Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “autonomy diagnosis”

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
NASA NTRSDate not supplied

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗
NASA NTRSDate not supplied

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗
NASA NTRS1988

Machine intelligence and autonomy for aerospace systems

The present volume discusses progress toward intelligent robot systems in aerospace applications, NASA Space Program automation and robotics efforts, the supervisory control of telerobotics in space, machine intelligence and crew/vehicle interfaces, expert-system terms and building tools, and knowledge-acquisition for autonomous systems. Also discussed are methods for validation of knowledge-based systems, a design methodology for knowledge-based management systems, knowledge-based simulation for aerospace systems, knowledge-based diagnosis, planning and scheduling methods in AI, the treatment of uncertainty in AI, vision-sensing techniques in aerospace applications, image-understanding techniques, tactile sensing for robots, distributed sensor integration, and the control of articulated and deformable space structures.

Heer, Ewald↗
NASA NTRS1990

A model for a space shuttle safing and failure-detection expert

The safing and failure-detection expert (SAFE) is a prototype for a malfunction detection, diagnosis, and safing system for the atmospheric revitalization subsystem (ARS) in the Space Shuttle orbiter. SAFE, whose knowledge was extracted from expert-provided heuristics and documented procedures, automatically manages all phases of failure handling: detection, diagnosis, testing procedures, and recovery instructions. The SAFE architecture allows it to handle correctly sensor failures and multiple malfunctions. Since SAFE is highly interactive, it was used as a test bed for the evaluation of various advanced human-computer interface (HCI) techniques. The use of such expert systems in the next generation of space vehicles would increase their reliability and autonomy to levels not achievable before.

Zeilingold, Daphna↗
NASA NTRS2023

Distributed Sensing and Reasoning for Advanced Air Mobility Health Management and Mission Assurance

As envisioned, Advanced Air Mobility (AAM) and Urban Air Mobility (UAM) will introduce new vehicles and operations within the national airspace, moving people and cargo safely and efficiently at a much larger scale than today. Driven by transformative technology and revolutionary aircraft, this movement must still manage technical, regulatory, operational, and policy challenges. NASA’s work in support of AAM and UAM includes, but is not limited to tools, technologies, and architectures for distributed sensing of aircraft, data & reasoning services exchange, Human-Autonomy Teaming (HAT), contingency management, and vehicle health management. This paper builds upon these concepts and evaluates the use of distributed sensing and infrastructure assistance towards health management and mission assurance of UAM vehicles in specific operational scenarios. Through analysis of these example missions, aided by the data produced by the conceptual distributed sensing and reasoning infrastructure, we define opportunities for state estimation, diagnosis, and key decision points affecting the health state of the vehicle and the airspace volume. As a result, we define a number of measurable health state parameters providing relevant information to drive decision-making in contingency situations or feed automation tools in support of operators and managers.

Safety↗
NASA NTRS1996

A Model-based Approach to Reactive Self-Configuring Systems

This paper describes Livingstone, an implemented kernel for a self-reconfiguring autonomous system, that is reactive and uses component-based declarative models. The paper presents a formal characterization of the representation formalism used in Livingstone, and reports on our experience with the implementation in a variety of domains. Livingstone's representation formalism achieves broad coverage of hybrid software/hardware systems by coupling the concurrent transition system models underlying concurrent reactive languages with the discrete qualitative representations developed in model-based reasoning. We achieve a reactive system that performs significant deductions in the sense/response loop by drawing on our past experience at building fast prepositional conflict-based algorithms for model-based diagnosis, and by framing a model-based configuration manager as a prepositional, conflict-based feedback controller that generates focused, optimal responses. Livingstone automates all these tasks using a single model and a single core deductive engine, thus making significant progress towards achieving a central goal of model-based reasoning. Livingstone, together with the HSTS planning and scheduling engine and the RAPS executive, has been selected as the core autonomy architecture for Deep Space One, the first spacecraft for NASA's New Millennium program.

