AI-Powered Robotic ‘Picassnake’ Paints Images Based On Music

With over 15 years of writing experience, Jonathan has had a passion for all things tech-related since watching Inspector Gadget as a child. He's disassembled countless appliances and managed to put a few back together, and one actually still works. When not writing, he can often be found playing video games or accidentally hurting himself tinkering in the garage.

Researchers at the University of Manitoba’s Human-Computer Interactions (HCI) Lab have developed Picassnake. This robotic snake analyzes music and paints pieces of art based on the music’s unique characteristics. Is that how Picasso painted? I don’t think so, but they had to name it something, and I guess Van Goghsnake didn’t have the same ring. Matissnake isn’t bad, either.

Picassnake is a robotic arm covered with a stuffed animal snakeskin and can process music through a microphone or MP3 file. Once it “listens” to the music, it generates a set of unique strokes from the sound and then transforms those digital strokes into actual physical ones on paper.

To generate unique strokes, Picassnake does frequency analysis of the music. After taking some time to think, Picassnake decides the color of a stroke based on the loudness of the highest frequency range (14k-22k). The start point of a stroke is the end point of last stroke. Picassnake decides the end point of the stroke by calculating a distance and angle from the start point based on spectrum of the music,” said the team.

That’s certainly an interesting use of technology, and I’m curious what my favorite songs would look like in robot-painted art form. Do metal songs produce dark and angsty paintings? Do classical songs create flowing, calming paintings? From what I could gather from watching, it looks like it’s pretty much up in the air. This is a painting robotic snake we’re talking about, after all.

[IEEE via TechEBlog]