Prototyping, Making A Board For, And Coding An ARM Neural Net Robot

[Sean Hodgins]’s calls his three-part video series an Arduino Neural Network Robot but we’d rather call it an enjoyable series on prototyping, designing a board with surface mount parts, assembling it, and oh yeah, putting a neural network on it, all the while offering plenty of useful tips.

In part one, prototype and design, he starts us out with a prototype using a breadboard. The final robot isn’t on an Arduino, but instead is on a custom-made board built around an ARM Cortex-M0+ processor. However, for the prototype, he uses a SparkFun SAM21 Arduino-sized board, a Pololu DRV8835 dual motor driver board, four photoresistors, two motors, a battery, and sundry other parts.

Once he’s proven the prototype works, he creates the schematic for his custom board. Rather than start from scratch, he goes to SparkFun’s and Pololu’s websites for the schematics of their boards and incorporates those into his design. From there he talks about how and why he starts out in a CAD program, then moves on to KiCad where he talks about his approach to layout.

Part two is about soldering and assembly, from how he sorts the components while still in their shipping packages, to tips on doing the reflow in a toaster oven, and fixing bridges and parts that aren’t on all their pads, including the microprocessor.

In Part three he writes the code. The robot’s objective is simple, run away from the light. He first tests the photoresistors without the motors and then writes a procedural program to make the robot afraid of the light, this time with the motors. Finally, he writes the neural network code, but not before first giving a decent explanation of how the neural network works. He admits that you don’t really need a neural network to make the robot run away from the light. But from his comparisons of the robot running using the procedural approach and then the neural network approach, we think the neural network one responds better to what would be the in-between cases for the procedural approach. Admittedly, it could be that a better procedural version could be written, but having the neural network saved him the trouble and he’s shown us a lot that can be reused from the effort.

In case you want to replicate this, [Sean]’s provided a GitHub page with BOM, code and so on. Check out all three parts below, or watch just the parts that interest you.

Continue reading “Prototyping, Making A Board For, And Coding An ARM Neural Net Robot”

An Interview with Alex Williams, Grand Prize Winner

Alex Williams pulled off an incredible engineering project. He developed an Autonomous Underwater Vehicle (AUV) which uses a buoyancy engine rather than propellers as its propulsion mechanism and made the entire project Open Source and Open Hardware.

The design aims to make extended duration missions a possibility by using very little power to move the vessel. What’s as remarkable as the project itself is that Alex made a goal for himself to document the project to the level that it is fully reproducible. His success in both of these areas is what makes the Open Source Underwater Glider the perfect Grand Prize winner for the 2017 Hackaday Prize.

We got to sit down with Alex the morning after he won to talk about the project and the path he took to get here.

Continue reading “An Interview with Alex Williams, Grand Prize Winner”

Gorgeous Engineering Inside Wheels of a Robotic Trail Buddy

Robots are great in general, and [taylor] is currently working on something a bit unusual: a 3D printed explorer robot to autonomously follow outdoor trails, named Rover. Rover is still under development, and [taylor] recently completed the drive system and body designs, all shared via OnShape.

Rover has 3D printed 4.3:1 reduction planetary gearboxes embedded into each wheel, with off the shelf bearings and brushless motors. A Raspberry Pi sits in the driver’s seat, and the goal is to use a version of NVIDA’s TrailNet framework for GPS-free navigation of paths. As a result, [taylor] hopes to end up with a robotic “trail buddy” that can be made with off-the-shelf components and 3D printed parts.

Moving the motors and gearboxes into the wheels themselves makes for a very small main body to the robot, and it’s more than a bit strange to see the wheel spinning opposite to the wheel’s hub. Check out the video showcasing the latest development of the wheels, embedded below.

Continue reading “Gorgeous Engineering Inside Wheels of a Robotic Trail Buddy”

Real-Life Electronic Neurons

All the kids down at Stanford are talking about neural nets. Whether this is due to the actual utility of neural nets or because all those kids were born after AI’s last death in the mid-80s is anyone’s guess, but there is one significant drawback to this tiny subset of machine intelligence: it’s a complete abstraction. Nothing called a ‘neural net’ is actually like a nervous system, there are no dendrites or axions and you can’t learn how to do logic by connecting neurons together.

NeruroBytes is not a strange platform for neural nets. It’s physical neurons, rendered in PCBs and Molex connectors. Now, finally, it’s a Kickstarter project, and one of the more exciting educational electronic projects we’ve ever seen.

