Results for “Trusted autonomy” — Page 3

NASA NTRSDate not supplied

Bootstrapping Multi-Agent Unmanned Aerial Vehicle (UAV) System Integration Using Ground-Based Assets: Lessons Learned

The highly dynamic nature of UAVs imposes significant challenges when conducting initial testing ranging from safety risks posed by high-capacity lithium batteries and spinning propellers to rigorous timing demands on controllers and the consequences of failures mid-air. Flight testing of a single vehicle is time and labor intensive due to these challenges and more, and the complexity increases exponentially with the number of vehicles. While simulations and hardware-in-the-loop bench testing can provide adequate environments for preliminary validation, differences in system deployment architecture, software interfaces, and hardware infrastructure between simulation and a fleet of real UAVs create a sizable gap that must be navigated carefully during system integration. In support of the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project, which had the goal of establishing a basis of certification of trust and trustworthiness in multi-agent autonomous systems, this gap was tackled from two directions. First, a novel mixed-reality simulation environment was engineered to blur the transition from simulation to flight hardware. Second, a fleet of Unmanned Surface Vehicles (USVs) was developed as a test and evaluation platform that more closely represented the final aerial fleet while eliminating many of the risks associated with air vehicles. This paper delves into the second element, analyzing the efficacy of the USV platform in performing system integration testing for the UAV system. In this paper we present the USV fleet and its role in reducing the aforementioned gaps in deployment architecture, software interfaces, and hardware infrastructure when moving from simulation to flight. An overview of the hardware and software onboard the vehicles will be provided along with supporting infrastructure. The system integration process will be documented including results in supporting both the overarching design reference mission (DRM) of ATTRACTOR and individual research efforts conducted during the project. Finally, we will discuss some of the practical lessons learned regarding the testing, deployment, and operation of multi-agent autonomous systems.

Matthew P Vaughan↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight methods is paramount for establishing an effective architecture for autonomous systems. A fundamental objective of the ATTRACTOR (Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability) project was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation environment for test and evaluation of autonomous systems. The Autonomous Entity Operations Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single- and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. Together AEON and BEAM enable sim-to-flight with minimal configuration changes. By using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the lab and in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗

NASA NTRSDate not supplied

Bootstrapping Multi-Agent Unmanned Aerial Vehicle (UAV) System Integration Using Ground-Based Assets: Lessons Learned

In support of the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project, a fleet of unmanned ground vehicles (UGVs) was developed as a test and evaluation (T\&E) platform to reduce system integration gaps between simulation and live flight hardware. While simulation and hardware-in-the-loop bench testing provide adequate environments for preliminary validation, differences in system deployment architecture, software interfaces, and hardware infrastructure increase the risks to safety, property, and the project. Given ATTRACTOR’s goal of establishing a basis of certification of trust and trustworthiness in multi-agent autonomous systems, bridging these gaps was critical to successful project execution and feasibility assessment. In this paper we present the UGV fleet and its role in speeding up system integration, smoothing the transition from simulation to flight, and providing researchers an easy-to-use hardware test bed. An overview of the hardware and software on-board the vehicles is provided along with supporting infrastructure. The system integration process is documented including results in supporting both the overarching design reference mission (DRM) of ATTRACTOR and individual research efforts conducted since the creation of the fleet. Finally, we discuss the practical lessons learned regarding the testing, deployment, and operation of multi-agent autonomous systems.

Matthew P. Vaughan↗

NASA NTRSDate not supplied

A Distributed Simulation-to-Flight Framework to Support Investigating Trust/Trustworthiness in Multi-Agent Systems

