Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI safety”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2022

TruePAL – An AI Assistant for First Responder Safety

This paper presents the development of an AI assistant, Trusted and Explainable Artificial Intelligence for Saving Lives (TruePAL), to provide real-time warning of risks of potential crashes to the first responders. The TruePAL system employs an AI and deep learning technology for saving first responders and roadside crews lives in and around active traffic. A deep neural network (DNN) and a Non-Axiomatic Reasoning System (NARS) are implemented as an AI system. A mobile app with AI interface is developed to perform verbal communication with the first responders. The TruePAL team has developed an explainable AI approach by opening up the DNN blackbox to extract the activation filters of various features and parts of the targeted objects. The combination of DNN and NARS makes the TruePAL system explainable to the users. TruePAL ingests on-board cameras, radar, and other sensor signals, analyzes the environment and traffic patterns to generate timely warning to drivers and roadside crews to avoid crashes. The TruePAL team, in collaboration with the Miami/Dade Police Dept., has designed five use cases and multiple sub-scenarios in a CARLA driving simulator to test the capability of TruePAL in timely warning to the first responder drivers in potential crash scenarios. We have successfully demonstrated its capability of timely warning in over a dozen scenarios based on the use cases. The preliminary test simulation results show that TruePAL could provide the drivers and crew members advanced warning before a crash occurs.

Chow, Edward↗
NASA NTRS2023

An MBSE Approach for Developing an Autonomous Rover Platform

The proliferation of increasingly autonomous systems calls for new ways to address how safety is assured. As these systems become more advanced and complex, it becomes more important to model and prototype autonomous functions at the systems level and the functions that assure they are operating safely and as expected. To that effect, researchers at the National Aeronautics and Space Administration (NASA) 's Robust Software Engineering (RSE) group are working on prototyping a Research Autonomous Vehicle, commonly referred to as R-RAV. The R-RAV is an autonomous rover platform designed to act as a case study for assured autonomy research. Moreover, an overarching goal is for the R-RAV to serve as a training ground for other mission projects. In this paper, we will detail how we have used a Model-Based Systems Engineering (MBSE) approach to model a prototype of the R-RAV and test and verify its different functionalities.

MBSE↗
NASA NTRS2019

Artificial Intelligence in Aviation Safety Applications - Exploring Myths and Truths of AI and ML

Artificial Intelligence (AI) and machine learning (ML) are gaining increased attention as ways to leverage the world's data to solve problems. Although AI and ML offer much potential, there are often misconceptions about the application of such techniques.Panel speakers will present machine learning approaches they have developed on a variety of aviation data, including digital flight data, safety reporting data, and voice communications data. They will discuss the purpose of the application, the data used, and the lessons learned in the development and deployment of their solutions. The panel will also discuss common pitfalls in developing an AI solution, the dangers of the current hype around AI, tips for gaining value from a ML solution, how to determine whether a ML approach is appropriate for a problem, and more.

Reeves, Scott (Capt.)↗
NASA NTRS2024

Transfer-AE: A novel autoencoder-based impact detection model for structural digital twin

Accurately detecting the location and intensity of impacts is crucial for ensuring structural safety. Currently, AI-based structural impact detection methods are widely used for their excellent detection accuracy. However, their generalization capability is limited by the scenarios present in the training data. Many complex and dangerous impact scenarios are difficult to conduct real-world experiments on to collect sufficient samples. To capture all impact scenarios and fully leverage the advantages of AI-based detection technologies, advanced methods involve combining real-world structural monitoring data with corresponding numerical models to construct digital twins. These methods continuously refine the created numerical models with limited real-world data and provide diverse impact scenarios through numerical model simulations. However, there are inevitable differences between digital models and physical models that are challenging to correct through mechanical means. This discrepancy in data distribution between the two models significantly hinders the application of digital twin technology in impact/event identification tasks. To address this challenge, this study proposes a novel model based on autoencoders, named Transfer-AE. Transfer-AE encodes the common features of digital twins in the latent space to bridge the uncertainty gap at a macro scale between numerical models and physical models and synchronously fits the magnitude and location of the impact load in the decoder. This enables consistent detection results for the same impact event, whether the sample comes from the numerical model or the physical model. Transfer-AE includes two operating modes: Mode 1 has a fixed computational complexity with stable inference speed, but the training cost and difficulty increase with data distribution. Mode 2's computational complexity increases with data distribution, but it has a fixed training cost and speed. In both cases involving the geodesic dome structure simulating a deep space habitat and the IASC-ASCE benchmark structure, Transfer-AE demonstrated the best performance in impact localization and quantification tasks compared to mainstream domain-adaptive transfer models.

