The jigsaw puzzles are a lot of fun and to complete it requires an amazing amount of problem solving skills that humans are uniquely suited to. With a typical jigsaw puzzle, the printed image serves as the main reference for locating the piece. But there are special jigsaw puzzles that are all solid color, forcing analysts to find the location of a piece based solely on the unique shape of the edges. Puzzles like these take months of trial and error to solve – and that’s human. Build a robot to solve those solid color puzzles Quite a challenge, but Shane Wheaton’s engineering skills were up to the task.
As Wheaton says, this is the future and robots You should be able to have a good time for us. But this is still quite an engineering challenge. To explain how Wighton does this work, we’ll start with the simplest part of the equation: the motion system. The robot looks like a large CNC router and is very close to what it is in practice. The sturdy wooden table supports the CoreXY kinematic system, which allows for extremely fast movement. It can pick up single jig saw pieces using a vacuum suction end effect like the one you find in a pick-and-place machine. A vacuum suction table, like the kind used to install plywood on CNC routers, keeps the pieces I lay down after the robot drops them.
All this is impressive and was easy compared to the rest of the bot. In order for this robot to solve the puzzle, it must compare every edge of every piece to every edge of every edge else Piece. For a 5000 piece puzzle like this, with 4 sides on each piece, the result is about 1.82 x 1077337 compared. If the robot performed one comparison per second, it would take 4.2 x 1077319 times the age of the universe to complete the comparisons. Wighton’s algorithm performs comparisons much faster than once per second and presumably takes shortcuts such as deleting edges and resolved blocks, but he still estimates that it will take about 3,000 years to solve the puzzle. In the next video, he plans to improve the algorithm and will go into more detail at that time.
Until then, it’s worth understanding how the bot compares to slashing. Wighton built a magazine for the robot to take the cut. Then he places the pieces on a backlit window to take a picture. A normal camera would distort the image and make edge measurements inaccurate, so Wighton used a specialized (and very expensive) center lens. This lens produces an image that looks as if it was taken from an infinite distance away, eliminating all distortion so that each edge is perfectly perpendicular to the image plane. With this distortion-free image, Wighton can use computer vision software to detect cutting edges and collect accurate measurements for its solution algorithm.
To prove it, Wighton made a custom 45-piece puzzle. The robot successfully solved this puzzle, but even this small puzzle took about an hour and a half to complete. The time for each additional piece increases exponentially, not linearly. To see how Wighton managed to overcome this crushing hurdle, be sure to catch the following video.
#robot #solves #jigsaw #puzzle #Hacksterio