Possessing little artistic skills may no longer be an obstacle to creating great works of art, after scientists design a robot that can paint your ideas into reality.
Carnegie Mellon University has developed an artificially intelligent robotic arm that will paint on command once given an idea.
Similar to how ChatGPT generates text in a chosen style, users can direct the robot to paint a specific image, copy a photograph or work in another artist’s style.
The robot is called Frida – in honor of Frida Kahlo – which also stands for Framework and Robotics Initiative for Developing Arts.
“Frida is a robotic paint system, but Frida is not an artist,” said graduate student Peter Schaldenbrand, of the Robotics Institute at Carnegie Mellon, who helped develop the robot.
“It’s not generating ideas to communicate. It’s a system that an artist could collaborate with. The artist can specify high-level goals for Frida and then can execute them.
She added: “There’s this painting of a dancing frog that I think came out really well. It’s really silly and fun, and I think the surprise of what she’s generated based on my input has been really fun to see.
Frida was trained on massive datasets pairing text and images pulled from the internet, before AI systems crunch the data to generate a new image that she can then paint.
Once Frida has been given a concept to work with, the robot uses machine learning to create a simulation of the final painting, then develops a plan for how to make it using brushstrokes.
It also uses machine learning to gauge its progress as it works. From time to time, the robot uses an overhead camera to capture an image of the painting and refines its plan if necessary.
The team describe the final paintings as “impressionistic” and “whimsical” that intriguingly lack the precision expected of robots.
The researchers say they are struggling to improve Frida’s artistry and admit there is room for improvement in what she composes in simulation versus the final result on canvas.
However, even if the program does improve, the team doesn’t think the performers are in danger of being replaced by artificially intelligent robots.
“People wonder if Frida will accept artists’ works, but the main goal of the Frida project is just the opposite. We really want to foster human creativity through Frida,” said Dr. Jean Oh, research professor at the Robotics Institute.
“For example, I personally wanted to be an artist. Now I can actually collaborate with Frida to express my ideas in painting”.
Dr James McCann, assistant professor at the Robotics Institute, added: “Frida is a project that explores the intersection of human and robotic creativity.
“Frida is using the kind of AI models that have been developed to do things like caption images and understand the content of the scene and apply that to this generative art problem.”