Controlling a robotic arm with your brain

Mind = Blown.

When it comes to brain-controlled interfaces, advancements in the space have come a long way since its earliest days of research at UCLA in the 1970s. Under a grant from the National Science Foundation and followed by a contract from DARPA, the papers published following the study marked the first appearance of the expression BCI in scientific literature. Now fast forward nearly 40 years and Makers are inspiring a wide-range of possibilities, from EEG beanies that can read and change colors based on a wearer’s mood to amputees instructing a prosthesis to gain movement in their arms.

(Source: MAKE)

(Source: MAKE)

Writing for MAKE: Magazine, Nathan Hurst highlights a recent project from Cognitive Technology for their recent Make it Move interactive display in San Francisco. The device was simply plugged into a computer and screen, and into a two-jointed robotic arm.

To bring the exhibit to life, the team adapted an EEG board from OpenBCI. The ATmega328 based platform measures brain activity in both hemispheres, and records that data on eight channels. However, for it to work, it requires electrodes to be pasted onto the skull — something which wouldn’t work for a public exhibit. Subsequently, the Makers decided to use a soft neoprene cap with dry electrodes that was capable of sitting on the head with a velcro strap under the chin. It would then read and output brainwaves to the OpenBCI board.


“I think if this technology advances more, it will help a lot of disabled people who can’t move their arms,” Jisoo Kim tells MAKE. “Since everything is open-source, people can build it themselves, so I think it will advance a lot more.”

Maker Tomas Vega, who is a University of California student and Cog Tech member, shares that an EEG device can read that in the form of electrical signals on the scalp. Those signals are then processed, filtered and analyzed into more digestible form of feedback. Software interprets the information from the EEG and assists in processing the signals to create useful output. However, these signals can come in rather noisy, and as a result, the program must employ some machine learning to sort it out.

(Source: MAKE)

(Source: MAKE)

As MAKE points out, EEG interpretation faces a bit of skepticism from the academic community, and in the current exhibit’s setting, the team was faced with an additional barrier of teaching visitors to actually control the interface. While brain-controlled interfaces have been used primarily for science, the Cog Tech crew hopes that new tools will help spur further research and more importantly, address more practical problems including assisting those who are paralyzed.

For the exhibit, Cog Tech is harnessing the powers of BCI to command a robotic arm that Jon Ferran devised using an Arduino Mega (ATmega2560) along with some parts from an old bartending arm. At the moment, motion is limited to waving left and right.

Kim explains to MAKE that after just a few hours of training, she could already feel herself getting better with controlling the arm — something that the team hopes others will one day have the chance to experience. “It was pretty difficult. The most difficult part was to think the way that can control the arm; imagining moving my left or right arm is different from moving it.”

(Source: MAKE)

(Source: MAKE)

While BCI boasts several possible applications in basic computer control, such as replacing mice and keyboards, some have a more personal goal as well. “I want to be a cyborg. That’s my long-term goal,” Vega concludes. “I’m going to work all my life to make this a reality. There’s nothing that makes my heart beat faster than this dream of being enhanced by technology. This dream of being augmented, and augmenting my capabilities as a human, and trying to push the boundary.”

Interested in learning more? You can read the entire feature in MAKE: Magazine here. 

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s