As autonomous systems continue to grow both in use and complexity, the necessity for robust and extensible simulation-to-flight methods is paramount for establishing an effective architecture for autonomous systems. A fundamental objective of the ATTRACTOR (Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability) project was to design and develop a distributed mixed-reality simulation environment to begin establishing a basis for certification of autonomous systems via research into trust and trustworthiness. In this paper, we present an autonomous systems architecture and development framework paired with a persistent distributed modeling and simulation environment for test and evaluation of autonomous systems. The Autonomous Entity Operations Network (AEON) framework enables autonomous system development with an easily extensible collection of libraries and plug-n-play nodes facilitated by the Data Distribution Service (DDS) communication protocol standard. The Baseline Environment for Autonomous Modeling (BEAM) simulation environment is a distributed mixed-reality Unity™-based environment built around the same DDS communication paradigm allowing for easy integration with AEON-based autonomous applications. They were designed under ATTRACTOR in order to measure and establish trustworthiness and trust in single- and multi-agent human-machine systems whether these machines are fixed-wing general aviation, rotary-wing Unmanned Aerial Vehicles (UAVs), ground rovers, or even spacecraft. Together AEON and BEAM enable sim-to-flight with minimal configuration changes. By using AEON and BEAM, source code that runs in simulation ports directly to hardware and has successfully flown in the lab and in the National Airspace System (NAS) at NASA LaRC many times over the lifetime of ATTRACTOR.

Benjamin N Kelley↗

NASA NTRSDate not supplied

Human Autonomy Teaming - m:N Operations

The principles and reasons for employing Human Autonomy Teaming is discussed. Application of these techniques to multi-vehicle control is described. In several operational environments from small drone delivery to air taxi to autonomous cargo, many companies will need technologies that will allow for the operation of an unmanned aircraft (UAS or eVTOL) by a small crew of individuals that are located in a remote network operations center. That is, Multiple operators supervising an increasing Number of vehicles (M:N). This will require a new control/supervisory paradigm where the supervisors team with automation to achieve their joint tasks; Human Autonomy Teaming (HAT). This task will follow the HAT philosophy and tenants (e.g., trust, bi-directional communication, pilot directed interfaces). It will also develop and employ specific HAT tools (e.g., playbook, working agreements, predictive timeline displays, transparent interfaces to build trust).

multi-vehicle control↗

NASA NTRSDate not supplied

Exploring Multimodal Interactions in Human-Autonomy Teaming Using a Natural User Interface

The creation of a multimodal, natural user interface to facilitate multi-agent interaction is essential to establishing trust among human and machine teammates in multi-agent systems. Trust is being researched, along with trustworthiness, as a path to certification of autonomous systems by the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project at NASA. The Autonomous Mission Experimental Logistics Interactive Assistant (AMELIA) is a natural user interface that enables multimodal interaction and is designed for rapid mission planning. AMELIA is an intelligent system that considers the user’s preferred communication strategies, as well as the time-critical aspect of the multi-agent system decision-making process. Twenty-four participants planned a multi-agent search and rescue mission, with the aid of an intelligent assistant. The results show that while the combined use of touch and speech was faster than speech alone, the single modality, touch, was still the most efficient. Future research should investigate additional input technologies.

Lisa R Le Vie↗

NASA NTRSDate not supplied

Exploring Multimodal Interactions in Human-Autonomy Teaming Using a Natural User Interface

The creation of a multimodal, natural user interface to facilitate multi-agent interaction is essential to establishing trust among human and machine teammates in multi-agent systems. Trust is being researched, along with trustworthiness, as a path to certification of autonomous systems by the Autonomy Teaming and TRAjectories for Complex Trusted Operational Reliability (ATTRACTOR) project at NASA. The Autonomous Mission Experimental Logistics Interactive Assistant (AMELIA) is a natural user interface that enables multimodal interaction and is designed for rapid mission planning. AMELIA is an intelligent system that considers the user’s preferred communication strategies, as well as the time-critical aspect of the multi-agent system decision-making process. Twenty-four participants planned a multi-agent search and rescue mission, with the aid of an intelligent assistant. The results show that while the combined use of touch and speech was faster than speech alone, the single modality, touch, was still the most efficient. Future research should investigate additional input technologies.

