A new AI robotic arm was created to paint compelling artwork and is now coming to the forefront as a revolutionary entity. FRIDA (Framework and Robotics Initiative for Developing Arts) is a robotic arm created at Carnegie Mellon University’s School of Computer Science and is the newest addition to the university’s art world.
The AI arm is named after iconic Mexican painter Frida Kahlo, and can collaborate with humans to create works of art, Aaron Aupperlee, Senior Director of Media Relations, said in a letter shared with Gizmodo.
FRIDA’s creation was conducted by Peter Schaldenbrand, a Ph.D. student at the School of Computer Science alongside faculty members Jean Oh and Jim McCann.
Aupperlee shared FRIDA’s works of art with Gizmodo along with photos of FRIDA’s paintings.
Click through to see FRIDA’s artistic process.
FRIDA makes brush strokes to begin a painting
FRIDA takes about an hour to learn how to use the paintbrush and specific brush strokes before creating the art — which is done by humans sending a text description or by the user uploading a photo to inspire its style. Schaldenbrand and the FRIDA team are also testing music as a directive, such as ABBA’s song, Dancing Queen.
Although FRIDA’s artwork is impressive, Schaldenbrand cautioned in a press release sent to Gizmodo, “FRIDA is a robotic painting system, but FRIDA is not an artist.”
“FRIDA is not generating 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.”
Two mixing trays are held in front of the colour palette suggested by FRIDA
When FRIDA has established working the paintbrush and has received its directives for the type of painting style, it will create a colour palette for a human to mix.
A method for automatic paint mixing is in the development stages by Jiaying Wei, a master’s student in the School of Architecture with faculty member Eunsu Kang.
FRIDA creates a painting
FRIDA will take hours to complete just one painting, and will occasionally use an overhead camera that captures an image of the painting to evaluate how it is doing and if it needs to alter its plan.
Oh said in the press release: “People wonder if FRIDA is going to take artists’ jobs, but the main goal of the FRIDA project is quite the opposite. We want to really promote human creativity through FRIDA. For instance, I personally wanted to be an artist. Now, I can actually collaborate with FRIDA to express my ideas in painting.”
A collection of FRIDA’s paintings
FRIDA has completed dozens of paintings, all based on the text, visual, or audio instructions it receives.
Schaldenbrand: “There’s this one painting of a frog ballerina that I think turned out really nicely. It is really silly and fun, and I think the surprise of what FRIDA generated based on my input was really fun to see.”
Collaborators (Left to Right): Peter Schaldenbrand, Jean Oh, and Jim McCann
All of FRIDA’s work is available to view on a CMU-run Twitter account, FRIDA Robot Painter.
McCann told TechCrunch: “FRIDA is a project exploring 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 scene content and applying it to this artistic generative problem.”