Carnegie Mellon researchers working with peers from the University of Minnesota have made a big breakthrough in brain-computer interface (BCI) and robotic technology: They’ve developed a way for a person to control a robot arm with their minds — with no surgery or invasive procedures required to make it possible.
The mind-controlled robot in this experiment also showed a high degree of motor control, as it’s able to track a computer cursor as it moves across a screen. This is obviously a huge step forward in the field, as it proves the viability of controlling computers with your brain more generally, which could have all kinds of potential applications, not least of which are providing people with paralysis or other kinds of disorders that affect movement an alternative way to operate computerized devices.
To date, successful, highly precise demonstrations and executions of BCI tech in people has depended on systems that incorporate brain implants, which pick up the signals from inside the user. Implanting these devices is not only dangerous, but also expensive and not necessarily fully understood in terms of their long-term impact. This has led to them not being very widely used, which means only a few people have been able to benefit from their impact.
The CMU and University of Minnesota research team’s breakthrough is to develop a system that can deal with the lower signal quality that comes from using sensors that are used outside of the body, applied to the skin instead. They were able to employ a combination of new sensing and machine learning technologies to grab signals from the user that are from deep within the brain, but without the kind of “noise” that typically comes with noninvasive techniques.
This groundbreaking discovery might not even be that far away from changing the lives of actual patients — the research team intends to start clinical trials soon.