A robot developed by MIT students Ben Katz and Jared Di Carlo can solve a Rubik’s Cube in a record-breaking 0.38 seconds-Mary Beth O’Leary
Few toys have captured the public’s imagination quite like the Rubik’s Cube. Rubik’s Cube references have been made in all corners of popular culture — from “The Simpsons” to “Being John Malkovich.” For the better part of four decades, this small handheld object has tormented those who tried to solve it.
Over the years, competitions have been held to see who could solve the Rubik’s Cube the fastest by hand. Engineers then started building robots programmed to solve the cube at a lightning speeds. In 2016, a robot broke the world record and solved the cube in 0.637 seconds. Mechanical engineering graduate student Ben Katz and third-year electrical engineering and computer science major Jared Di Carlo thought they could do better.
“We watched the videos of the previous robots, and we noticed that the motors were not the fastest that could be used,” recalls Di Carlo. “We thought we could do better with improved motors and controls.”
The pair met through the MIT Electronics Research Society, MITERS, a student-run hackerspace. Throughout January’s Independent Activities Period, they set out to build a robot that could shatter the world record for solving a Rubik’s Cube.
“The gist is that there is a motor actuating each face of a Rubik’s Cube,” explains Katz, who conducts research at MIT’s Biomimetic Robotics Lab. Custom-built electronics and controls are then used to control each of those motors. The robot also has the pair of webcams pointed at the cube. “When we tell the robot to solve the cube, we use those webcams to identify the different colours on the face of the cube,” says Katz.
Di Carlo wrote software that identifies the colours of each individual part within the cube to determine the cube’s initial state. The team then used existing software written to instruct the robot on exactly how to move the pieces to solve the puzzle.
The result? They set a new world record. It only took their robot 0.38 seconds to solve the Rubik’s Cube. The team credits the unique skills they brought to the table as the key to their success. “I worked on the computer vision software, while Ben worked on the more mechanical stuff,” adds Di Carlo.