The inventor Daniel West has created a sorter for the details of the LEGO designer based on artificial intelligence.

Made of 10,000 LEGO parts, the LEGO universal sorter uses a neural network to identify, classify and organize plastic parts more efficiently and quickly than a human could.

The parts are loaded onto a moving tape, where they are sorted, with a camera installed that captures all the details on the video. The Raspberry Pi minicomputer then processes the video stream and transmits the data to the laptop. The software compares each item with a database containing 3D models of all LEGO items.

As soon as the neural network matches the part with the part number, it sends the data back to the sorter, who at this point knows which of the 18 sorting baskets to place. The machine processes approximately one brick every two seconds.