Chengjia Han↗
NASA NTRSDate not supplied

Artificial Neural Networks and AI in high Assurance Applications: Gaps and Techniques

In recent years, capabilties of Deep Neural Networks (DNN) and Artificial Intelligence (AI) systems have grown tremendously. They are now applied in many areas ranging from game playing, social media, science, to robotics, automotive, and aerospace applications.Based upon requirements for safety of DNN and AI in high assurance automotive and aerospace applications, I will discuss the necessity to ensure that AI technqiues for the analysis of Earth observation data and reasoning are working correctly and reliably.In this talk I will present modern techniques for the verification and validation (V&V) of DNN and other AI components as well as approaches for interpretable AI. I will discuss how these techniques can help to ensure quality of the AI results, improve confidence in their application, and facilitate human-AI interaction and collaboration.

Johann Schumann↗
NASA NTRSDate not supplied

Architecting Safer Autonomous Aviation Systems

The aviation literature gives relatively little guidance to practitioners about the specifics of architecting systems for safety, particularly the impact of architecture on allocating safety requirements, or the relative ease of system assurance resulting from system or subsystem level architectural choices. As an exemplar, this paper considers common architectural patterns used within traditional aviation systems and explores their safety and safety assurance implications when applied in the context of integrating artificial intelligence (AI) and machine learning (ML) based functionality. Considering safety as an architectural property, we discuss both the allocation of safety requirements and the architectural trade-offs involved early in the design lifecycle. This approach could be extended to other assured properties, similar to safety, such as security. We conclude with a discussion of the safety considerations that emerge in the context of candidate architectural patterns that have been proposed in the recent literature for enabling autonomy capabilities by integrating AI and ML. A recommendation is made for the generation of a property-driven architectural pattern catalogue.

Architecture patterns↗
NASA NTRSDate not supplied

Architecting Safer Autonomous Aviation Systems

The aviation literature gives relatively little guidance to practitioners about the specifics of architecting systems for safety, particularly the impact of architecture on allocating safety requirements, or the relative ease of system assurance resulting from system or subsystem level architectural choices. As an exemplar, this paper considers common architectural patterns used within traditional aviation systems and explores their safety and safety assurance implications when applied in the context of integrating artificial intelligence (AI) and machine learning (ML) based functionality. Considering safety as an architectural property, we discuss both the allocation of safety requirements and the architectural trade-offs involved early in the design lifecycle. This approach could be extended to other assured properties, similar to safety, such as security. We conclude with a discussion of the safety considerations that emerge in the context of candidate architectural patterns that have been proposed in the recent literature for enabling autonomy capabilities by integrating AI and ML. A recommendation is made for the generation of a property-driven architectural pattern catalogue.

Architecture patterns↗
NASA NTRS1986

Artificial intelligence for Space Station automation: Crew safety, productivity, autonomy, augmented capability

Artificial intelligence (AI) R&D projects for the successful and efficient operation of the Space Station are described. The book explores the most advanced AI-based technologies, reviews the results of concept design studies to determine required AI capabilities, details demonstrations that would indicate the existence of these capabilities, and develops an R&D plan leading to such demonstrations. Particular attention is given to teleoperation and robotics, sensors, expert systems, computers, planning, and man-machine interface.

