Human hands let us solve a wide variety of tasks. For the past 60 years of robotics, hard tasks which humans accomplish with their fixed pair of hands have required designing a custom robot for each task⁠(opens in a new window). As an alternative, people have spent many decades trying to use general-purpose robotic hardware⁠(opens in a new window), but with limited success due to their high degrees of freedom. In particular, the hardware we use here is not new—the robot hand we use has been around for the last 15 years—but the software approach is.

Since May 2017, we’ve been trying to train a human-like robotic hand to solve the Rubik’s Cube⁠(opens in a new window). We set this goal because we believe that successfully training such a robotic hand to do complex manipulation tasks lays the foundation for general-purpose robots. We solved the Rubik’s Cube in simulation in July 2017. But as of July 2018, we could only manipulate a block⁠ on the robot. Now, we’ve reached our initial goal.

A full solve of the Rubik’s Cube. This video plays at real-time and was not edited in any way.

Solving a Rubik’s Cube one-handed is a challenging task even for humans, and it takes children several years to gain the dexterity required to master it. Our robot still hasn’t perfected its technique⁠ though, as it solves the Rubik’s Cube 60% of the time (and only 20% of the time for a maximally difficult⁠(opens in a new window) scramble).

We train neural networks to solve the Rubik’s Cube in simulation⁠(opens in a new window) using reinforcement learning and Kociemba’s algorithm⁠(opens in a new window) for picking the solution steps.A Domain⁠(opens in a new window) randomization⁠(opens in a new window) enables networks trained solely in simulation to transfer to a real robot.