Meet Frida, the AI-powered robot that makes works of art

Researchers at Carnegie Mellon University’s Robotics Institute in Pittsburgh have developed a robotic arm with a paintbrush that, powered by artificial intelligence, can help human artists create works of art.

This robot was called FRIDA, which clearly owes its name to Frida Kahlo, but its acronym really means “Framework and Robotics Initiative for Developing Arts”.

According to a report published on the Europa Press website, users can direct FRIDA by entering a text description, submitting other artworks to inspire their style, or uploading a photo and asking it to paint a representation of it.

The experts are also experimenting with other inputs such as audio. They put on ABBA’s “Dancing Queen” and asked FRIDA to paint it.

What do the scientists think?

Peter Schaldenbrand, a doctoral student who is part of the team that has developed the robot to explore the limits of Artificial Intelligence and creativity, said: “FRIDA is a robotic painting system, but it is not an artist.”

“FRIDA does not generate the ideas to communicate. FRIDA is a system that an artist could collaborate with. The artist can specify high-level goals for FRIDA and then FRIDA can execute them,” she added.

How does it work? Once the human FRIDA user has specified a high-level concept of the box they want to create, the robot uses machine learning to create its simulation and develop a plan to make a box that meets the user’s goals.

FRIDA displays a color palette on a computer screen for a human to mix and provide to the robot. The robot uses AI models similar to tools like OpenAI’s ChatGPT and DALL-E 2, which generate text or an image, respectively, in response to the prompt.

As a result, her paintings are impressive but lack precision, and if she makes a mistake, FRIDA touches it up with a smudge of paint.