Williams, Brian C.↗
NASA NTRS2003

Simulation-Based Verification of Livingstone Applications

AI software is viewed as a means to give greater autonomy to automated systems, capable of coping with harsh and unpredictable environments in deep space missions. Autonomous systems pose a serious challenge to traditional test-based verification approaches, because of the enormous space of possible situations that they aim to address. Before these systems are put in control of critical applications, appropriate new verification approaches need to be developed. This article describes Livingstone PathFinder (LPF), a verification tool for autonomous diagnosis applications based on NASA's Livingstone model-based diagnosis system. LPF applies state space exploration algorithms to an instrumented testbed, consisting of the Livingstone diagnosis system embedded in a simulated operating environment. The article describes different facets of LPF and reports some experimental results from applying LPF to a Livingstone model of the main propulsion feed subsystem of the X-34 space vehicle. This paper describes Livingstone PathFinder (LPF), a verification tool for autonomous diagnosis applications based on NASA's Livingstone model-based diagnosis system. LPF applies state space exploration algorithms to an instrumented testbed, consisting of the Livingstone diagnosis system embedded in a simulated operating environment. Section 2 provides an overview of Livingstone; Section 3 describes the LPF architecture; Section 4 discusses its applicability; Section 5 reviews some experimental results; Section 6 compares LPF to related verification approaches; Section 7 draws conclusions and discusses some perspectives.

Lindsey, Anthony E.↗
NASA NTRS2014

Determining Mission Effects of Equipment Failures

NASA plans call for long duration deep space missions with human crews. Because of light-time delay and other considerations, increased autonomy is needed. Crews on next-generation missions will likely be small, perhaps with as few as four members. A small crew is not likely to possess the full range of expertise needed to deal with unexpected failures and anomalies. Applied artificial intelligence technologies have developed decision support tools with the potential to fill the gap, but these tools need to be integrated to provide a smooth operational capability. In this paper we describe such an integration involving anomaly detection, diagnosis, system effect propagation, and plan repair.

Morris, Paul↗
NASA NTRS2003

Agent Based Software for the Autonomous Control of Formation Flying Spacecraft

Distributed satellite systems is an enabling technology for many future NASA/DoD earth and space science missions, such as MMS, MAXIM, Leonardo, and LISA [1, 2, 3]. While formation flying offers significant science benefits, to reduce the operating costs for these missions it will be essential that these multiple vehicles effectively act as a single spacecraft by performing coordinated observations. Autonomous guidance, navigation, and control as part of a coordinated fleet-autonomy is a key technology that will help accomplish this complex goal. This is no small task, as most current space missions require significant input from the ground for even relatively simple decisions such as thruster burns. Work for the NMP DS1 mission focused on the development of the New Millennium Remote Agent (NMRA) architecture for autonomous spacecraft control systems. NMRA integrates traditional real-time monitoring and control with components for constraint-based planning, robust multi-threaded execution, and model-based diagnosis and reconfiguration. The complexity of using an autonomous approach for space flight software was evident when most of its capabilities were stripped off prior to launch (although more capability was uplinked subsequently, and the resulting demonstration was very successful).

