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!

Mickey Mouse Is Getting His Own Beats By Dre Headphones

Beats, Amazon
Beats, Amazon

Since debuting in a black-and-white cartoon in 1928, Mickey Mouse has grown into an icon recognized around the world. To celebrate the character's 90th birthday, Beats by Dre has designed him his very own pair of Solo3s, The Verge reports.

The special-edition, wireless headphones depict a pattern of classic Mickeys against a gray background. They come in a gray felt carrying case—a nod to the material used to make the Mickey Mouse ears sold at Disney parks. The purchase also includes an enamel pin and decal sticker commemorating the anniversary.

At $329.95, the Mickey headphones cost about $30 more than conventional Solo3 headphones, but it's not unusual for Beats to charge extra for limited-edition designs. In 2014, the company released Hello Kitty Solo2s for the character's 40th anniversary for $50 more than the headphones' standard selling price.

The Mickey Beats will be available starting November 11—a few days before the 90th anniversary of the premiere of Steamboat Willie. You can pre-order them on Amazon today.

[h/t The Verge]

This Smart Mug Alerts You When You've Had Too Much Caffeine

Ember
Ember

Since 2010, Ember has been giving perfectionists ultimate control over their morning coffee. Their travel mug lets you set the preferred temperature of your drink down to the degree when you're on the go, and their ceramic cup allows you to do the same in the office or at home. Now, in addition to telling you how hot your beverage is at all times, Ember lets you know how much caffeine you're consuming through Apple's Health app, CNET reports.

Ember's new feature takes advantage of the same Bluetooth technology that lets you control the temperature of you drink from your smartphone. Beginning October 17, you can connect your Ember vessel to your Apple device to keep track of what you're drinking. If you drink all your tea and coffee from an Ember mug, the Health app should be able to give you a rough estimate of your daily caffeine intake.

Ember wasn't originally designed to measure caffeine content, but its built-in sensors allow it do so. In order to maintain a constant temperature, the mug needs to know whether it's full or empty, and exactly how much liquid it's holding at any given time. The feature also gives you the option to preset your serving size within the app if you drink the same amount of coffee everyday. And if you like to drink specific beverages at their recommended temperatures, the mug can guess what type of drink it's holding based on how hot it is.

The new caffeine-calculating feature from Ember is especially useful for coffee addicts: If the mug senses you've exceeded your recommended caffeine intake for the day, it will alert you on your phone. Here are some energizing caffeine alternatives to keep that from happening.

[h/t CNET]

SECTIONS

arrow
LIVE SMARTER