A new artificial intelligence technology created at Mälardalens University (MDU) in Sweden is promising to help air traffic controllers by calculating delay lengths and predicting various interruptions. This system, in addition to predicting disruptions and communicating necessary updates to customers, can even help prevent disruptions from occurring.
The AI system prototype was developed by researchers at MDU and is aimed at helping operators in air traffic management (ATM) to handle airspaces and aircraft more efficiently. It will do so through helping operators create and maintain optimized traffic flows while monitoring aircraft positions. Additionally, the system has the ability to identify potential collisions and provide the needed guidance to avoid such accidents. While it does provide efficient solutions, this system also supplies explanations for why its suggestions are optimal for the conditions.
In addition to monitoring and analyzing traffic in real time, this system is also predictive. The system developed three machine learning algorithms, allowing it to provide transparency and thus delay predictions on single runways. It is built in an environment using XAI (Explainable Artificial Intelligence) and utilizes both 2D and 3D maps to visualize a wide range of possible solutions before identifying the best one. It supplies pilots with information needed for them to keep safe distance between their aircraft and other air traffic—while providing guidance to air traffic control as well.
This system was developed as a part of the Artimation project at MDU, and was shaped using input from human end-users. This will allow it to improve existing infrastructure within the industry. As Mobyen Uddin Ahmed, Professor of Artificial Intelligence at MDU, explained, “The project results will improve the functionality, acceptance and the reliability of AI systems in general, but also meet global goals such as the improvement of industry, innovation and infrastructure in society.”
While this new AI system has taken promising steps toward improving the aviation industry, the project can also help advance AI research and application across a variety of industries. “The results from the project will also be useful for other AI researchers, who can take advantage of the research when it comes to the transparency and explainability of AI methods,” explained Shahina Begum, Professor of Artificial Intelligence at MDU. “In addition, technology providers will benefit from the results, which will hopefully lead to AI systems that will become more communicative and reliable for human users.”
As the skies grow more crowded, efficient and safe air traffic management will be critical to accommodate such an important and growing industry. The work done at Mälardalens University through its Artimation project promises to help air traffic controllers and aircraft operators fly in a safer and more efficient manner.
The post New AI Sytem Offers Potential Air Traffic Management Solutions appeared first on Avionics International.