Regular Hackaday readers should be very familiar with NeuroBytes. It began as a project for the Hackaday Prize all the way back in 2015. There, it was recognized as a finalist for the Best Product, Since then, the team behind NeuroBytes have received an NHS grant, they’re certified Open Source Hardware through OSHWA, and there are now enough NeuroBytes to recreate the connectome of a flatworm. It’s doubtful the team actually has enough patience to recreate the brain of even the simplest organism, but is already an impressive feat.

The highlights of the NeuroBytes Kickstarter include seven different types of neurons for different sensory systems, kits to test the patellar reflex, and what is probably most interesting to the Hackaday crowd, a Braitenberg Vehicle chassis, meant to test the ideas set forth in Valentino Braitenberg’s book, Vehicles: Experiments in Synthetic Psychology. If that book doesn’t sound familiar, BEAM robots probably do; that’s where the idea for BEAM robots came from.

It’s been a long, long journey for [Zach] and the other creators of NeuroBytes to get to this point. It’s great that this project is now finally in the wild, and we can’t wait to see what comes of it. Hopefully a full flatworm connectome.

Bluetooth Photo Booth Gets Vetting at Wedding

With just two weeks to go before his friends’ wedding, [gistnoesis] built a well-featured robotic photo booth. Using a Bluetooth PS3 controller, guests could move the camera around, take a picture, style it in one of several ways (or not), and print it out with a single button press.

The camera is mounted on a DIY 2-axis gimbal made from extruded aluminium and 3D-printed parts. It can be moved left/right with one joystick, and up/down with the other. [gistnoesis] set up a four-panel split-screen display that shows the live feed from the camera and a diagram for the controls. The third panel shows the styled picture. Guests could explore the camera roll on the fourth panel.

LINN uses two PCs running Lubuntu, one of which is dedicated to running an open-source neural style transfer program. After someone takes a picture, they can change the style to make it look like a Van Gogh or Picasso before printing it out. A handful of wedding attendees knew about some of the extra features, like manual exposure control and the five-second timer option, and the information spread gradually. Not only was LINN a great conversation piece, it inspired multi-generational collaboration.

Despite the assembled size, LINN packs up nicely into a couple of reusable shopping bags for transport (minus the TV, of course).  This vintage photo booth we saw a few years ago is more of a one-piece solution, although it isn’t as feature-rich.

Continue reading “Bluetooth Photo Booth Gets Vetting at Wedding”

3D-Printed Robot Golem Only a Tiny Bit Creepy

ASPIR, the Autonomous Support and Positive Inspiration Robot is an goblin-sized robot, designed by [John Choi], aims to split the difference between smaller hobbyist robots and more robust but pricy full-sized humanoids only a research institute could afford. By contrast, [John] estimates it cost a relatively meager $2,500 to create such a homunculus.

The robot consists of 33 servos of various types moving the limb, controlled by an Arduino Mega with a servo control shield seated on it. The chassis uses 5 kg of filament and took 300 hours to print, and it has a skeleton made up of aluminum hex rods. Spring-loaded RC shocks help reinforce the shoulders. There are some nice touches, like 3D-printed hands with living hinge fingers, each digit actuated by a metal-gear micro servo. It stores its power bricks in its shins. For sensors it includes a chest-mounted webcam and a laser distance sensor.

The main design feature is the Android smartphone serving as its brains, and also — at least cosmetically — its eyes. Those eyes… might be just a teensy bit too Chucky for our taste. (Nice work, [John]!)

Robotic Arm Rivals Industrial Counterparts

We’ve seen industrial robotic arms in real life. We’ve seen them in classrooms and factories. Before today, we’ve never mistaken a homemade robotic arm for one of the price-of-a-new-home robotic arms. Today, [Chris Annin] made us look twice when we watched the video of his six-axis robotic arm. Most of the DIY arms have a personal flare from their creator so we have to assume [Chris Annin] is either a robot himself or he intended to build a very clean-looking arm when he started.

He puts it through its paces in the video, available after the break, by starting with some stretches, weight-lifting, then following it up and a game of Jenga. After a hard day, we see the arm helping in the kitchen and even cracking open a cold one. At the ten-minute mark, [Chris Annin] walks us through the major components and talks about where to find many, many more details about the arm.

Many of the robotic arms on Hackaday are here by virtue of resourcefulness, creativity or unusual implementation but this one is here because of its similarity to the big boys.

Continue reading “Robotic Arm Rivals Industrial Counterparts”