Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning

iStock // Ekaterina Minaeva
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Tesla Drivers Now Have Access to a Library of Fart Sounds in Their Car

Spencer Platt, Getty Images
Spencer Platt, Getty Images

Tesla’s latest software update includes more than just a few technical tweaks. It also turns the electric vehicles into on-demand fart machines, according to Inverse.

Tesla’s Emissions Testing Mode lets drivers choose different fart sounds from the car’s touchscreen, giving electric-car owners a good sense of Elon Musk’s sense of toilet humor. There’s “Short Shorts Ripper,” “Falcon Heavy,” Ludicrous Fart,” Neurastink,” “Boring Fart,” and “Not a Fart,” all of which are named after some Musky in-joke. (The last one is a play on the Boring Company’s Not a Flamethrower.) Should drivers find it impossible to choose between all the sound effects, the “I’m so random” will shuffle through them automatically.

Users can program the fart sounds to play when a turn signal is activated or when the driver touches the left-side steering scroll wheel. You can see/hear it in action in a Tesla Model S here.

Farting functionality isn’t the only whimsical edition to the software. At this point, Tesla's in-car software comes with a variety of Easter eggs for users to unlock, including games, special lighting effects, and more. In addition to all the flatulence, this update includes a Romance Mode that brings up video of a cozy, crackling fire on the central console and prompts the car to blast the heat and turn on some sensual tunes.

[h/t Inverse]

Warning: Don't Fall for the New Netflix Phishing Scam Going Around

iStock.com/wutwhanfoto
iStock.com/wutwhanfoto

In addition to catching up on Stranger Things and kicking ex-roommates off your account, you now have something else to worry about if you're a Netflix user. As WYFF 4 reports, there's a phishing scam circulating through email that targets subscribers to the streaming service.

The email is formatted to look like an official message from Netflix, with the company's logo at the top. It informs you that "your account is on hold," and that you need to update your payment information before service can resume.

But law officials are warning web users not to click the link in the email, or in any emails that come from unfamiliar sources. "Criminals want you to click the links, so that you voluntarily give your personal identifying information away. It is very successful," the Solon, Ohio police department shared in a Facebook post. "Don't click the links. The links could also be a way to install malware on your computer."

The phishing email contains a few clues that it's not legitimate: It lists an international phone number, uses the British spelling of centre, and opens with the unusual greeting "Hi Dear."

But even without these giveaways, you should always be wary of emails that ask for personal information, even if they appear to come from companies that you trust. According to Netflix, communications emails will always come from the address info@mailer.netflix.com. If you receive a message from this address (or an address that looks like it), and aren't sure if it's trustworthy, you can always go to Netflix and reach out to customer service about the problem directly.

[h/t WYFF 4]

SECTIONS

arrow
LIVE SMARTER