How, Jonathan P.↗
NASA NTRS1998

Integration of the Remote Agent for the NASA Deep Space One Autonomy Experiment

This paper describes the integration of the Remote Agent (RA), a spacecraft autonomy system which is scheduled to control the Deep Space 1 spacecraft during a flight experiment in 1999. The RA is a reusable, model-based autonomy system that is quite different from software typically used to control an aerospace system. We describe the integration challenges we faced, how we addressed them, and the lessons learned. We focus on those aspects of integrating the RA that were either easier or more difficult than integrating a more traditional large software application because the RA is a model-based autonomous system. A number of characteristics of the RA made integration process easier. One example is the model-based nature of RA. Since the RA is model-based, most of its behavior is not hard coded into procedural program code. Instead, engineers specify high level models of the spacecraft's components from which the Remote Agent automatically derives correct system-wide behavior on the fly. This high level, modular, and declarative software description allowed some interfaces between RA components and between RA and the flight software to be automatically generated and tested for completeness against the Remote Agent's models. In addition, the Remote Agent's model-based diagnosis system automatically diagnoses when the RA models are not consistent with the behavior of the spacecraft. In flight, this feature is used to diagnose failures in the spacecraft hardware. During integration, it proved valuable in finding problems in the spacecraft simulator or flight software. In addition, when modifications are made to the spacecraft hardware or flight software, the RA models are easily changed because they only capture a description of the spacecraft. one does not have to maintain procedural code that implements the correct behavior for every expected situation. On the other hand, several features of the RA made it more difficult to integrate than typical flight software. For example, the definition of correct behavior is more difficult to specify for a system that is expected to reason about and flexibly react to its environment than for a traditional flight software system. Consequently, whenever a change is made to the RA it is more time consuming to determine if the resulting behavior is correct. We conclude the paper with a discussion of future work on the Remote Agent as well as recommendations to ease integration of similar autonomy projects.

Dorais, Gregory A.↗
NASA NTRS2001

Collaboration Between NASA Centers of Excellence on Autonomous System Software Development

Software for space systems flight operations has its roots in the early days of the space program when computer systems were incapable of supporting highly complex and flexible control logic. Control systems relied on fast data acquisition and supervisory control from a roomful of systems engineers on the ground. Even though computer hardware and software has become many orders of magnitude more capable, space systems have largely adhered to this original paradigm In an effort to break this mold, Kennedy Space Center (KSC) has invested in the development of model-based diagnosis and control applications for ten years having broad experience in both ground and spacecraft systems and software. KSC has now partnered with Ames Research Center (ARC), NASA's Center of Excellence in Information Technology, to create a new paradigm for the control of dynamic space systems. ARC has developed model-based diagnosis and intelligent planning software that enables spacecraft to handle most routine problems automatically and allocate resources in a flexible way to realize mission objectives. ARC demonstrated the utility of onboard diagnosis and planning with an experiment aboard Deep Space I in 1999. This paper highlights the software control system collaboration between KSC and ARC. KSC has developed a Mars In-situ Resource Utilization testbed based on the Reverse Water Gas Shift (RWGS) reaction. This plant, built in KSC's Applied Chemistry Laboratory, is capable of producing the large amount of Oxygen that would be needed to support a Human Mars Mission. KSC and ARC are cooperating to develop an autonomous, fault-tolerant control system for RWGS to meet the need for autonomy on deep space missions. The paper will also describe how the new system software paradigm will be applied to Vehicle Health Monitoring, tested on the new X vehicles and integrated into future launch processing systems.

Goodrich, Charles H.↗
NASA NTRS2016

Intelligent (Autonomous) Power Controller Development for Human Deep Space Exploration

As NASAs Evolvable Mars Campaign and other exploration initiatives continue to mature they have identified the need for more autonomous operations of the power system. For current human space operations such as the International Space Station, the paradigm is to perform the planning, operation and fault diagnosis from the ground. However, the dual problems of communication lag as well as limited communication bandwidth beyond GEO synchronous orbit, underscore the need to change the operation methodology for human operation in deep space. To address this need, for the past several years the Glenn Research Center has had an effort to develop an autonomous power controller for human deep space vehicles. This presentation discusses the present roadmap for deep space exploration along with a description of conceptual power system architecture for exploration modules. It then contrasts the present ground centric control and management architecture with limited autonomy on-board the spacecraft with an advanced autonomous power control system that features ground based monitoring with a spacecraft mission manager with autonomous control of all core systems, including power. It then presents a functional breakdown of the autonomous power control system and examines its operation in both normal and fault modes. Finally, it discusses progress made in the development of a real-time power system model and how it is being used to evaluate the performance of the controller and well as using it for verification of the overall operation.