Lisa Renee Le Vie↗

NASA NTRS2021

Trust in Collaborative Automation in High Stakes Software Engineering Work

The amount of autonomy in software engineering tools is increasing as developers build increasingly complex systems. Research in other domains shows that too much or too little trust in autonomous tools can have negative consequences, but we are not aware of any study that has investigated trust in autonomous tools in the highly interactive context of a software engineering workplace. We present the results of a ten week ethnographic case study of engineers collaborating with autonomous tools to write flight software at a large national space exploration organization to support high stakes missions. We find that trust in an autonomous software engineering tool in this setting was influenced by four main factors: the tool’s transparency, social context, an organization’s associated processes, and its usability. We outline theoretical implications for future research into trust in autonomous software engineering tools, and practical implications for tool designers and organizations conducting high stakes work with autonomous tools.

Davidoff, Scott↗

NASA NTRSDate not supplied

NASA HAT Lab Activities

The principles and reasons for employing Human Autonomy Teaming is discussed. Application of these techniques to multi-vehicle control is described. In several operational environments from small drone delivery to air taxi to autonomous cargo, many companies will need technologies that will allow for the operation of an unmanned aircraft (UAS or eVTOL) by a small crew of individuals that are located in a remote network operations center. That is, Multiple operators supervising an increasing Number of vehicles (M:N). This will require a new control/supervisory paradigm where the supervisors team with automation to achieve their joint tasks; Human Autonomy Teaming (HAT). This task will follow the HAT philosophy and tenants (e.g., trust, bi-directional communication, pilot directed interfaces). It will also develop and employ specific HAT tools (e.g., playbook, working agreements, predictive timeline displays, transparent interfaces to build trust).

multi-vehicle control↗

NASA NTRS2018

Operator Trust Function for Predicted Drone Arrival

To realize the full benefit from autonomy, systems will have to react to unknown events and uncertain dynamic environments. The resulting number of behaviors is essentially infinite; thus, the system is effectively non-deterministic but an operator needs to understand and trust the actions of the autonomous vehicles. This research began to tackle non-deterministic systems and trust by beginning to develop a user trust function based on intent information displayed and the prescribed bounds on allowable behaviors/actions of the non-deterministic system. Linear regression shows promise on being able to predict a person’s confidence of the machine’s prediction. Linear regression techniques indicated that subject characteristics, scenario difficulty, the experience with the system, and confidence earlier in the scenario account for approximately 60% of the variation in confidence ratings. This paper details the specifics of the liner regression model – essentially a trust function – for predicting a person’s confidence.

Trujillo, Anna C.↗

NASA NTRSDate not supplied

m:N Operations and Future

The principles and reasons for employing Human Autonomy Teaming is discussed. Application of these techniques to multi-vehicle control is described. In several operational environments from small drone delivery to air taxi to autonomous cargo, many companies will need technologies that will allow for the operation of an unmanned aircraft (UAS or eVTOL) by a small crew of individuals that are located in a remote network operations center. That is, Multiple operators supervising an increasing Number of vehicles (M:N).This will require a new control/supervisory paradigm where the supervisors team with automation to achieve their joint tasks; Human Autonomy Teaming (HAT).This task will follow the HAT philosophy and tenants (e.g., trust, bi-directional communication, pilot directed interfaces). It will also develop and employ specific HAT tools (e.g., playbook, working agreements, predictive timeline displays, transparent interfaces to build trust). This presentation discusses the barriers and requirements for future m:N operations.

multi-vehicle control↗

NASA NTRSDate not supplied

On the Moral Hazard of Autonomy

This paper describes the concept of moral hazard as applied to technologies that incorporate automation and autonomy. Moral hazard is said to exist when a party to a transaction feels more comfortable taking undue risks because another party will bear the costs if things go badly. As opposed to regular physical hazards, a moral hazard comes from within a person. In this paper, we reveal two categories of moral hazards related to autonomy. The first category of moral hazard occurs when the owner of the autonomy introduces an autonomous system without accepting the full responsibility for improper operation thereby shifting the risks from one party to another party. This category of moral hazard is similar to moral hazards experienced in other industries and can often be addressed through appropriate policy and establishing liability for irresponsible behavior. The issue becomes more complicated in cases where the operator of the autonomy may not have a full understanding of the system behavior. In the second category of moral hazard, risks are shifted from people to autonomy. In this category, the humans in proximity to the autonomous system begin to trust its behavior. Their behavior may change in that they may believe they are more insulated from harm and subsequently exhibit more risky behavior towards increasingly autonomous technologies. Mitigating this type of moral hazard may require the autonomy to possess certain design features to discourage this type of harmful human behavior so that humans do not suffer needlessly in their interactions with autonomous systems by placing inappropriate trust where that trust is neither warranted nor deserved.