Firschein, O.↗
NASA NTRSDate not supplied

Approach and Guiding Principles for Developing AI/ML Components and their Standards

The objective of the AI Roadmap meeting is to engage with all stakeholders in aviation in an open conversation about our approach and the guiding principles that can help us in moving forward in the technological landscape of AI/ML. The objective of the Technical Exchange Meeting is to identify categories of safety concerns associated with having an AI component in the aircraft we identified in the previous Technical Exchange Meeting on January 24, 2024. This presentation is to spur the discussion regarding the use of AI/ML in civil aviation and stimulate active participation with all stakeholders.

AI/ML↗
NASA NTRSDate not supplied

AI/ML Components in Safety-Critical Aviation Systems: Selected Concepts and Underlying Principles

The objective of the AI Roadmap meeting is to engage with all stakeholders in aviation in an open conversation about our approach and the guiding principles that can help us in moving forward in the technological landscape of AI/ML. The objective of the Technical Exchange Meeting is to identify categories of safety concerns associated with having an AI component in the aircraft we identified in the previous Technical Exchange Meetings. The speakers will bring their experience to the discussion to stimulate active participation with all stakeholders.

Design Safety↗
NASA NTRSDate not supplied

Data-Centric Operational Design Domain Characterization for Machine Learning-Based Aeronautical Products

We give for Machine Learning (ML)-based aeronautical products, a first rigorous characterization of Operational Design Domains (ODDs). Unlike in other application sectors (such as self-driving road vehicles) where ODD development is scenario-based, our approach is data-centric: we propose the dimensions along which the parameters that define an ODD can be explicitly captured, using a top-down approach starting from system specifications, and a bottom-up approach starting from detailed ML Model (MLM) designs. Then we give a categorization of the data that ML-based applications can encounter in operation, identifying their system-level relevance and impact. Specifically, we discuss how those data categories are useful to determine: (1) the requirements necessary to drive the design of MLMs; (2) the potential effects on the MLM and higher levels of the system hierarchy; (3) the learning assurance processes that may be needed, and (4) system architectural considerations. We illustrate the underlying concepts with an example of an aircraft flight envelope. The approach in this paper is one of the cornerstones of a future process guidance for development and certification/approval of safety-related aeronautical products implementing Artificial Intelligence (AI), currently being developed through aviation industry-based consensus, jointly by the SAE G-34 Committee for AI in aviation, and EUROCAE WG-114 for AI.

Aeronautical products↗
NASA NTRS2022

Space Applications of a Trusted AI Framework: Experiences and Lessons Learned

Artificial intelligence (AI), which encompasses machine learning (ML), has become a critical technology due to its well-established success in a wide array of applications. However, the proper application of AI remains a central topic of discussion in many safety-critical fields. This has limited its success in autonomous systems due to the difficulty of ensuring AI algorithms will perform as desired and that users will understand and trust how they operate. In response, there is growing demand for trustability in AI to address both the expectations and concerns regarding its use. The Aerospace Corporation (Aerospace) developed a Framework for Trusted AI (henceforth referred to as the framework) to encourage best practices for the implementation, assessment, and control of AI-based applications. It is generally applicable, being based on terms and definitions that cut across AI domains, and thus is a starting point for practitioners to tailor to their particular application. To help demonstrate how the framework can be tailored into mission assurance guidance for the space domain, Aerospace sought the involvement of the Jet Propulsion Laboratory (JPL) to engage with actual examples of AI-based space autonomy.

Kaufman, James↗
NASA NTRSDate not supplied

A Systems Approach to AI Model Integration and Performance Evaluation for the Generic UAM Simulation Framework

This paper introduces py-guam, an open-source experimentation framework developed for the NASA Generic Urban Air Mobility simulation (GUAM) environment, facilitating the integration and evaluation of advanced artificial intelligence (AI) algorithms. We present a systems approach which enables the seamless incorporation of data-driven models, including off-nominal and failure state detection, into the GUAM’s Cognitive Architecture (CA). The framework supports customizable experimentation parameters, derives Safety Performance Indicators (SPIs) from UL 4600 safety case analyses, and employs rapid UAM simulations to assess AI impacts on flight performance across diverse scenarios. Through comprehensive testing and validation experiments, we demonstrate GUAM’s capability to enhance safety and efficiency in urban air mobility operations. Additionally, the open-source nature of py-guam fosters community collaboration, ensuring continuous improvement and adaptability to evolving technological advancements. This work establishes a robust tool for developing and testing AI-driven urban air mobility (UAM) systems, advancing the safety and reliability of autonomous urban air vehicles.

