There’s always been something so annoying about people who found the need to stack additional challenges onto solving a Rubik’s Cube quickly, whether it was doing it blindfolded or while juggling or one-handed. While it might have just been a challenge for them, it also seemed like a need to show off.
OpenAI is clearly interested in showing off what its Dactyl robotic-hand can do with a Rubik’s Cube.
The organization announced that the robot has learned to solve a Rubik’s Cube one-handed, an accomplishment that speaks to the robot’s dexterity in handling and manipulating the cube more than anything. Previously, we had seen the robot interact with unknown objects without any real-world training, only virtual simulations. Now, Dactyl has built on that ability to learn this new one.
Allowing the robot to analyze the cube and figure out a way to solve it would be one thing; actually pulling off the movements to carry that out would be another, but “learning” to solve means that even with severe impairments that altered its path of action — like having some of its fingers tied together — the system was able to make adjustments to find the path toward solving the puzzle.
It’s certainly not a flawless system, and it won’t be taking down any world champions in the next few weeks, but in the video below you can see it solve the cube in less than four minutes, which is pretty damn impressive.