Cybernetics↗

NASA NTRSDate not supplied

Future Operations

The principles and reasons for employing Human Autonomy Teaming is discussed. Application of these techniques to multi-vehicle control is described. In several operational environments from small drone delivery to air taxi to autonomous cargo, many companies will need technologies that will allow for the operation of an unmanned aircraft (UAS or eVTOL) by a small crew of individuals that are located in a remote network operations center. That is, Multiple operators supervising an increasing Number of vehicles (M:N). This will require a new control/supervisory paradigm where the supervisors team with automation to achieve their joint tasks; Human Autonomy Teaming (HAT). This task will follow the HAT philosophy and tenants (e.g., trust, bi-directional communication, pilot directed interfaces). It will also develop and employ specific HAT tools (e.g., playbook, working agreements, predictive timeline displays, transparent interfaces to build trust). This presentation discusses the future of GCS control stations and need for Human Systems Integration.

multi-vehicle control↗

NASA NTRSDate not supplied

m:N Working Group

The principles and reasons for employing Human Autonomy Teaming is discussed. Application of these techniques to multi-vehicle control is described. In several operational environments from small drone delivery to air taxi to autonomous cargo, many companies will need technologies that will allow for the operation of an unmanned aircraft (UAS or eVTOL) by a small crew of individuals that are located in a remote network operations center. That is, Multiple operators supervising an increasing Number of vehicles (M:N). This will require a new control/supervisory paradigm where the supervisors team with automation to achieve their joint tasks; Human Autonomy Teaming (HAT). This task will follow the HAT philosophy and tenants (e.g., trust, bi-directional communication, pilot directed interfaces). It will also develop and employ specific HAT tools (e.g., playbook, working agreements, predictive timeline displays, transparent interfaces to build trust). This presentation discusses the background and progress of the m:N working group.

multi-vehicle control↗

NASA NTRSDate not supplied

Space ROS TOFU: Flying Space ROS with Containerized Hybrid Trust

Space ROS is a distribution of Robot Operating System 2 (ROS2) targeting the specific requirements of flight software and spaceborne robotics while maintaining the flexibility that has made ROS indispensible for robotics research and industrial system integration. With Space ROS, a project can leverage the existing ROS2 ecosystem to reduce redundant development while tackling increasingly complex demands for on-device intelligence; however, there is no substitute for flight heritage to combat the risk-aversion common to spaceflight projects, and Space ROS has yet to fly. To break the collective-action standoff and gain valuable flight experience, the Distributed Spacecraft Autonomy (DSA) team at NASA Ames Research Center developed Opportunistic Software Experiments for Spacecraft Autonomy Testbeds (OSE-SAT) architecture, utilizing containerization to execute lower-trust software under traditionally verified heritage flight software for demonstration on-orbit. OSE-SAT leverages a hybrid-trust model where flexible, complex components like Space ROS can run without risk to the host spacecraft while providing validated feedback to a highly scrutinized, trusted core. We leverage this testbed to demonstrate Space ROS in flight, building heritage, and experience for projects with "Trust On First Use" (TOFU) requirements for flight heritage. We present a Space ROS component for OSE-SAT, lessons learned integrating Space ROS into a flight software stack, and the results of the first known use of Space ROS in orbit.

small satellites↗

NASA NTRSDate not supplied

Human Factors Research Needs for In-Time Aviation Safety Management Systems (IASMS) Design: Enabling the NASA “Sky for All” Future Airspace Vision

Integrated safety management will be paramount for safely enabling the envisioned transformations of the future National Airspace System. Addressing the increasing need for advanced data analytics and fusion of aviation safety data, managed by human decision-makers, is essential for realizing the vision. The proposal, if accepted, will discuss safety management system challenges and how the concept of In-time Aviation Safety Management Systems addresses the need. It will also discuss human factors challenges involved in future integrated safety management, including trust, over-reliance, human-optimized data visualization, human-autonomy teaming, training, communication and dissemination of data, situation awareness, task load, and accountability.