Artificial Intelligence↗
NASA NTRSDate not supplied

System and Safety Analysis with SysAI A Statistical Learning Framework

This is a tutorial on how to use the SYSAI (System Analysis using Statistical AI), a flexible statistical learning framework for the V&V and analysis of complex and high-dimensional Aerospace systems with DNN and AI components. SYSAI provides functionality for a variety of analyses and V&V tasks, including statistical data analysis, high dimensional safety-envelope and time-series analysis, property checking, as well as intelligent test-case generation. The tutorial will demonstrate SYSAI with our industrial partner’s Autonomous Centerline Tracking system, which uses a DNN to enable autonomous aircraft taxiing as an example. Video & Tutorial

Statistical V&V for Complex safety-critical system↗
NASA NTRS1985

NASA space station automation: AI-based technology review

Research and Development projects in automation for the Space Station are discussed. Artificial Intelligence (AI) based automation technologies are planned to enhance crew safety through reduced need for EVA, increase crew productivity through the reduction of routine operations, increase space station autonomy, and augment space station capability through the use of teleoperation and robotics. AI technology will also be developed for the servicing of satellites at the Space Station, system monitoring and diagnosis, space manufacturing, and the assembly of large space structures.

Firschein, O.↗
NASA NTRSDate not supplied

Smart Crop Farming Systems for Artemis Exploration Missions

Space crop production systems that mitigate risks of crew poor performance or illness due to inadequate food and nutrition are needed during manned Artemis exploration missions beyond LEO. Prototype farms must be designed for deployment on ISS and tested in manned platforms: Gateway, lunar habitats, and Mars trans-hab spacecraft in preparation for human missions to Mars. Food production must be optimal and safe for human consumption. Thus, plant growth facilities (i.e. Veggie and APH) can be enhanced with imaging systems (including hyperspectral, multispectral, lidar, and fluorescence imaging systems) for nondestructive monitoring of plant health, stress and assessing food safety. Databases of crop responses to stress obtained during ground studies can be used to develop novel artificial intelligence (AI) algorithms for optimizing crop production (i.e. environmental settings during growth) and for detecting crop indices that ensure food safety. Future farming systems should be sustainable and smart. Novel adaptive AI algorithms requiring limited data sets for calibration are needed for reducing crew intervention during plant cultivation except for maintenance and harvesting events. Eventually, AI driven control systems that include autonomous planting, growing, and harvesting as well as periodic sanitization need evaluation for supplementing crew diets with fresh produce during future Mars exploration missions.

O Monje↗
NASA NTRSDate not supplied

Runtime Monitoring for Unmanned Aerospace Systems with Neural Network Components

AI components (e.g., Deep Neural Networks) are increasingly used in unmanned Aerospace systems for safety-relevant applications. Rigorous Verification and Validation methods for such components are still in their infancy and thus, monitoring of the AI's behavior during runtime is essential. In this paper, we will present a runtime-monitoring architecture, which combines the advanced statistical analysis framework SYSAI (System Analysis using Statistical AI) with temporal and probabilistic runtime monitoring carried out by R2U2 (Realizable, Responsive, and Unobtrusive Unit). Learned statistical models of complex systems with AI components are produced by the SYSAI framework and provide detailed information to enable the R2U2 runtime monitor to efficiently perform advanced safety and performance checks in nominal and off-nominal conditions. We will present initial results of our tool set and architecture on a case study, a DNN-based autonomous centerline tracking system (ACT).

Yuning He↗