Meet 'Milo', a mind-controlled, McGill-created automated wheelchair

Students develop wheelchair powered by imagination Milo, created by 35 McGill students, is a wheelchair controlled using the mind. Electrodes are measured via sensors, and the chair responds.

Some students at McGill University are taking the idea of “mind over matter” to a whole new level: they’ve developed a wheelchair that moves using your imagination.

Thirty five McGill students came together on their own time and designed “Milo” in just 30 days.

“Milo is a brain-controlled wheelchair that relies on imagined movement to turn. So when you imagine turning your right hand you can turn right and when you imagine turning your left hand you can turn left,” explained Danielle Nadin, who worked on data collection.

“First, we have to attach all the electrodes to the persons head. That gets the EEG signal off their scalp. Then there's a BCI board connected by Bluetooth to the computer where it's running the software that interprets this data,” explained Simon Tartakovsky, who was responsible, in part, for Milo’s hardware.

That information is then sent to a micro-controller that controls the wheels.

The user only needs to worry about big decisions like turning, and blinking prompts the wheelchair to start or stop.

The chair even has assisted driving features to keep things simple.

“If there's a wall the wheelchair will try to follow the wall and if there's an obstacle it'll stop right before the obstacle and that removes a lot of the burden on the user,” explained team leader Marley Xiong.

It took students from many academic backgrounds to – literally - get the wheels in motion.

"If you're in a technical field you don't always get access to the more human side of things and if you're in a more research human centred field, you don't always know about the technology,” Nadin added. “So it's nice to bring it together.”

They repaired and custom wired a broken chair.

Then they used an inexpensive EEG – or electroencephalogram - a non-invasive way to take a bio-signal from the scalp.

That signal renders an image that helps to visualize when you're thinking of doing something, even if you don't actually do it.

The team also collected data from 15 participants.

“All this data needs to be good in order to be able to predict on any given user whether they're doing left or right,” Xiong said.

It isn't the first brain-controlled wheelchair. But at $500, the team at McGill says it's the cheapest and simplest to use.

Even Google has expressed interest.

“At the end to be able to see the product of our work actually working it was super satisfying,” Nadin added.