Remote Agent Demonstration
We describe the computer demonstration of the Remote Agent Experiment (RAX). The Remote Agent is a high-level, model-based, autonomous control agent being validated on the NASA Deep Space 1 spacecraft.
Dorais, Gregory A.↗
SEARCH · Search NASA
Results for “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.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Evidence Report: Risk of Performance Errors Due to Training Deficiencies
Substantial evidence supports the claim that inadequate training leads to performance errors. Barshi and Loukopoulos (2012) demonstrate that even a task as carefully developed and refined over many years as operating an aircraft can be significantly improved by a systematic analysis, followed by improved procedures and improved training (see also Loukopoulos, Dismukes, & Barshi, 2009a). Unfortunately, such a systematic analysis of training needs rarely occurs during the preliminary design phase, when modifications are most feasible. Training is often seen as a way to compensate for deficiencies in task and system design, which in turn increases the training load. As a result, task performance often suffers, and with it, the operators suffer and so does the mission. On the other hand, effective training can indeed compensate for such design deficiencies, and can even go beyond to compensate for failures of our imagination to anticipate all that might be needed when we send our crew members to go where no one else has gone before. Much of the research literature on training is motivated by current training practices aimed at current training needs. Although there is some experience with operations in extreme environments on Earth, there is no experience with long-duration space missions where crews must practice semi-autonomous operations, where ground support must accommodate significant communication delays, and where so little is known about the environment. Thus, we must develop robust methodologies and tools to prepare our crews for the unknown. The research necessary to support such an endeavor does not currently exist, but existing research does reveal general challenges that are relevant to long-duration, high-autonomy missions. The evidence presented here describes issues related to the risk of performance errors due to training deficiencies. Contributing factors regarding training deficiencies may pertain to organizational process and training programs for spaceflight, such as when training programs are inadequate or unavailable. Furthermore, failure to match between tasks on the one hand, and learning and memory abilities on the other hand is a contributing factor, especially when individuals' relative efficiency with which new information is acquired, and adjustments made in behavior or thinking, are inconsistent with mission demands. Thus, if training deficiencies are present, the likelihood of errors or of the inability to successfully complete a task increases. What's more, the overall risk to the crew, the vehicle, and the mission increases.
Barshi, Immanuel↗
Online Self-Supervised Long-Range Scene Segmentation for MAVs
Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles (MAVs). As these robots aspire for high-speed autonomous flights in complex dynamic environments, robust scene understanding at long-range becomes critical. The problem is heavily characterized by either the limitations imposed by sensor capabilities for geometry-based methods, or the need for large-amounts of manually annotated training data required by data-driven methods. This motivates the need to build systems that have the capability to alleviate these problems by exploiting the complimentary strengths of both geometry and data-driven methods. In this paper, we take a step in this direction and propose a generic framework for adaptive scene segmentation using self-supervised online learning. We present this in the context of vision-based autonomous MAV flight, and demonstrate the efficacy of our proposed system through extensive experiments on benchmark datasets and real world field tests.
Matthies, Larry↗
Towards Agentic AI on Particle Accelerators
As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.
43 PARTICLE ACCELERATORS↗
The German/Russian MIR 1997 Mission: An Overview
Session TP4 includes short reports concerning: (1) Life Science Experiments During the German-Russian Mir '97 Mission; (2) Orthostatic Intolerance Following Microgravity: A Role for Autonomic Dysfunction; (3) Heart Rate Variability and Skin Blood Flow in Man During Orthostatic Stress in Weightlessness; (4) Effects of Microgravity and Lower Body Negative Pressure on Circulatory Drives from Excercising Calf Muscles; (5) The Mir Station in Its Second Decade: Crew Science Operation During Mir '97; (6) Metabolic WARD (Water, Sodium, Calcium, and Bone Metabolism) and Endocrinological Experiments During the Mir '97 Mission; (7) Long-term Monitoring of the Spine-geometry During the Mir '97 Mission: Introduction of a New Method; and (8) Effects of 20 days of Microgravity (German/Russian Mir '97 Mission) on the Mechanical and Electromyographic Characteristics of Explosive Efforts of the Lower Limbs and of Cycloergometric Exercises of Mild to Sprint-Like Intensity.
