sqiddster

I've thought about it, but I have a feeling that the dollar value that an interested AFOL (or even Bricklink store) would be willing to pay is quite a bit less than the cost of designing, manufacturing and selling something of this complexity for real. Perhaps it could be put to the test with croudsourcing but I'd need a realistic prototype and cost estimate first, which in itself is very expensive to obtain! As for 18 bins, a 'real' manufactured version of this could be created with any arbitrary number of bins. There is no inherent mechanical or software limitation to how many you can have. The machine currently is even designed to be modular; each 'layer' of bins is completely independent and repeatable. You're also spot on regarding recursive sorting, with enough runs through you could have as much granularity as you want.

Training itself doesn't take too long, maybe 2 days or so. The real computational difficulty is in rendering the 25 million images. This took about 2 years of CPU core time, parallelized over 800 AWS cores to be completed in about a day.

Yes! Because it recognizes parts individually, it would be easy to sort the parts into any categories that you choose ^_^

Over the past two and a half years, I've been working on my most insane project to date: the world's first Universal LEGO Sorting Machine. I call it 'Universal' because, thanks to the use of cutting-edge AI, it's capable of recognizing and sorting any LEGO part that has ever been produced. The machine itself is built from over 10,000 LEGO bricks, and, even though it's small enough to fit on a desk, it is capable of taking a large bucket of completely unsorted parts and categorizing them into 18 different output buckets at near-human speed. First, the machine uses a series of belts and a vibrating table to separate the parts out. It uses a camera and a Raspberry Pi to take streaming video footage of the parts running along a belt, and sends the footage wirelessly to a more powerful computer that runs a convolutional neural network - that's where the magic happens. A convolutional neural network is an AI technology that's designed to work with images. To build a network that is capable of recognizing almost 3000 different LEGO parts, the network needs a lot of training data. Using 3D models of LEGO bricks, I generated over 25 million images which were then used to train the network, allowing it to accurately recognize even the most obscure parts. I've also released a second video which demonstrates specifically how a neural network is able to recognize LEGO parts, and how I was able to train the system. The video also functions as a helpful beginner's introduction to the real technology behind AI.

Sorry, the PM went through my spam for some reason. Yeah, I'm working on other things at the moment I'm afraid. However, I did take some pictures (not cropped or edited or anything) but here you go. https://dl.dropboxusercontent.com/u/41931267/Shift%20Module%20Pics.zip Sorry about that.

Always nice to see another GBC builder! I look forward to seeing more of your original designs.

Cut the nubs off. Nobody will ever know

Yep, if you want inspiraion, just grab some popcorn and have a look through akiyuky's channel.

If you look closely, you can see a fantastic method of adjusting height with the gear racks and worm screw. That really is very clever.

For you, Philo, I'll be sure to get some photos ;)

Feel free If you ever really wanted to, I could take some detail pictures for you

Thanks, everyone! @Lasse, it has not gone through long-period testing yet, but it will before I bring it to an event. @Carsten, I think you are right in it being a tad slower than 1 ball per second, but I think it's pretty close.

Here's a little GBC module I made. All the movements come from 1 motor. It has a nice rhythm ;)

Your desk is so tidy!

I knew there was no bad intent. Scott was certainly very busy, all of his GBC modules disintegrated on arrival to the con (boxes dropped) and the poor guy had to spend most of the time rebuilding them. I don't blame him at all for missing this.