RemoteXY Simplifies Arduino Control

January 30, 2020 by Al Williams 12 Comments

[Labpacks] wanted to build a robot car controlled by his phone. As a Hackaday reader, of course you probably can imagine building the car. Most could probably even write a phone application to do the control. But do you want to? In most cases, you are better off focusing on what you need to do and using something off the shelf for the parts that you can. In [Labpacks’] case, he used Visuino to avoid writing ordinary code and RemoteXY to handle the smartphone interface.

RemoteXY is a website that allows you to easily build a phone interface that will talk to your hardware over Bluetooth LE, USB, or Ethernet (including WiFi). One thing of interest: even though the interface builder is Web-based, the service claims that the interface structure stays on the controller. There’s no interaction with the remote servers when operating the user interface so there is no need for an external Internet connection.

Continue reading “RemoteXY Simplifies Arduino Control” →

New Contest: Train All The Things

January 21, 2020 by Mike Szczys 8 Comments

The old way was to write clever code that could handle every possible outcome. But what if you don’t know exactly what your inputs will look like, or just need a faster route to the final results? The answer is Machine Learning, and we want you to give it a try during the Train All the Things contest!

It’s hard to find a more buzz-worthy term than Artificial Intelligence. Right now, where the rubber hits the road in AI is Machine Learning and it’s never been so easy to get your feet wet in this realm.

From an 8-bit microcontroller to common single-board computers, you can do cool things like object recognition or color classification quite easily. Grab a beefier processor, dedicated ASIC, or lean heavily into the power of the cloud and you can do much more, like facial identification and gesture recognition. But the sky’s the limit. A big part of this contest is that we want everyone to get inspired by what you manage to pull off.

Yes, We Do Want to See Your ML “Hello World” Too!

Wait, wait, come back here. Have we already scared you off? Don’t read AI or ML and assume it’s not for you. We’ve included a category for “Artificial Intelligence Blinky” — your first attempt at doing something cool.

Need something simple to get you excited? How about Machine Learning on an ATtiny85 to sort Skittles candy by color? That uses just one color sensor for a quick and easy way to harvest data that forms a training set. But you could also climb up the ladder just a bit and make yourself a camera-based LEGO sorter or using an IMU in a magic wand to detect which spell you’re casting. Need more scientific inspiration? We’re hoping someday someone will build a training set that classifies microscope shots of micrometeorites. But we’d be equally excited with projects that tackle robot locomotion, natural language, and all the other wild ideas you can come up with.

Our guess is you don’t really need prizes to get excited about this one… most people have been itching for a reason to try out machine learning for quite some time. But we do have $100 Tindie gift certificates for the most interesting entry in each of the four contest categories: ML on the edge, ML on the gateway, AI blinky, and ML in the cloud.

Get started on your entry. The Train All The Things contest is sponsored by Digi-Key and runs until April 7th.

Hackaday Podcast 050: Counterfeit Chips, Servo Kalimba, Resistor Colors, Pi Emulation, And SED Maze Solver

January 17, 2020 by Mike Szczys 5 Comments

Hackaday editors Elliot Williams and Mike Szczys work their way through a dizzying maze of great hacks this week, bringing you along for the ride.

We take a look at simplifying home automation with Node-RED and marvel at the misuse of the SED — Linux’s stream editor for filtering and transforming text — to find your way through a maze. Have the hippest portable; grab your really old Apple laptop and stuff a not-so-old Apple desktop inside. We bring it on home with our love (or hate?) for the resistor color code.

Take a look at the links below if you want to follow along, and as always tell us what you think about this episode in the comments!

Take a look at the links below if you want to follow along, and as always, tell us what you think about this episode in the comments!

Direct download (60 MB or so.)

Continue reading “Hackaday Podcast 050: Counterfeit Chips, Servo Kalimba, Resistor Colors, Pi Emulation, And SED Maze Solver” →

Tiny Machine Learning On The Attiny85

January 7, 2020 by Danie Conradie 19 Comments

We tend to think that the lowest point of entry for machine learning (ML) is on a Raspberry Pi, which it definitely is not. [EloquentArduino] has been pushing the limits to the low end of the scale, and managed to get a basic classification model running on the ATtiny85.

Using his experience of running ML models on an old Arduino Nano, he had created a generator that can export C code from a scikit-learn. He tried using this generator to compile a support-vector colour classifier for the ATtiny85, but ran into a problem with the Arduino ATtiny85 compiler not supporting a variadic function used by the generator. Fortunately he had already experimented with an alternative approach that uses a non-variadic function, so he was able to dust that off and get it working. The classifier accepts inputs from an RGB sensor to identify a set of objects by colour. The model ended up easily fitting into the capabilities of the diminutive ATtiny85, using only 41% of the available flash and 4% of the available ram.

