Technology 2 min read

Using Robomorphic Computing to Make Robots React Faster

Andy Kelly / Unsplash.com

Andy Kelly / Unsplash.com

A team of MIT researchers has devised a way to speed up a robot‘s operation using what they call robomorphic computing.

The motors in current robots are faster and more powerful thanks to advancements in technology. So, the machines should be able to move and react faster than ever before.

Unfortunately, that’s not always the case.

In complex operations, such as interaction with humans, robots are incapable of moving quickly. That’s because a boatload of computation goes into perceiving stimuli and calculating response.

As a result, new robots have a slower reaction time than their “body” is capable of achieving. And that could be a problem.

In a statement, a researcher at the Massachusetts Institute of Technology, Sabrina Neuman, said:

“For robots to be deployed into the field and safely operate in dynamic environments around humans, they need to be able to think and react very quickly,”

So, Neuman and other MIT researchers developed a hardware acceleration solution to address the issue. They called it robomorphic computing.

How Robomorphic Computing Increases Robot’s Response Time

Every robot has a unique physical layout designed to fit an intended application. Robomorphic computing considers such a layout to generate a customized computer chip to meet the machine’s needs.

It begins with the user inputting specific robot parameters — such as its limb layout and how the joints can move.

After that, Neuman’s system translates these physical properties into mathematical matrices. It then designs a hardware architecture that focuses entirely on the movable parts of the robot’s anatomy.

With that, the resulting chip can maximize efficiency for a specific robot’s computing needs.

In a test, the researchers noted that the chip created using robomorphic computing outperformed off-the-shelf CPU and GPU units.

Admittedly, the customized hardware architecture operated at a slower clock rate. However, it performed eight times faster and 86 times faster than the off-the-shelf CPU and GPU units, respectively.

Neuman noted:

“I was thrilled with those results. Even though we were hamstrung by the lower clock speed, we made up for it by just being more efficient.”

The advancement has several applications in robotics. These include frontline medical care of contagious patients, to name a few.

It would be fantastic if we could have robots that could help reduce the risk for patients and hospital workers,” says Neuman.

Read More: Robot Programming: A Guide to Programming Your Own Robots

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.


Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
You
1
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.