Power Systems↗
NASA NTRS2004

Simulation-Based Verification of Autonomous Controllers via Livingstone PathFinder

AI software is often used as a means for providing greater autonomy to automated systems, capable of coping with harsh and unpredictable environments. Due in part to the enormous space of possible situations that they aim to addrs, autonomous systems pose a serious challenge to traditional test-based verification approaches. Efficient verification approaches need to be perfected before these systems can reliably control critical applications. This publication describes Livingstone PathFinder (LPF), a verification tool for autonomous control software. LPF applies state space exploration algorithms to an instrumented testbed, consisting of the controller embedded in a simulated operating environment. Although LPF has focused on NASA s Livingstone model-based diagnosis system applications, the architecture is modular and adaptable to other systems. This article presents different facets of LPF and experimental results from applying the software to a Livingstone model of the main propulsion feed subsystem for a prototype space vehicle.

Lindsey, A. E.↗
NASA NTRS2020

Demonstrating Assurance of Model-Based Fault Diagnosis Systems on an Operational Mission

Developers of robotic scientific and commercial spacecraft are trending towards use of onboard autonomous capabilities for responding quickly to dynamic environments and rapidly changing situations. These capabilities need to know the state of the spacecraft’s health. Model-based fault diagnosis (MBFD) is an approach to estimating health by continuously verifying accurate behavior and diagnosing off-nominal behavior. Proper functioning of MBFD depends on 1) the quality of the diagnostic system model that is analyzed and compared to commands and onboard measurements to estimate a system’s health state, and 2) the correct functionality of the diagnosis engine interrogating the model and comparing its analyses to observed system behavior. Our goal is to develop Verification and Validation (V&V) techniques for MBFD to provide future missions sufficient confidence in its functionality and performance to deploy it on the systems they develop. Our work has been focused on infusing the techniques we developed earlier to an operational mission. First, we are constructing diagnostic models of a spacecraft attitude control system and updating our diagnostic engine so they can be demonstrated aboard the Arcsecond Space Telescope Enabling Research in Astrophysics (ASTERIA) mission, an operational spacecraft for which experiments in autonomy are being planned and executed, using the V&V techniques we have previously developed to assure they are both correct and complete. Since it is nearing the end of its life, ASTERIA provides a unique opportunity to demonstrate MBFD since the monitored components are expected to fail. Our demonstration will give system developers additional confidence to make timely, informed MBFD deployment decisions. Second, we will be completing performance assessments of the diagnostic engine/diagnostic model ensemble both on the flight system and ground-based testbeds to gain confidence in MBFD’s ability to run successfully in a spacecraft’s resource-constrained environment without adversely affecting other on-board activities. Finally, we are capturing our experience in preparing this demonstration in a set of checklists and guidance documents. Current practice includes high-level institutional guidance documents and standards, but at a high level of abstraction that does not necessarily address specific MBFD concerns. The purpose of the new checklists is to provide future mission developers clear, unambiguous, procedure-oriented guidance on assuring MBFD. This paper describes our work in these areas. For the first area, we describe the diagnostic models and updated diagnostic engine that will be used for the on-board demonstration. We describe how the V&V techniques we developed earlier are used to assure model and engine correctness and completeness. For the second area, we identify the performance measurement and assessment techniques used to characterize the diagnostic engine and diagnostic models, and discuss the effect of measured performance on overall mission operation. Finally, we present the checklist and guidance documents and describe how they meet the goals of providing system developers with clear, unambiguous, procedure-oriented guidance on MBFD assurance. We show how the techniques we have developed map into those artifacts.

