For all the complexity involved in driving, it becomes second nature to respond to pedestrians, environmental conditions, even the basic rules of the road. When it comes to AI, teaching machine learning algorithms how to drive in a virtual world makes sense when the real one is packed full of squishy humans and other potential catastrophes. So, why not use the wildly successful virtual world of Grand Theft Auto V to teach machine learning programs to operate a vehicle?
The hard problem with this approach is getting a large enough sample for the machine learning to be viable. The idea is this: the virtual world provides a far more efficient solution to supplying enough data to these programs compared to the time-consuming task of annotating object data from real-world images. In addition to scaling up the amount of data, researchers can manipulate weather, traffic, pedestrians and more to create complex conditions with which to train AI.
It’s pretty easy to teach the “rules of the road” — we do with 16-year-olds all the time. But those earliest drivers have already spent a lifetime observing the real world and watching parents drive. The virtual world inside GTA V is fantastically realistic. Humans are great pattern recognizers and fickle gamers would cry foul at anything that doesn’t analog real life. What we’re left with is a near-perfect source of test cases for machine learning to be applied to the hard part of self-drive: understanding the vastly variable world every vehicle encounters.
A team of researchers from Intel Labs and Darmstadt University in Germany created a program that automatically indexes the virtual world (as seen above), creating useful data for a machine learning program to consume. This isn’t a complete substitute for real-world experience mind you, but the freedom to make a few mistakes before putting an AI behind the wheel of a vehicle has the potential to speed up development of autonomous vehicles. Read the paper the team published Playing for Data: Ground Truth from Video Games.
In Star Trek, there is a race of cyborgs with a drive to slowly assimilate all sentient life. Their aesthetic is not far off from the one [Ronald]’s ever expanding coffee machine is taking on. One has to wonder, what dark purpose would bring the Borg into existence? Where did they start? If [Ronald] doesn’t get a satisfying cup of coffee soon, we may find out.
We covered the first iteration of his brewing machine in 2013. We like to imagine that he’s spent many sleepless, heavily caffeinated days and nights since then to arrive at version 2. This version is a mechanical improvement over his original Rube Goldberg contraption. On top of that, it has improved electronics and code, with a color screen reminiscent of industrial control panels.
He’s also working on something called, “AutoBaristaScript(TM),” which attempts to hold the entire universe of pour-over coffee within its clutches. We don’t know when he’ll stop, but when he does finally create that perfect cup, what’s left of the world will breathe easier. They’ll also drink good coffee.
Editor’s Note: The Borg do not necessarily want to assimilate all sentient life as an end unto itself. The Kazon were deemed unworthy of assimilation (VOY: Mortal Coil). The Borg are driven towards perfection, accomplished by adding technological and biological distinctiveness to their own.
We all know that the little black globs on electronics has a semiconductor of some sort hiding beneath, but the process is one that’s not really explored much in the home shop. The basic story being that, for various reasons , there is no cheaper way to get a chip on a board than to use the aptly named chip-on-board or COB process. Without the expense of encapsulating the raw chunk of etched and plated silicon, the semiconductor retailer can sell the chip for pennies. It’s also a great way to accept delivery of custom silicon or place a grouping of chips closely together while maintaining a cheap, reliable, and low-profile package.
As SparkFun reveals, the story begins with a tray of silicon wafers. A person epoxies the wafer with some conductive glue to its place on the board. Surprisingly, alignment isn’t critical. The epoxy dries and then the circuit board is taken to a, “semi-automatic thermosonic wire bonding machine,” and slotted into a fixture at its base. The awesomely named machine needs the operator to find the center of the first two pads to be bonded with wire. Using this information it quickly bonds the pads on the silicon wafer to the board — a process you’ll find satisfying in the clip below.
The final step is to place the familiar black blob of epoxy over the assembly and bake the board at the temperature the recipe in the datasheet demands. It’s a common manufacturing process that saves more money than coloring a multimeter anything other than yellow.
If your problem is how to put out a maximum amount of repetitive graffiti with a minimum amount of effort, we’ve got your solution. Or rather, [Ariel Schlesinger] and [Aram Bartholl] had your solution way back in 2010. The banner image says it all.
Of course, it doesn’t have to be graffiti that you’re spraying. This idea could be easily adapted to stencil that repeating floral pattern that my grandmother had on her walls too. It’s like a patterned paint roller, but for a spray can.
There’s room for improvements here. For instance, we can’t cut out stencils to save our life but we know where to find a laser cutter. From the look of things, they could use a slightly bigger stencil and something to catch the drips. There’s probably an optimal size for this gizmo, which calls for experimentation.
