Robots have once again shown their superiority to humans, this time by solving a Rubik's Cube in less than half a second. The new build, created by software developer Jared Di Carlo and MIT Biometrics Lab Master’s student Ben Katz, can solve a 3X3 square Rubik’s Cube in just .38 seconds.
Humans have steadily increased their Rubik’s cube solving speed over the past few decades but have been no match for robotic competition. The current human world record holder, SeungBeom Cho, solved the cube in a by-comparison slothlike 4.59 seconds.
Prior to Katz and Di Carlo’s build, another robot made by Infineon Technologies called Sub1 Reloaded was able to complete the task in just .63 seconds.
Katz and Di Carlo’s build uses six ServoDisc U-9 series motors, six motor drivers, two Playstation Eye webcams, and a Rubik’s Cube.
“One counterintuitive trick for getting things to work well was to make the cube really tight,” Katz wrote in a blog post. “When the cube is loose (like it would be if a person were trying to solve it fast), the outer faces just cam outwards when you try to turn the center faces quickly.”
In the post, Katz said that their machine is not even being pushed to its full potential.
“The machine can definitely go faster, but the turning process is really time consuming since debugging needs to be done with the high speed camera, and mistakes often break the cube of blow up FETs [Field-Effect Transistors],” Katz wrote.
“We used the cheapest cube we could find on Amazon Prime because we thought we’d end up destroying many of them, but somehow ended up only going through four cubes [and] hundreds of solves,” Di Carlo wrote in his own blog post.
According to Di Carlo, the team implemented a two-phase algorithm called min2phase to get the robot to detect the colors. The robot uses a Playstation 3 Eye Webcam to visually detect the cube’s colors and anticipate solutions before it makes a move. Di Carlo wrote that the entire color detection process takes just 45 milliseconds with most of that time being used up waiting for the webcam driver. The two released their software on GitHub.