A team working to restore capacity to people with spinal injuries have released a video of Robert “Buz” Chmielewski cutting a piece of cake and feeding it to himself. An everyday activity for most people becomes a world-changing breakthrough when considering Chmielewski has had almost no control over his limbs for 30 years, following a surfing accident as a teenager. Chmielewski collaborated with computer intelligence to operate the two robotic arms needed to achieve the feat.
For decades scientists have dreamed of bypassing neural damage and plugging electrodes directly into the brain, then passing the signals on so people can control either their own limbs, or artificial body parts. Unfortunately, it took hundreds of millions of years for our central nervous system to develop, and replicating it is not an easy challenge. Progress has been made, particularly where connections between limbs and brains have been only partially severed, but mostly one limb at a time.
"This type of research, known as brain-computer interface [BCI], has, for the most part, focused on only one arm, controlled from only one side of the brain," Professor Pablo Celnik of Johns Hopkins University said in a statement. That's fine for people who have an additional working limb, but only goes so far for people who can't move either and need to operate in a world built for the two-handed. However, operating two arms using implants at once is a much more complex challenge than using both in succession.
To address this, Celnik and colleagues arranged for Chmielewski's prosthetic arms to be partially controlled by artificial intelligence, leaving Chmielewski only having to do part of the job.
They've now released a video of man and machine in action.
"It's pretty cool," Chmielewski said in a statement. "I wanted to be able to do more of it."
Impressive though it is, the path to get to this point shows we're still a long way from making such capacities widespread. The electrodes Chmielewski used to send the messages were implanted almost two years ago in a 10-hour surgery. Although Chmielewski was able to control both prosthetic limbs simultaneously for simple movements within months, it's taken long slow practice and plenty of support from robotics engineers to extend his capacity to where he is now.
"Our ultimate goal is to make activities such as eating easy to accomplish, having the robot do one part of the work and leaving the user, in this case Buz, in charge of the details: which food to eat, where to cut, how big the cut piece should be," said Johns Hopkins' Dr David Handelman. "By combining brain-computer interface signals with robotics and artificial intelligence, we allow the human to focus on the parts of the task that matter most."
Currently, Chmielewski needs to be able to see what the arms are doing in order to control them, but the Johns Hopkins team hope to provide him with sensory feedback that gives him knowledge of where the limbs are without looking.
The video below compares Chmielewski's capacity after he first gained control of the limbs with his more recent movements.