Nikora, Allen↗
NASA NTRS2003

Active State Model for Autonomous Systems

The concept of the active state model (ASM) is an architecture for the development of advanced integrated fault-detection-and-isolation (FDI) systems for robotic land vehicles, pilotless aircraft, exploratory spacecraft, or other complex engineering systems that will be capable of autonomous operation. An FDI system based on the ASM concept would not only provide traditional diagnostic capabilities, but also integrate the FDI system under a unified framework and provide mechanism for sharing of information between FDI subsystems to fully assess the overall health of the system. The ASM concept begins with definitions borrowed from psychology, wherein a system is regarded as active when it possesses self-image, self-awareness, and an ability to make decisions itself, such that it is able to perform purposeful motions and other transitions with some degree of autonomy from the environment. For an engineering system, self-image would manifest itself as the ability to determine nominal values of sensor data by use of a mathematical model of itself, and selfawareness would manifest itself as the ability to relate sensor data to their nominal values. The ASM for such a system may start with the closed-loop control dynamics that describe the evolution of state variables. As soon as this model was supplemented with nominal values of sensor data, it would possess self-image. The ability to process the current sensor data and compare them with the nominal values would represent self-awareness. On the basis of self-image and self-awareness, the ASM provides the capability for self-identification, detection of abnormalities, and self-diagnosis.

Park, Han↗
NASA NTRS2019

Health Management and Prognostics for Electric Aircraft Powertrain

W and c Any air borne vehicle needs incorporating safety as key parameter of measure, and inclusion of autonomy raises the critical need for safety under autonomous operations. Management of faults and component degradation is key as complexity in autonomous operations grow over the period of time. Therefore, in addition to basic operational requirements, an autonomous electric vehicle should be able to make accurate estimates of its current system health and take the correct decisions to complete its mission successfully. Real-time safety and state-awareness tools are therefore essential for the vehicle to be able to reach its destination in a safe and successful manner. The need for safety assurance and health management capabilities is particularly relevant for aircraft electric propulsion systems, which are relatively new and with limited historical to learn. They are critical systems requiring high power density along with reliability, resilience, efficient management of weight, and operational costs. A model- based fault diagnosis and prognostics approach of complex critical systems can successfully accomplish the safety and state awareness goal for such electric propulsion systems, enabling autonomous decision making capability for safe and efficient operation. To identify critical components in the system a Qualitative Bayesian approach using FMECA is implemented. This requires the assessment of some quantities representing the state of the electric unmanned aerial systems (e-UAS), as well as look-ahead forecasts of such states during the entire flight, presented in form of safety metrics (SM). In-service data and performance data gathered from degraded components sup- ports diagnostic and prognostic methods for these systems, but this data can be difficult to obtain as weight and packaging restrictions reduce redundancy and instrumentation on-board the vehicle. Therefore, an model-based framework should be capable or operating with limited data. In addition to data scarcity, the variability of such complex critical systems re- quires the model-based framework to reason in the presence of uncertainty, such as sensor noise, and modeling imperfections. Quantification of errors and uncertainties in the measured states and quantities is therefore a fundamental step for a precise estimation of such SMs; un-modeled uncertainty may result in erroneous state assessment and un- reliable predictions of future states of e-UAVs. Typical, centralized model-based schemes suffer from inherent disadvantages such as computational complexity, single point of failure, and scalability issues, and therefore may fail in such a complex scenario. This paper presents a methodology for developing a system level diagnostics and prognostics approach using a Qualitative Bayesian FMECA approach along with a formal uncertainty management framework for an e-UAS. In this work we demonstrate the efficacy of the framework to predict effects of sub-system level degradation on vehicle operation incorporating uncertainty management to predict future behavior under different operating conditions.

