Neural Networking: Robots Learning From Video

Humans are very good at watching others and imitating what they do. Show someone a video of flipping a switch to turn on a CNC machine and after a single viewing they’ll be able to do it themselves. But can a robot do the same?

Bear in mind that we want the demonstration video to be of a human arm and hand flipping the switch. When the robot does it, the camera that is its eye will be seeing its robot arm and gripper. So somehow it’ll have to know that its robot parts are equivalent to the human parts in the demonstration video. Oh, and the switch in the demonstration video may be a different model and make, and the CNC machine may be a different one, though we’ll at least put the robot within reach of its switch.

Sound difficult?

Researchers from Google Brain and the University of Southern California have done it. In their paper describing how, they talk about a few different experiments but we’ll focus on just one, getting a robot to imitate pouring a liquid from a container into a cup.

Continue reading “Neural Networking: Robots Learning From Video”

Capture The Flag Challenge Is The Perfect Gift

Nothing says friendship like a reverse engineering challenge on unknown terrain as a birthday present. When [Rikaard] turned 25 earlier this year, his friend [Veydh] put together a Capture the Flag challenge on an ESP8266 for him. As a software guy with no electronics background, [Rikaard] had no idea what he was presented with, but was eager to find out and to document his journey.

Left without guidance or instructions, [Rikaard] went on to learn more about the ESP8266, with the goal to dump its flash content, hoping to find some clues in it. Discovering the board is running NodeMCU and contains some compiled Lua files, he stepped foot in yet another unknown territory that led him down the Lua bytecode rabbit hole. After a detour describing his adjustments for the ESP’s eLua implementation to the decompiler he uses, his quest to capture the flag began for real.

While this wasn’t [Rikaard]’s first reverse engineering challenge, it was his first in an completely unknown environment outside his comfort zone — the endurance he demonstrated is admirable. There is of course still a long way down the road before one opens up chips or counts transistors in a slightly more complex system.

Flying The Friendly Skies With A Hall Effect Joystick

There are plenty of PC joysticks out there, but that didn’t stop [dizekat] from building his own. Most joysticks measure position mechanically using potentiometers or encoders. Only a few high-end models use Hall effect sensors. That’s the route [dizekat] took.

Hall effect sensors are non-contact devices which measure magnetic fields. They can be used to measure the position and orientation of a magnet. That’s exactly how [dizekat] is using a trio of sensors in his design. The core of the joystick is a universal joint from an old R/C car. The center section of the joint (called a spider) has two one millimeter thick disc magnets glued to it. The Hall sensors themselves are mounted in the universal itself. [Dizekat] used a small piece of a chopstick to hold the sensors in position while he found the zero point and glued them in. A third Hall effect sensor is used to measure a throttle stick positioned on the side of the box.

An Arduino micro reads the sensors and converts the analog signal to USB.  The Arduino Joystick Library by [Matthew Heironimus] formats the data into something a PC can understand.

While this is definitely a rough work in progress, we’re excited by how much [dizekat] has accomplished with simple hand tools and glue. You don’t need a 3D printer, laser cutter, and a CNC to pull off an awesome hack!

If you think Hall effect sensors are just for joysticks, you’d be wrong – they work as cameras for imaging magnetic fields too!

Making A Covox Speech Thing Work On A Modern PC

Long ago, when mainframes ruled the earth, computers were mute. In this era before MP3s and MMUs, most home computers could only manage a simple beep or two. Unless you had an add-on device like the Covox Speech Thing, that is. This 1986 device plugged into your parallel port and allowed you to play sound. Glorious 8-bit, mono sound. [Yeo Kheng Meng] had heard of this device, and wondered what it would take to get it running again on a modern Linux computer. So he found out in the best possible way: by doing it.

Continue reading “Making A Covox Speech Thing Work On A Modern PC”

Speech Recognition For Linux Gets A Little Closer

It has become commonplace to yell out commands to a little box and have it answer you. However, voice input for the desktop has never really gone mainstream. This is particularly slow for Linux users whose options are shockingly limited, although decent speech support is baked into recent versions of Windows and OS X Yosemite and beyond.

