Summary
COntroller adaptive Digital Assistant
The CODA project involves developing a system in which hybrid human-machine teams collaboratively perform tasks. To do so, the system put together state of art from different fields: i) Prediction models to foresee future situations and have the system know which activities will be carried out by the operators and their impact on the same human performance; ii) Neurophysiological assessment of mental states to enable the system to know operators’ real current level of workload, attention, stress, fatigue, and vigilance by validating the predicted cognitive models and maximising the effectiveness of the interaction between the human and the machine by developing an HMPE (Human Machine Performance Envelope); iii) AI-based adaptable and explainable systems, to have the system act to prevent future performance or safety issues.
Specifically, the project will show how a system could adapt to specific situations and react accordingly by using advanced adaptable and adaptive automation principles that will dynamically guide the allocation of tasks. The system will assess the operator's cognitive status, use current traffic data to foresee the future tasks that the operator will need to perform in the future, and calculate the impact of those tasks in terms of cognitive complexity. With this information, the system will predict the future mental state of the operator and will act accordingly by developing an adaptive automation strategy. For example, imagine an ATCO managing a complex traffic situation and experiencing a medium workload. The system is aware of this (thanks to the neurophysiological assessment). It predicts that the additional upcoming tasks the ATCO will need to take care of will increase their workload, exceeding the maximum an operator can handle. To avoid this, the system decides how to act, following an adaptation strategy: it may, for instance, increment the level of automation, enable additional AI-based tools, or request a sector splitting.
The CODA project involves developing a system in which hybrid human-machine teams collaboratively perform tasks. To do so, the system put together state of art from different fields: i) Prediction models to foresee future situations and have the system know which activities will be carried out by the operators and their impact on the same human performance; ii) Neurophysiological assessment of mental states to enable the system to know operators’ real current level of workload, attention, stress, fatigue, and vigilance by validating the predicted cognitive models and maximising the effectiveness of the interaction between the human and the machine by developing an HMPE (Human Machine Performance Envelope); iii) AI-based adaptable and explainable systems, to have the system act to prevent future performance or safety issues.
Specifically, the project will show how a system could adapt to specific situations and react accordingly by using advanced adaptable and adaptive automation principles that will dynamically guide the allocation of tasks. The system will assess the operator's cognitive status, use current traffic data to foresee the future tasks that the operator will need to perform in the future, and calculate the impact of those tasks in terms of cognitive complexity. With this information, the system will predict the future mental state of the operator and will act accordingly by developing an adaptive automation strategy. For example, imagine an ATCO managing a complex traffic situation and experiencing a medium workload. The system is aware of this (thanks to the neurophysiological assessment). It predicts that the additional upcoming tasks the ATCO will need to take care of will increase their workload, exceeding the maximum an operator can handle. To avoid this, the system decides how to act, following an adaptation strategy: it may, for instance, increment the level of automation, enable additional AI-based tools, or request a sector splitting.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101114765 |
| Start date: | 01-09-2023 |
| End date: | 28-02-2026 |
| Total budget - Public funding: | 2 149 690,00 Euro - 1 929 486,00 Euro |
Cordis data
Original description
COntroller adaptive Digital AssistantThe CODA project involves developing a system in which hybrid human-machine teams collaboratively perform tasks. To do so, the system put together state of art from different fields: i) Prediction models to foresee future situations and have the system know which activities will be carried out by the operators and their impact on the same human performance; ii) Neurophysiological assessment of mental states to enable the system to know operators’ real current level of workload, attention, stress, fatigue, and vigilance by validating the predicted cognitive models and maximising the effectiveness of the interaction between the human and the machine by developing an HMPE (Human Machine Performance Envelope); iii) AI-based adaptable and explainable systems, to have the system act to prevent future performance or safety issues.
Specifically, the project will show how a system could adapt to specific situations and react accordingly by using advanced adaptable and adaptive automation principles that will dynamically guide the allocation of tasks. The system will assess the operator's cognitive status, use current traffic data to foresee the future tasks that the operator will need to perform in the future, and calculate the impact of those tasks in terms of cognitive complexity. With this information, the system will predict the future mental state of the operator and will act accordingly by developing an adaptive automation strategy. For example, imagine an ATCO managing a complex traffic situation and experiencing a medium workload. The system is aware of this (thanks to the neurophysiological assessment). It predicts that the additional upcoming tasks the ATCO will need to take care of will increase their workload, exceeding the maximum an operator can handle. To avoid this, the system decides how to act, following an adaptation strategy: it may, for instance, increment the level of automation, enable additional AI-based tools, or request a sector splitting.
Status
SIGNEDCall topic
HORIZON-SESAR-2022-DES-ER-01-WA2-1Update Date
31-07-2023
Images
No images available.
Geographical location(s)
Search