Kulkarni, Chetan↗
NASA NTRSDate not supplied

Objective Structured Clinical Evaluation (OSCE) of an Artificial Intelligence (AI) Clinical Decision Support System (CDSS) Tool

BACKGROUND Objective Structured Clinical Evaluations (OSCEs) have long been established as a robust methodology for summative assessment of clinical skills and decision-making during medical education. The recent integration of Artificial Intelligence (AI) into clinical decision-making processes has prompted the need for novel evaluation frameworks to assess the efficacy and reliability of AI clinical decision support system (CDSS) tools. This abstract outlines the process of quantitatively evaluating a novel CDSS (“Doc in a Box” Google 2024) trained on curated medical spaceflight data in the psychomotor domain as it interfaces with a human volunteer acting as the crew medical officer (CMO). PURPOSE The AI CDSS under review was developed as part of the Lunar Command and Control Interoperability (LuCCI) project, which is intended to address a gap in how Lunar Surface Systems (LSS) would interoperate across multiple programs, commercial partners, and international partners. The project objective is to define, prototype, integrate, and evaluate an interoperable lunar command, control, data, and software reference architecture to enable autonomy and informatics capability through common standards across LSS. A multi-modal AI-based CDSS compatible with Federated LSS will assist clinicians in diagnosing and managing complex medical conditions by providing evidence-based recommendations through predictive analytics. Given the critical role of decision-support as NASA continues to evolve its Earth-independent medical operations (EIMO), it is imperative to ensure that such AI tools perform reliably and align with clinical standards during progressive lunar and Martian exploration class missions. METHODS The OSCE framework, traditionally used for evaluating human clinicians, was adapted to assess the AI tool's decision-making capabilities in simulated clinical scenarios. In this adapted OSCE, the AI CDSS was tested across a series of structured clinical scenarios designed to mimic real-life spaceflight patient cases. These scenarios included a range of conditions and complexities, allowing for comprehensive assessment of the tool's performance. Key evaluation metrics included accuracy of diagnosis, timeliness of decision-making, and appropriate recommendations for therapies. The OSCE was scored by human physician evaluators who assessed the AI's recommendations in comparison with expert clinicians' medical decision making to ensure alignment with best practices and the standard of care. RESULTS Preliminary results indicate that the AI CDSS demonstrated high accuracy in diagnostic recommendations and decision support across various scenarios. However, certain limitations were noted, such as occasional discrepancies in handling complex or nuanced cases that required a more contextual understanding. Additionally, the tool scored higher on the diagnostic portion of the rubric, with lower scores in the therapeutic recommendations. These findings highlight the importance of continuous refinement and validation of AI tools through rigorous evaluation frameworks like the OSCE. The adaptation of OSCEs for AI tools presents several advantages, including a structured and reproducible approach to evaluation, the ability to test AI systems in diverse clinical scenarios, and the opportunity to benchmark AI performance against established clinical standards to permit charting of future progress as aerospace medicine evolves as a discipline. Remaining challenges include ensuring that these evaluations capture the full spectrum of clinical decision-making scenarios that will be confronted by CMOs during missions and adequately reflecting real-world variability of the austere spaceflight environment. CONCLUSION Employing OSCEs to evaluate AI clinical decision support tools offers a promising approach to validating their clinical utility and efficacy. This methodology not only provides insights into the tool's performance but also fosters ongoing improvement and alignment with standard of care practices. Future research should focus on refining these evaluation processes and addressing limitations to enhance the integration of AI tools in clinical spaceflight settings. REFERENCES Scott S, Hearns V, Barker MA. Testing Clinical Skills: A Look at the OSCE and USMLE Clinical Skills Exams. S D Med. 2019 Oct;72(10):451-453. Majumder MAA, Kumar A, Krishnamurthy K, Ojeh N, Adams OP, Sa B. An evaluative study of objective structured clinical examination (OSCE): students and examiners perspectives. Adv Med Educ Pract. 2019 Jun 5;10:387-397. Karam VY, Park YS, Tekian A, Youssef N. Evaluating the validity evidence of an OSCE: results from a new medical school. BMC Med Educ. 2018 Dec 20;18(1):313.

Ariana M Nelson↗