There are four well-known open speech recognition engines: CMU Sphinx, Julius, Kaldi, and the recent release of Mozilla’s DeepSpeech (part of their Common Voice initiative). The trick for Linux users is successfully setting them up and using them in applications. [Michael Sheldon] aims to fix that — at least for DeepSpeech. He’s created an IBus plugin that lets DeepSpeech work with nearly any X application. He’s also provided PPAs that should make it easy to install for Ubuntu or related distributions.

You can see in the video below that it works, although [Michael] admits it is just a starting point. However, the great thing about Open Source is that armed with a working set up, it should be easy for others to contribute and build on the work he’s started.

Continue reading “Speech Recognition For Linux Gets A Little Closer”

Recreating The Radio From Portal

If you’ve played Valve’s masterpiece Portal, there’s probably plenty of details that stick in your mind even a decade after its release. The song at the end, GLaDOS, “The cake is a lie”, and so on. Part of the reason people are still talking about Portal after all these years is because of the imaginative world building that went into it. One of these little nuggets of creativity has stuck with [Alexander Isakov] long enough that it became his personal mission to bring it into the real world. No, it wasn’t the iconic “portal gun” or even one of the oft-quoted robotic turrets. It’s that little clock that plays a jingle when you first start the game.

Alright, so perhaps it isn’t the part of the game that we would be obsessed with turning into a real-life object. But for whatever reason, [Alexander] simply had to have that radio. Of course, being the 21st century and all his version isn’t actually a radio, it’s a Bluetooth speaker. Though he did go through the trouble of adding a fake display showing the same frequency as the one in-game was tuned to.

The model he created of the Portal radio in Fusion 360 is very well done, and available on MyMiniFactory for anyone who might wish to create their own Aperture Science-themed home decor. Though fair warning, due to its size it does consume around 1 kg of plastic for all of the printed parts.

For the internal Bluetooth speaker, [Alexander] used a model which he got for free after eating three packages of potato chips. That sounds about the best possible way to source your components, and if anyone knows other ways we can eat snack food and have electronics sent to our door, please let us know. Even if you don’t have the same eat-for-gear promotion running in your neck of the woods, it looks like adapting the model to a different speaker shouldn’t be too difficult. There’s certainly enough space inside, at least.

Over the years we’ve seen some very impressive Portal builds, going all the way back to the infamous levitating portal gun [Caleb Kraft] built in 2012. Yes, we’ve even seen somebody do the radio before. At this point it’s probably safe to say that Valve can add “Create cultural touchstone” to their one-sheet.

Continue reading “Recreating The Radio From Portal”

Improvising An EPROM Eraser

Back in the old days, when we were still twiddling bits with magnetized needles, changing the data on an EPROM wasn’t as simple as shoving it in a programmer. These memory chips were erased with UV light shining through a quartz window onto a silicon die. At the time, there were neat little blacklights in a box sold to erase these chips. There’s little need for these chip erasers now, so how do you erase and program a chip these days? Build your own chip eraser using components that would have blown minds back in the 70s.

[Charles] got his hands on an old 2764 EPROM for a project, but this chip had a problem — there was still data on it. Fortunately, old electronics are highly resistant to abuse, so he pulled out the obvious equipment to erase this chip, a 300 watt tanning lamp. This almost burnt down the house, and after a second round of erasing of six hours under the lamp, there were still unerased bits.

Our ability to generate UV light has improved dramatically over the last fifty years, and [Charles] remembered he had an assortment of LEDs, including a few tiny 5mW UV LEDs. Can five milliwatts do what three hundred watts couldn’t? Yes; the LED had the right frequency to flip a bit, and erasing an EPROM is a function of intensity and time. All you really need to do is shine a LED onto a chip for a few hours.

With this vintage chip erased, [Charles] slapped together an EPROM programmer — with a programming voltage of 21V — out of an ATMega and a bench power supply. It eventually worked, allowing [Charles]’ project, a vintage liquid crystal display, to have the right data using vintage-correct parts.