Source record↗
Onboard Autonomy and Ground Operations Automation for the Intelligent Payload Experiment (IPEX) CubeSat Mission
The Intelligent Payload Experiment (IPEX) is a cubesat manifested for launch in October 2013 that will flight validate autonomous operations for onboard instrument processing and product generation for the Intelligent Payload Module (IPM) of the Hyperspectral Infra-red Imager (HyspIRI) mission concept. We first describe the ground and flight operations concept for HyspIRI IPM operations. We then describe the ground and flight operations concept for the IPEX mission and how that will validate HyspIRI IPM operations. We then detail the current status of the mission and outline the schedule for future development.
project data planning↗
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↗
New potentials of NIICHIMMASH's thermal vacuum facilities
The potentialities of existing test facilities as to simulating space environment governing factors for spacecraft successful development thermal vacuum testing are analyzed, ways of modernizing existing test facilities and specific proposals on their redesign are considered. The problem of spacecraft (S/C) ground development in simulated external environments, the solution of which started more than 30 years ago, has not lost its urgency today. Stringent requirements on S/C active lifetime under space conditions, module large dimensions, great number of extension elements and complicated mode of their interaction in long mission do not allow S/C designers to abandon ground tests. S/C thermal modes development is a combination of calculations, thermal vacuum tests and actions on improving S/C design and its thermal control system. Traditionally, tests are carried out by stages from component and end unit level verifications to complex tests of modules and S/C as a whole. In our opinion, sufficient correctness of calculated models and experience gained in organizations designing space systems allow to reduce cost and time of autonomous tests. Unfortunately, this is not true for complex (integrated) thermal vacuum tests. More than that, their recent programs include tasks of verifying other (than thermal control system) systems if S/C for operation under space simulated conditions. The outlined circumstances are the main reason for critical review of the potentialities of the existing test base, and of NIICHIMMASH's two large thermal vacuum chambers, first of all. The reasons for and ways of enlargement of these facilities potentially are analyzed and the results attained are described.
Afanassiev, N. A.↗
Next Generation Remote Agent Planner
In May 1999, as part of a unique technology validation experiment onboard the Deep Space One spacecraft, the Remote Agent became the first complete autonomous spacecraft control architecture to run as flight software onboard an active spacecraft. As one of the three components of the architecture, the Remote Agent Planner had the task of laying out the course of action to be taken, which included activities such as turning, thrusting, data gathering, and communicating. Building on the successful approach developed for the Remote Agent Planner, the Next Generation Remote Agent Planner is a completely redesigned and reimplemented version of the planner. The new system provides all the key capabilities of the original planner, while adding functionality, improving performance and providing a modular and extendible implementation. The goal of this ongoing project is to develop a system that provides both a basis for future applications and a framework for further research in the area of autonomous planning for spacecraft. In this article, we present an introductory overview of the Next Generation Remote Agent Planner. We present a new and simplified definition of the planning problem, describe the basics of the planning process, lay out the new system design and examine the functionality of the core reasoning module.
Jonsson, Ari K.↗
Critical Team Composition Issues for Long-Distance and Long-Duration Space Exploration: A Literature Review, an Operational Assessment, and Recommendations for Practice and Research
Prevailing team effectiveness models suggest that teams are best positioned for success when certain enabling conditions are in place (Hackman, 1987; Hackman, 2012; Mathieu, Maynard, Rapp, & Gilson, 2008; Wageman, Hackman, & Lehman, 2005). Team composition, or the configuration of member attributes, is an enabling structure key to fostering competent teamwork (Hackman, 2002; Wageman et al., 2005). A vast body of research supports the importance of team composition in team design (Bell, 2007). For example, team composition is empirically linked to outcomes such as cooperation (Eby & Dobbins, 1997), social integration (Harrison, Price, Gavin, & Florey, 2002), shared cognition (Fisher, Bell, Dierdorff, & Belohlav, 2012), information sharing (Randall, Resick, & DeChurch, 2011), adaptability (LePine, 2005), and team performance (e.g., Bell, 2007). As such, NASA has identified team composition as a potentially powerful means for mitigating the risk of performance decrements due to inadequate crew cooperation, coordination, communication, and psychosocial adaptation in future space exploration missions. Much of what is known about effective team composition is drawn from research conducted in conventional workplaces (e.g., corporate offices, production plants). Quantitative reviews of the team composition literature (e.g., Bell, 2007; Bell, Villado, Lukasik, Belau, & Briggs, 2011) are based primarily on traditional teams. Less is known about how composition affects teams operating in extreme environments such as those that will be experienced by crews of future space exploration missions. For example, long-distance and long-duration space exploration (LDSE) crews are expected to live and work in isolated and confined environments (ICEs) for up to 30 months. Crews will also experience communication time delays from mission control, which will require crews to work more autonomously (see Appendix A for more detailed information regarding the LDSE context). Given the unique context within which LDSE crews will operate, NASA identified both a gap in knowledge related to the effective composition of autonomous, LDSE crews, and the need to identify psychological and psychosocial factors, measures, and combinations thereof that can be used to compose highly effective crews (Team Gap 8). As an initial step to address Team Gap 8, we conducted a focused literature review and operational assessment related to team composition issues for LDSE. The objectives of our research were to: (1) identify critical team composition issues and their effects on team functioning in LDSE-analogous environments with a focus on key composition factors that will most likely have the strongest influence on team performance and well-being, and 1 Astronaut diary entry in regards to group interaction aboard the ISS (p.22; Stuster, 2010) 2 (2) identify and evaluate methods used to compose teams with a focus on methods used in analogous environments. The remainder of the report includes the following components: (a) literature review methodology, (b) review of team composition theory and research, (c) methods for composing teams, (d) operational assessment results, and (e) recommendations.
