Abstract
Lack of trust has been identified as an obstacle in the introduction of workload-alleviating automation in air traffic control. The work presented in this paper describes a concept to generate individual-sensitive resolution advisories for air traffic conflicts, with the aim of increasing acceptance by adapting advisories to different controller strategies. These personalized advisories are achieved using a tailored convolutional neural network model that is trained on individual controller data. In this study, a human-in-the-loop experiment was performed to generate datasets of conflict geometries and controller resolutions, with a velocity obstacle representation as a learning feature. Results show that the trained models can reasonably predict command type, direction and magnitude. Furthermore, a correlation is found between controller consistency and achieved prediction performance. A comparison between individual-sensitive and general models showed a benefit of individually trained models, confirming the strategy heterogeneity of the population, which is a critical assumption for personalized automation.
Original language | English |
---|---|
Title of host publication | Proceedings of the 13th USA/Europe Air Traffic Management Research and Development Seminar 2019, ATM 2019 |
Subtitle of host publication | 17/06/19 - 21/06/19 Vienna, Austria |
Number of pages | 10 |
Publication status | Published - 2019 |
Event | 13th USA/Europe Air Traffic Management Research and Development Seminar 2019, ATM 2019 - Vienna, Austria Duration: 17 Jun 2019 → 21 Jun 2019 |
Conference
Conference | 13th USA/Europe Air Traffic Management Research and Development Seminar 2019, ATM 2019 |
---|---|
Country/Territory | Austria |
City | Vienna |
Period | 17/06/19 → 21/06/19 |
Keywords
- Consistency
- Decision-support
- Machine learning
- Solution space diagram
- Strategic conformance
- Velocity obstacles