languages, the existence of anomalies in real-world interactions, and a lack of required capabilities in current sensor technology.

Rokey, Mark↗

DOE OSTI2025

Exploring Large Language Model Agents in Cybersecurity: A Literature Review with Experiments

The accelerated development and integration of large language model (LLM) agents have led researchers and developers to explore their effectiveness in cybersecurity, specifically with penetration testing (pentesting). Recent research efforts have attempted to use LLM agents to automate the process of pentesting because of the cost and time requirements that are required to perform a manual review. However, not all of the tools perform as expected. This paper reviews some of the newest and most popular autonomous pentesting frameworks, highlighting the capabilities and limitations of each one with the goal of providing the components needed to successfully and effectively build an autonomous pentesting agent in the future.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Modular Autonomous Experimentation for Biological Applications

The Modular Autonomous Research System (MARS) was created to address a key challenge in scientific discovery: experiments are often slow, require significant manual labor, and generate data that is not easily integrated across different tools. This limits how quickly scientists can explore new materials, processes, and chemical reactions. Our motivation was to design a system that makes research faster, more reliable, and adaptable by combining automation with artificial intelligence. By doing so, we aimed to reduce human error, accelerate discovery, and allow researchers to quickly test many possibilities that would otherwise take months or years. Our approach was to build a flexible platform that connects laboratory robots, measurement instruments, and a central data system, all guided by artificial intelligence. MARS integrates liquid handling robots, robotic arms, and plate readers with an intelligent decision-making system that chooses the most informative experiments to run next. This creates a closed loop where experiments are performed automatically, the data is analyzed in real time, and new conditions are immediately tested. Through this work, we demonstrated that MARS can carry out multiple experiments with little or no human intervention, adapt to different scientific problems, and handle uncertain or noisy measurements in a robust way. The results show that modular and intelligent automation can significantly accelerate the pace of discovery, providing a model for future self-driving laboratories. This approach addresses the growing scientific need for adaptable, data-driven research platforms that can keep up with the complexity and scale of modern science.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1986

Automation and robotics for Space Station in the twenty-first century

Space Station telerobotics will evolve beyond the initial capability into a smarter and more capable system as we enter the twenty-first century. Current technology programs including several proposed ground and flight experiments to enable development of this system are described. Advancements in the areas of machine vision, smart sensors, advanced control architecture, manipulator joint design, end effector design, and artificial intelligence will provide increasingly more autonomous telerobotic systems.

Willshire, K. F.↗