<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
Increasing airspace demand requires an increase in effectiveness and efficiency of the ATC system. Automation, and specifically Machine Learning (ML), may present good prospects for increasing system performance and decreasing workload of ATCOs. AI, however, is typically a “black box” making it hard to include in a socio-technical environment. This exploratory research aims to increase operator trust and acceptance and move towards a more “cooperative” approach to automation in ATC. It focuses on building upon previous efforts by using two different approaches: Strategically Conformal AI and Explainable AI methods to AI-Human interactions. Strategic Conformance aims to increase acceptance by producing individual-sensitive advisories. Explainable AI focuses on producing more optimal solutions and providing a clear explanation for these solutions. In this article, we propose the use of a single visual representation for tactical conflict detection and resolution, called the Solution Space Diagram (SSD), to serve as a common ground for both explainable and conformal AI. Through this research, it has become clear that there needs to be a careful definition given both to optimality and conformance. Likewise, the training of the AI agents comes with requirements for a large amount of data to be available and displaying these solutions in a human-interpretable way, while maintaining optimality, has its own unique challenges to overcome.
...
Increasing airspace demand requires an increase in effectiveness and efficiency of the ATC system. Automation, and specifically Machine Learning (ML), may present good prospects for increasing system performance and decreasing workload of ATCOs. AI, however, is typically a “black box” making it hard to include in a socio-technical environment. This exploratory research aims to increase operator trust and acceptance and move towards a more “cooperative” approach to automation in ATC. It focuses on building upon previous efforts by using two different approaches: Strategically Conformal AI and Explainable AI methods to AI-Human interactions. Strategic Conformance aims to increase acceptance by producing individual-sensitive advisories. Explainable AI focuses on producing more optimal solutions and providing a clear explanation for these solutions. In this article, we propose the use of a single visual representation for tactical conflict detection and resolution, called the Solution Space Diagram (SSD), to serve as a common ground for both explainable and conformal AI. Through this research, it has become clear that there needs to be a careful definition given both to optimality and conformance. Likewise, the training of the AI agents comes with requirements for a large amount of data to be available and displaying these solutions in a human-interpretable way, while maintaining optimality, has its own unique challenges to overcome.
In order to satisfy future air travel demands, there is a need for a more automated and modernized air traffic control. Automation is expected to advance from its current principal utilization as software tools to become an autonomous agent cooperating with the air traffic controller. To facilitate interchangeable, functional and sustainable human-automation collaboration, there is a need to develop better interaction and visualization techniques. Ultimately, automation might be rejected because of the system’s opacity (what is it doing and why?) or mismatch in underlying strategy (I would solve this problem differently). Human-machine cooperation is believed to benefit from automation sensitive and adaptive to individual preferences in problem solving. Furthermore, increased transparency afforded by a decision-aid in regards to its reasoning and problem solving, can positively influence user attitudes including acceptance and trust. In a recent study we hypothesized that both these factors (strategic conformance and interface representation transparency), would influence task performance and willingness to use an automated decision aid in a conflict detection and resolution task. Nine controller trainees participated in two real-time simulations in which they were tasked with directing traffic and maintaining separation in short en-route traffic scenarios. Results showed that controllers perceived and used the two interface representations differently. Even though controllers accepted conformal solutions more often than nonconformal, with a degree similar to what has been observed in previous studies, the effect of strategic conformance was not significant. These findings are discussed in relation to the challenges in diffusion and acceptance of decision-aiding automation.
...
In order to satisfy future air travel demands, there is a need for a more automated and modernized air traffic control. Automation is expected to advance from its current principal utilization as software tools to become an autonomous agent cooperating with the air traffic controller. To facilitate interchangeable, functional and sustainable human-automation collaboration, there is a need to develop better interaction and visualization techniques. Ultimately, automation might be rejected because of the system’s opacity (what is it doing and why?) or mismatch in underlying strategy (I would solve this problem differently). Human-machine cooperation is believed to benefit from automation sensitive and adaptive to individual preferences in problem solving. Furthermore, increased transparency afforded by a decision-aid in regards to its reasoning and problem solving, can positively influence user attitudes including acceptance and trust. In a recent study we hypothesized that both these factors (strategic conformance and interface representation transparency), would influence task performance and willingness to use an automated decision aid in a conflict detection and resolution task. Nine controller trainees participated in two real-time simulations in which they were tasked with directing traffic and maintaining separation in short en-route traffic scenarios. Results showed that controllers perceived and used the two interface representations differently. Even though controllers accepted conformal solutions more often than nonconformal, with a degree similar to what has been observed in previous studies, the effect of strategic conformance was not significant. These findings are discussed in relation to the challenges in diffusion and acceptance of decision-aiding automation.
