Home » Technology » Robotics » Watch: Humanoid Robot Ameca uses AI for drawing a Cat on a board like a Child

Watch: Humanoid Robot Ameca uses AI for drawing a Cat on a board like a Child

World’s most advanced humanoid robot called ‘Ameca’ now has learned to draw using its hands, after equipping generative AI technology.

Robots are expanding at a faster pace, striving to be indistinguishable from humans. And in the track, humanoid robots have been taking huge steps in recent years, with human-emotion imitation and now drawing capabilities. The recent leap of AI has played a major role here with these robots to unfold new parameters for the robots.

The firm that designs and manufactures this ‘Ameca’ – advanced humanoid robot, named “Engineered Arts”, has just made their robot to imagine drawings.

Ameca robot drawing a Cat

Ameca is one of the frontiers of robotic technology and innovation of the world, with GPT-powered brain and can imitate multiple face reactions too. Ameca is built on a software called ‘tritium’, refined over 12 years and is designed to be operatable remotely, can understand any coding language, and interacts good with people, as what it is made for.

Engineered Arts upgraded Ameca by tutoring them GPT-4 in April 2023 and currently an AI image generator platform gets tied into Ameca’s brain. Researchers of Engineered Arts have deployed Stable Diffusion, a text-to-image AI generator, in Ameca for the ability to imagine drawings.

To brief it about Stable Diffusion – It is a deep learning AI image generating model launched last year, primarily for creating detailed images from text description inputs.

Researchers of the firm wanted Ameca draw fast and make it entertaining to watch, which was their main focus. However, the real challenge was in converting images to vectors or lines (outlines), for easing the drawing, as likely for a child.

The firm had released a video showing Ameca drawing a cat, and in fact signing at the bottom corner, as an artist.



In the Video

Cat drawn by Ameca Robot

“I generate my drawing image through the open-source neural network project Stable Diffusion. From there, trajectories of the drawing are available, and then I skeletonize the image and vectorize it. After that, I plan and execute the trajectory to draw the image on my canvas,” explains Ameca, on being asked how do it generate these drawings.

Then the robot starts drawing a cat and at the same time speaks about cats and their interaction with humans. Ameca even seems confident about her work, says “If you don’t like my art, you probably just don’t understand art.”

Watch the full video here.

(For more such interesting informational, technology and innovation stuffs, keep reading The Inner Detail).

Scroll to Top