Elon Musk is a firm believer that brain-computer interfaceswill be a big part of how we interact with computers in the future. But make no mistake: Mind-reading machines are here already.As science fiction writer William Gibson has noted, “The future is already here — it’s just not evenly distributed.”
Without further ado, then, here are eight examples of amazing mind-reading tech being explored in some of the world’s most exciting research labs.
Hearing aids are amazing inventions, but they run into problems in certain scenarios, such as crowded rooms where multiple people are speaking at the same time. One possible solution? Add in a dose of mind-reading.
That’s the broad idea behind a so-called “cognitive hearing aid” developed by researchers at the Columbia University School of Engineering and Applied Science. The device is designed to read brain activity to determine which voice a hearing aid user is most interested in listening to, and then focusing in on it. It’s still in the R&D phase, but this could be a game-changer for millions of deaf or hard of hearing people around the world.
“Working at the intersection of brain science and engineering, I saw a unique opportunity to combine the latest advances from both fields, to create a solution for decoding the attention of a listener to a specific speaker in a crowded scene which can be used to amplify that speaker relative to others,” Nima Mesgarani, an associate professor of electrical engineering, told Digital Trends.
Want an idea of what future interrogation scenarios might look like? Researchers at Japan’s Ochanomizu University have developed artificial intelligence that’s capable of analyzing a person’s fMRI brain scans and providing a written description of what they have been looking at.Accurate descriptions can extend to the complexity of “a dog is sitting on the floor in front of an open door” or “a group of people standing on the beach.”
Ichiro Kobayashi, one of the researchers on the project, said that there are no plans to use it as the basis for a supercharged lie detector just yet, at least. “So far, there are not any real-world applications for this,” he told Digital Trends. “However, in the future, this technology might be a quantitative basis of a brain-machine interface.”
Another project from neuroscientists at Canada’s University of Toronto Scarborough was able to recreate the faces of people that participants had previously seen.
Bionic prostheses have made enormous strides in recent years — and the concept of a mind-controlled robot limb is now very much a reality. In one example, engineers at Johns Hopkins built a successful prototype of such a robot arm that allows users to wiggle each prosthetic finger independently, using nothing but the power of the mind.
Perhaps even more impressively, earlier this year a team of researchers from Italy, Switzerland, and Germany developed a robot prosthesis which can actually feed sensory information back to a user’s brain — essentially restoring the person’s sense of touch in the process.
“We ‘translate’ information recorded by the artificial sensors in the [prosthesis’] hand into stimuli delivered to the nerves,” Silvestro Micera, a professor of Translational Neuroengineering at the Ecole Polytechnique Fdrale de Lausanne School of Engineering, told Digital Trends. “The information is then understood by the brain, which makes the patient feeling pressure at different fingers.”
For people with epilepsy, seizures can appear to come out of nowhere. Unchecked, they can be extremely dangerous, as well as traumatic for both the sufferer and those people around them. But mind-reading tech could help.
Researchers at the University of Melbourne and IBM Research Australia have developed a deep learning algorithm which analyzes the electrical activity of patients’ brains and greatly improves seizure prediction.
“Our hope is that this could inform the development of a wearable seizure warning system that is specific to an individual patient, and could alert them via text message or even a fitbit-style feedback loop,” Stefan Harrer, an IBM Research Australia staff member who worked on the recent study, told Digital Trends. “It could also one day be integrated with other systems to prevent or treat seizures at the point of alert.”
In not dissimilar work, researchers from Stanford University School of Medicine have developed mind-reading tech that could be used to moderate dangerously impulsive behavior.
Their system watches for a characteristic electrical activity pattern in the brain which occurs prior to impulsive actions, and then applies a quick jolt of targeted electricity. (No, it’s not as painful as that makes it sound!)
“This is the first example in a translatable setting that we could use a brain machine interface to sense a vulnerable moment in time and intervene with a therapeutic delivery of electrical stimulation,” Dr. Casey Halpern, assistant professor of neurosurgery, told Digital Trends. “This may be transformative for severely disabling impulse control disorders.”
Imagine if it was possible to navigate through a virtual reality world without having to worry about any handheld controller. That’s the idea behind a project by tech company Neurable and VR graphics company Estudiofuture. They’re busy developing the technology that will make brain-controlled virtual reality a… well, real reality.
Neurable’s custom headset monitors users’ brain activity using head-mounted electrodes to determine their intent. While there are limitations (it’s not ideal for typing or navigating menus), it could nonetheless be invaluable for making fields like VR gaming even more immersive than they already are.
When we control a vehicle, it’s important that our ability to manipulate its controls are as close as possible to our ability to perceive potential obstacles. In other words, we see something; we process it; our brain tells our hands to turn the wheel. Wouldn’t it be a whole lot easier if we just cut out the middleman?
That’s the concept behind neural interfaces which make it possible to steer drones (or even swarms of drones) using nothing more than our thoughts. Back in 2016, the University of Florida made headlines when it organized the world’s first ever brain-controlled drone race. Participants donned electroencephalogram headsets powered by brain-computer interface (BCI) technology, and then flew drones around a course using only their brainwaves.
While there’s still work to go, this could potentially be a useful method of rethinking the way in which future vehicles are piloted. Speaking of which…
So you’ve got a new possible means of controlling a vehicle using brainwaves, but it’s not quite ready for prime time just yet. What do you test it on? Driving a car, of course — with the passengers inside. At least, that was the basis for an intriguing (if terrifying) experiment carried out by carmaker Renault late last year.
The company recruited three willing participants and gave them the opportunity to work together to mentally pilot a modified Renault Kadjar SUV. One person controlled the car’s left turns, another controlled its right turns, and the third handled its acceleration.
No, this is unlikely to make it to our roads any time soon, but it’s certainly a memorable tech demo. Even if, quite frankly, we’d rather walk to pick up our groceries!