It’s important to note what [EloquentArduino] isn’t doing here: running an artificial neural network. They’re just too inefficient in terms of memory and computation time to fit on an ATtiny. But neural nets aren’t the only game in town, and if your task is classifying something based on a few inputs, like reading a gesture from accelerometer data, or naming a color from a color sensor, the approach here will serve you well. We wonder if this wouldn’t be a good solution to the pesky problem of identifying bats by their calls.

We really like how approachable machine learning has become and if you’re keen to give ML a go, have a look at the rest of the EloquentArduino blog, it’s a small goldmine.

We’re getting more and more machine learning related hacks, like basic ML on an Arduino Uno, and Lego sortings using ML on a Raspberry Pi.

Magnetic Circuits Are More Attractive Than Breadboarding

January 1, 2020 by Kristina Panos 16 Comments

Let’s face it, breadboarding can be frustrating, even for advanced electronics wizards. If you have an older board, you could be dealing with loose tie points left from large component legs, and power rails of questionable continuity. Conversely, it can be hard to jam just-made jumper wires into new boards without crumpling the copper. And no matter what the condition of the board is, once you’ve plugged in more than a few components, the circuit becomes hard to follow, much less troubleshoot when things go pear-shaped.

In the last twenty years or so, we’ve seen systems like Snap Circuits and Little Bits emerge that simplify the circuit building process by making the connections more intuitive and LEGO-like than even those 160-in-1 kits where you shove component legs between the coils of tight little springs. You will pay handsomely for this connective convenience. But why should you? Just make your own circuit blocks with cardboard, magnets, and copper tape. It should only cost about 10¢ each, as long as you source your magnets cheaply.

[rgco] gives the lowdown on building a minimal set of 23 component and connector blocks using 100 magnets. He’s got 11 example circuits to get you started, and some example videos of more advanced circuits that got tacked up after the break.

This method of making the circuit look more like the schematic may be the best way for the visually-inclined to learn electronics. But the best way to learn electronics depends on where you’re coming from.

Continue reading “Magnetic Circuits Are More Attractive Than Breadboarding” →

Sleek, Sophisticated Skittle Sorter

December 16, 2019 by Kristina Panos 5 Comments

Sorting candy by color is a classic problem that has its roots in the contract riders of rock stars who were just trying to make sure that more important contractual obligations were not being overlooked by concert venues. Through the years, candy sorting has become a classic problem for hobbyists to solve in various ways. After a false start a few years back, [little french kev] was compelled to dust off those plans and make the most compact sorter possible.

This minimalist beauty uses an Arduino Nano and RGB sensor to assess the color. At the top, a small servo rotates an arm inside the hopper that both shakes the Skittles and sets them up single file before the sensor. Another small servo spins the tube rack around to catch the rainbow. There’s an RGB LED in the base that bathes the tube from below in light that matches the Skittles. Check out the series of gifs on [little french kev]’s personal project site that show how each part works, and then watch the build video after the break.

Did you know you can roll your own color sensor from an RGB LED and a photocell? If you don’t think candy is so dandy, you could always color-sort your LEGO.

Continue reading “Sleek, Sophisticated Skittle Sorter” →

Jubilee: A Toolchanging Homage To 3D Printer Hackers Everywhere

November 14, 2019 by Sonya Vasquez 36 Comments

I admit that I’m late to the 3D printing game. While I just picked up my first printer in 2018, the rest of us have been oozing out beautiful prints for over a decade. And in that time we’ve seen many people reimagine the hardware for mischief besides just printing plastic. That decade of hacks got me thinking: what if the killer-app of 3D printing isn’t the printing? What if it’s programmable motion? With that, I wondered: what if we had a machine that just offered us motion capabilities? What if extending those motion capabilities was a first class feature? What if we had a machine that was meant to be hacked?

One year later, I am thrilled to release an open-source multitool motion platform I call Jubilee. For a world that’s hungry for toolchanging 3D printers, Jubilee might be the best toolchanging 3D printer you can build yourself–with nothing more than a set of hand tools and some patience. But it doesn’t stop there. With a standardized tool pattern established by E3D and a kinematically coupled hot-swappable bed, Jubilee is rigged to be extended by anyone looking to harness its programmable motion capabilities for some ad hoc automation.

Jubilee is my homage to you, the 3D printer hacker; but it’s meant to serve the open-source community at large. Around the world, scientists, artists, and hackers alike use the precision of automated machines for their own personal exploration and expression. But the tools we use now are either expensive or cumbersome–often coupled with a hefty learning curve but no up-front promise that they’ll meet our needs. To that end, Jubilee is meant to shortcut the knowledge needed to get things moving, literally. Jubilee wants to be an API for motion.

Continue reading “Jubilee: A Toolchanging Homage To 3D Printer Hackers Everywhere” →