Bell, Suzanne T.↗
Ground-based Characterization of Plant Water Management (PWM) Hydroponic Root Modules for Spaceflight
Hydroponic crop production in space is crucial for long-term space travel but faces numerous challenges – one of which is providing sufficient dissolved oxygen (DO) in nutrient solution. In microgravity environments, surface tension is the primary force acting on liquids, causing water to form into suspended spherical droplets. This can suffocate plants as the liquid clings onto plant roots and the lack of aeration deprives the plant of oxygen needed for growth. To overcome these challenges, plant water management (PWM) systems explore options of growing plants in space autonomously and passively through capillary forces. From 2018-2023, there have been 6 PWM experiments conducted on the ISS. In past experiments conducted in microgravity, bubbles formed in test cells have disrupted fluid dynamics and may adversely affect plant growth. The accumulation of bubbles may lead to inconsistent nutrient delivery, break prime in tubing, and suspend plant roots in air, leading to plant stress and eventually death. Current research efforts focus on the oxygenation capabilities of the PWM system along with a comprehensive sensor array that will improve nutrient and DO monitoring capabilities.
L Wang↗
Real-time tracking of objects for a KC-135 microgravity experiment
The design of a visual tracking system for use on the Extra-Vehicular Activity Helper/Retriever (EVAHR) is discussed. EVAHR is an autonomous robot designed to perform numerous tasks in an orbital microgravity environment. Since the ability to grasp a freely translating and rotating object is vital to the robot's mission, the EVAHR must analyze range image generated by the primary sensor. This allows EVAHR to locate and focus its sensors so that an accurate set of object poses can be determined and a grasp strategy planned. To test the visual tracking system being developed, a mathematical simulation was used to model the space station environment and maintain dynamics on the EVAHR and any other free floating objects. A second phase of the investigation consists of a series of experiments carried out aboard a KC-135 aircraft flying a parabolic trajectory to simulate microgravity.
Littlefield, Mark L.↗
Vision Based Autonomous Robotic Control for Advanced Inspection and Repair
The advanced inspection system is an autonomous control and analysis system that improves the inspection and remediation operations for ground and surface systems. It uses optical imaging technology with intelligent computer vision algorithms to analyze physical features of the real-world environment to make decisions and learn from experience. The advanced inspection system plans to control a robotic manipulator arm, an unmanned ground vehicle and cameras remotely, automatically and autonomously. There are many computer vision, image processing and machine learning techniques available as open source for using vision as a sensory feedback in decision-making and autonomous robotic movement. My responsibilities for the advanced inspection system are to create a software architecture that integrates and provides a framework for all the different subsystem components; identify open-source algorithms and techniques; and integrate robot hardware.
sensory feedback↗
Autonomous support for microorganism research in space
A preliminary design for performing on-orbit, autonomous research on microorganisms and cultured cells/tissues is presented. An understanding of gravity and its effects on cells is crucial for space exploration as well as for terrestrial applications. The payload is designed to be compatible with the COMmercial Experiment Transported (COMET) launch vehicle, an orbiter middeck locker interface, and with Space Station Freedom. Uplink/downlink capabilities and sample return through controlled reentry are available for all carriers. Autonomous testing activities are preprogrammed with inflight reprogrammability. Sensors for monitoring temperature, pH, light, gravity levels, vibration, and radiation are provided for environmental regulation and experimental data collection. Additional experiment data acquisition includes optical density measurement, microscopy, video, and file photography. Onboard full data storage capabilities are provided. A fluid transfer mechanism is utilized for inoculation, sampling, and nutrient replenishment of experiment cultures. In addition to payload design, representative experiments were developed to ensure scientific objectives remained compatible with hardware capabilities. The project is defined to provide biological data pertinent to extended duration crewed space flight including crew health issues and development of a Controlled Ecological Life Support System (CELSS). In addition, opportunities are opened for investigations leading to commercial applications of space, such as pharmaceutical development, modeling of terrestrial diseases, and material processing.
