Data Analytics for Safer Air Space

Queensland University of Technology

Researchers at Queensland University of Technology (QUT) in Australia used data analytics to create an algorithm that can predict the trajectory of an object faster and more accurately than existing approaches.

Imagine being able to predict an inexperienced pilot’s erratic flight path in real time.  “If it’s got a trajectory, we can predict it,” said Professor Clinton Fookes, who leads QUT’s Vision and Signal Processing research discipline in the Science and Engineering Faculty.

“In a Defence environment, this tool could help provide greater situational awareness of both owned and enemy assets and airspace.

“It could be applied to airspace, military bases, public transport or shopping centres – anywhere you want to analyze movement.”

The algorithm combines deep neural networks and memory networks to analyze and predict trajectories in real time. To ensure robustness, researchers trained the algorithm using disparate big data sets, including air traffic control data from Brisbane Airport, radar and camera data from pedestrian traffic at QUT and pedestrian trajectory databases from Edinburgh and New York.

Said QUT’s Simon Denman, “In civilian airspace, this algorithm could help manage drones, where we could see, potentially, an increasingly crowded and constrained airspace.” The researchers hope to extend the project in the future to investigate how the algorithm could optimize flight paths and travel routes. Read the report.