Aircraft could be equipped with an onboard AI system to help with midair stalls and sharp altitude drops, researchers have said.

A team from KTH Royal Institute of Technology in Sweden has conducted tests on an AI system designed to enhance the effectiveness of experimental technologies for manipulating airflow on wing surfaces.

An AI technique known as deep reinforcement learning (DRL) allows the programme to use previous experiences to guide the way it controls the airflow technologies in real time.

The AI control system zeroes in on one particularly dangerous aerodynamic phenomenon known as flow detachment, or turbulent separation bubbles. To stay aloft, aircraft need slow-moving air underneath the wing, and fast-moving air above it. The air moving over the wing surface needs to follow the wing shape, or ‘attach’, to the surface.

According to Ricardo Vinuesa, a fluid dynamics expert at KTH, when the air moving over the wing’s surface no longer follows the wing shape and instead breaks...