Luttges, M. W.↗
Statistical learning framework for safety and failure analysis of a DNN-based autonomous aircraft system
Deep Neural Networks (DNNs) and Machine Learning technology is increasingly used for safety-critical applications in the Aerospace domain. To ensure safe operations, the DNN and the system must undergo rigorous verification and validation, including advanced statistical analyses. Performance and safety of the DNN and system behavior must not only be analyzed for the nominal case, but under numerous off-nominal and failure cases. In this paper we will describe how our statistical learning framework SYSAI can efficiently perform such analyses using the tool’s unique combination of advanced learning modeling and statistical analysis techniques. SYSAI can effectively explore the high-dimensional state and failure space of the system under test; geometrical shape detection of safety regions and boundaries support explainability of the results to the designer. In this paper, we report experiments and results obtained with a vision-based DNN control system (ACT) that is capable of autonomously steering an aircraft down a runway.
Yuning He↗
Reactive control and reasoning assistance for scientific laboratory instruments
Scientific laboratory instruments that are involved in chemical or physical sample identification frequently require substantial human preparation, attention, and interactive control during their operation. Successful real-time analysis of incoming data that supports such interactive control requires: (1) a clear recognition of variance of the data from expected results; and (2) rapid diagnosis of possible alternative hypotheses which might explain the variance. Such analysis then aids in decisions about modifying the experiment protocol, as well as being a goal itself. This paper reports on a collaborative project at the NASA Ames Research Center between artificial intelligence researchers and planetary microbial ecologists. Our team is currently engaged in developing software that autonomously controls science laboratory instruments and that provides data analysis of the real-time data in support of dynamic refinement of the experiment control. the first two instruments to which this technology has been applied are a differential thermal analyzer (DTA) and a gas chromatograph (GC). coupled together, they form a new geochemicstry and microbial analysis tool that is capable of rapid identification of the organiz and mineralogical constituents in soils. The thermal decomposition of the minerals and organics, and the attendance release of evolved gases, provides data about the structural and molecular chemistry of the soil samples.
Thompson, David E.↗
CONCAP 4: A Complex Autonomous Payload (CAP) for growing organic thin films in microgravity
A GAS facility has been developed for carrying out low temperature experiments. The arrangement being used on CONCAP IV-01 is designed for thin film growth in microgravity and can process up to twelve samples per mission. The nonlinear optical oven hardware can also be made suitable for other low temperature applications, such as gradient freeze and solution growth of crystals.
Carswell, W. E.↗
An Overview of the Guided Parafoil System Derived from X-38 Experience
The NASA Johnson Space Center built a 4200 sq ft parafoil for the U.S. Army Natick Soldier Center to demonstrate autonomous flight using a guided parafoil system to deliver 10,000 lbs of useable payload. The parafoil's design was based upon that developed during the X-38 program. The drop test payload consisted of a standard 20-foot Type V airdrop platform, a standard 12-foot weight tub, a 60 ft drogue parachute, a 4200 ft2 parafoil, an instrumentation system, and a Guidance, Navigation, and Control (GN&C) system. Instrumentation installed on the load was used to gather data to validate simulation models and preflight loads predictions and to perform post flight trajectory and performance reconstructions. The GN&C system, developed during NASA's X-38 program, consisted of a flight computer, modems for uplink commands and downlink data, a compass, laser altimeter, and two winches. The winches were used to steer the parafoil and to perform the dynamic flare maneuver for a soft landing. The laser was used to initiate the flare. The GN&C software was originally provided to NASA by the European Space Agency. NASA incorporated further software refinements based upon the X-38 flight test results. Three full-scale drop tests were conducted, with the third being performed during the Precision Airdrop Technology Conference and Demonstration (PATCAD) Conference at the U.S. Army Yuma Proving Ground (YPG) in November of 2003. For the PATCAD demonstration, the parafoil and GN&C software and hardware performed well, concluding with a good flare and the smallest miss distance ever experienced in NASA's parafoil drop test program. This paper describes the 4200 sq ft parafoil system, simulation results, and the results of the drop tests.
Stein, Jenny M.↗