In the show Full Metal Alchemist, there’s a city called Rush Valley whose main and only business are the high performance prostheses called Automail. Engineers roam the street in Rush Valley; the best have their own shop like that of the high-end clothiers in Saville Row. Of course; it’s all fantasy set in a slightly ridiculous Japanese cartoon, but while walking through this year’s Maker Faire I began to wonder if is a future that may come to be.
The problem with prosthetics is the sheer variety of injuries, body types, and solutions needed. If an injury is an inch higher or an inch lower it can have a big effect on how a prosthetic will interact with the limb. If the skin is damaged or the nerves no longer function a different type of prosthesis will be needed. Some prostheses are to replace a lost limb, others are to assist an ailing body in order to return it to normal function. More than a few are simply temporary aides to help the body along in its healing efforts. Unfortunately, this means that it’s often the case that larger companies only sell the prostheses people are most likely to need; the rarer cases are often left without a solution.
However, we see hackers stepping up and not just working on the problems, but solving them. One of our semifinalists last year, openbionics, inspired one of the projects we’ll be talking about later. There are robotic legs. We met a guy at MRRF who has been 3D printing hands for his son from the E-nable project.
Along these lines, we saw two really cool projects at Maker Faire this year: The first is the Motor-Assistive Glove, or MAG. MAG is designed to help people with Peripheral Neropathy regain some use of their hands while they go through the lengthy road to recovery. Perhipheral Neuropathy is a disease, usually resulting from diabetes, toxin exposure, or infection, where the nerves are damaged in such a way that typically the hands and feet are no longer mobile or feel sensation in a useful way. Once the disease is in full swing, a previously able person will find themselves unable to do simple things like hold a can of soda or grasp a doorknob firmly enough to open it.
We had a chance to interview one of the members of the MAG team, [Victor Ardulov], which you can see in the following video. [Victor] and his group started a research project at the University of Santa Cruz to develop the Motor-Assistive Glove. The concept behind it is simple. People with Peripheral Neuropathy typically have some movement in their hands, but no strength. The MAG has some pressure sensors at the tips of the fingers. When the user puts pressure on the pad; the glove closes that finger. When the pressure is off; the glove opens. The concept is simple, but the path to something usable is a long one.
We tried to figure out how to describe the band [Wintergatan]. It took a lot of googling, and we decided to let their really incredible music machine do it for them. The best part? Unlike some projects like this that come our way, [Wintergatan] documented the whole build process in an eight part video series.
The core of the machine is a large drum with two tracks of alternating grey and black Lego Technic beams and pins. The musician sequences out the music using these. The pins activate levers which in turn drop ball bearings on the various sound producing devices in the machine. The melody is produced by a vibraphone. At first we thought the drum kit was electronic, but it turns out the wires going to it were to amplify the sound they made when hit. At the end of their travel the bearings are brought up to the hopper again by a bucket conveyor.
The final part count for the machine sits at 3,000 not including the 2,000 ball bearings rolling around inside of it. If you’ve ever tried to make a marble machine, then you’ll be just as impressed as we were that the machine only appeared to lose a few marbles in the course of a three minute song. Aside from the smoothness of the machine, which is impressive, we also enjoyed the pure, well, hackiness of it. We can spy regular wood screws, rubber bands, plywood, bits of wire, and all sorts of on-the-spot solutions. Just to add bonus cool, the whole project appears to have been built with just a bandsaw, a drill press, and a few hand power tools.
The machine is great, but we also really appreciate the hacker spirit behind it. When a commenter on a YouTube video told him he was a genius, he replied, “Thank you for that! But I do think, though, that it is mostly about being able to put in the time! I mean the talent of being stubborn and able to see things through are more important than the abilities you have to start with. If you work hard on anything, you will learn what you need and success! Its my idea anyway! So happy people like the machine!”. Which we think is just as cool as the machine itself. Video of the machine in action and part one of the build series after the break!
You’re walking through a gallery and stop to take in two seemingly unrelated pieces hanging side-by-side. One of them is a drawing of a bird, rendered with such precision its feathers could easily pop off the paper. The other is a sketch of what seems to be the same bird, however it’s nearly unrecognizable due to inconsistent line quality and parts that are entirely missing.
In staring at the photo-real drawing of the perfect bird, you marvel over the technical ability required to produce it. You also study the sloppy sketch just as long, picking out each one of its flaws, yet decide you like the image of the strange bird because the errors are interesting to you.
When you lean forward to read the title card posted on the wall between them, you’re shocked to learn that the two drastically different images were made by the same artist; not the person them self, but a machine they built to create both drawings in two different styles.
As an illustrator, I’m fascinated by drawing machines because their purpose is to emulate an act which has always been a highly personal form of self expression for me. Drawing machines and their creators are in a sense my peers.