Lawrence J Prinzel III↗

NASA NTRSDate not supplied

Human Capabilities Assessments for Autonomous Missions: A Multi-Team Research Effort to Reduce Risk in the Human-System Integration Architecture for Future Deep-Space Missions

In future exploration missions beyond low earth-orbit, crew will have to execute complex operations and respond to off-nominal events, without real-time support from Mission Control. It is anticipated that increased reliance on automated systems, including human-centric vehicle and information architecture, will need to be designed to support the crew; increased risk to performance, health, and safety may occur if these are not implemented appropriately. The Human Factors and Behavioral Performance Element (HFBP) in the NASA Human Research Program supports research to characterize and mitigate such human health and performance risks, including the Risk of Adverse Outcome Due to Inadequate Human Systems Integration Architecture (HSIA). The HSIA risk addresses the integration of onboard capability and the crew roles and responsibilities necessary to enable the crew to respond effectively and efficiently in the increasingly autonomous mission operations environment. In 2017, HFBP released the “Human Capabilities Assessments for Autonomous Missions” (HCAAM) research topic to address HSIA related questions. HCAAM is a major NASA research effort that has assembled a multidisciplinary team from seven institutions to work closely with design and engineering efforts on research towards developing and refining human performance standards, guidelines and automation tools. The scientific focus is on quantitative assessment of human capabilities relevant to future deep-space missions during which earth/spacecraft communication is so delayed and intermittent that the crew must be able to function autonomously. The integrated strategy of the HCAAM project characterizes human capabilities and limitations related to potential performance decrements during long duration exploration mission spaceflight as relevant to both routine and complex task performance; defines system characteristics that reduce the likelihood or impact of potential decrements in human performance capabilities; performs integrated assessment of intelligent system responses within the context of an operational environment with relevant NASA tools, systems, and data structures in order to determine positive or negative interactions and validate recommended approaches; and proposes specific updates to existing standards and guidelines for inclusion in NASA handbooks for the design of future spacecraft intelligent systems that provide crew performance assessment/feedback, and to also serve as decision-support aids for the onboard crew (i.e., NASA-STD-3001, and NASA/SP-Human Integration Design Handbook (HIDH)). The scientific research vectors being addressed by the seven HCAAM teams include: - crew task performance (accuracy, efficiency) (crew + automation) - crew performance (accuracy, efficiency) - crew Situation Awareness - procedure design and multi-modal enhancement - concurrent tasking (mixed manual + some level of autonomy) - task handover - crew self-planning and time-lining - task design - trust in automation, real-time calibration - human multi-sensory feedback and guidance - human trust in on-board software-based intelligent assistants - virtual assistants The presentation will highlight plans and progress made in each of these research areas as well as the methods by which surrogate astronaut crews in the NASA JSC HERA spaceflight analog facility will function as human test subjects for all of the HCAAM research projects.

HCAAM VNSCOR↗

NASA NTRS2016

Workshop on Assurance for Autonomous Systems for Aviation

This report describes the workshop on Assurance for Autonomous Systems for Aviation that was held in January 2016 in conjunction with the SciTech 2016 conference held in San Diego, CA. The workshop explored issues related to assurance for autonomous systems and also the idea of trust in these systems. Specifically, we focused on discussing current practices for assurance of autonomy, identifying barriers specific to autonomy as related to assurance as well as operational scenarios demonstrating the need to address the barriers. Furthermore, attention was given to identifying verification techniques that may be applicable to autonomy, as well as discussing new research directions needed to address barriers, thereby involving potential shifts in current practices.

assurance↗