Articles
Wired up: An EEG cap acquires signals from the pilot’s brain
Engineers in Portugal have demonstrated for the first time in public a system that allows a pilot to control an unmanned drone with his mind.
The Brain-Machine Interface (BMI) shown by Portuguese aerospace firm Tekever allows the pilot to control an unmanned aerial vehicle (UAV) with just the electrical signals generated by the brain.
Ricardo Mendes, chief operating officer of Tekever, said the technology could one day allow people with physical disabilities to pilot aircraft, or free-up a pilot’s cognitive functions to focus on the most important tasks. “The whole cockpit would have to be redesigned, it’s a completely new paradigm,” he said.
The interface has three main elements. Signal acquisition is achieved using an off-the-shelf electroencephalography (EEG) cap normally used in the medical sector. It detects slight changes in the voltage between electrodes in contact with the head.
This reading is sent to the second part of the system, the decoder, a computer system running software written by the researchers. This converts the reading into an instruction and sends it to the device, in this case a UAV.
The final part of the BMI is the feedback, which through visual, audio or haptic cues allows the user to adjust their brain activity.
Rui Costa, principal investigator at the Champalimaud Foundation, a biomedical research organisation and partner in the project, said the traditional approach to using EEG as a control system is to take a snapshot of a subject’s EEG when performing an action and then configure the interface to detect that action. This has proved largely unsuccessful because different people produce different EEG readings for the same action.
He said: “Our approach is different. Our decoder is fixed and uses the signal from the brain to create feedback and slowly the user learns how to control. It’s similar to the way babies learn to control their limbs through feedback.”
The demonstration in Lisbon follows a demonstration of the BMI to control a simulator last June at the Technical University of Munich. The system has been researched for 10 years at institutions and companies in Germany, Holland and Portugal.
Mendes said: “The main challenge is moving out from the simulated environment into a real environment. This is an actual plane, there is wind and rain. There is a lot of variables out there that are not present in a simulated environment. This is the first time this has been done, not only testing it for real, but showing it to the world in a live session.”