Using colors to predict whether this is Pikachu or Bulbasaur…
The deployment environments of a machine learning (ML) model are changing. In recent years, we went from locally training models and running them on standalone scripts to deploying them in massive and specialized setups. However, the industry hasn’t been focusing only on large-scaled-productionized ML, but also its small, portable, and accessible counterpart—for machine learning has found a place in embedded systems.
Here is an easy project using a Echo Dot (Alexa) to control my ESP8266. I give it simple commands (Alexa, lights, off) and the command shows on the LCD screen attached to the ESP8266. Actual relays will be the next step to attach.
The project is based on the Adafruit tutorial at https://learn.adafruit.com/easy-alexa-or-echo-control-of-your-esp8266-huzzah/overview
with LCD and other modifications made by me. My code is found at https://pastebin.com/NjMcsTRh
The first version of my Light Up Clock for Kids I published a few years ago. At the time my wife and I were going crazy with our young kids (between 2 and 4 years old) who could not understand how to “wait for the 7” on the clock before coming in and waking us up early in the morning! Now the youngest (the 4th and hopefully the last) is 3 years old and this clock has been life-saving the last few years! Enhanced over time, it has provided a HUGE solution to our “child-waking-us-up-at-insane-hours-of-the-morning” problem!!!
The game is displayed using a laser which is directed using mirrors. You can find kits on eBay (search for laser galvo).
A low-cost home robot that can do tasks around the house.
I have been developing an autonomous home-assistant robot. This robot was entirely designed, created, and built from scratch with no use of a kit or directions. In the process of creating this, I taught myself how to use ROS, Python, C, HTML, CSS, OpenCV, and other complex systems/languages.
The robot is able to travel around the house independently using Simultaneous Localization and Mapping (SLAM) with Robot Operating System (ROS) for navigation. It knows where to go based on pre-set waypoints. This machine is a prototype of a low-cost robotic assistant for the average person to use in their home. It combines facial recognition, navigation, and a web-control page, as well as other easy-control options such as gesture-control, Wii remote, and even hand-guided. The robot uses many Proportional Integral Derivative (PID) control systems which allows the robot to self-balance, making it more user-friendly, lighter weight, and maneuverable.
Low-cost 3D-scanning system offers sub-30-micron accuracy on a cheap Raspberry Pi Camera Module v2.1, or 10-micron on the HQ Camera.
Thomas Megel is aiming to bring down the cost and complexity of accurate 3D scanning — and to prove it, he’s scanned a Raspberry Pi single-board computer using another Raspberry Pi single-board computer.
We live in a house with a very tight garage, and our relatively big car leaves a tiny space in front. I designed and built this simple project to visually guide the driver into the optimal parking distance, using real-time feedback about how close the car is to the wall in front. In short, it tells you when to stop.
The project uses an ultrasonic sensor and Arduino to measure distance and then displays it on a full-color LED strip as a progress bar. The sensor is mounted on the wall; as the distance between the car and wall shrinks, the light strip shows an increasing number of illuminated LEDs, which also change color from green to amber to red, and then finally, flashing red.
This is another article in know-how series, which focuses solely on a specific feature or technique and today I’ll tell you how to use neural network trained with Edge Impulse with new Raspberry Pico 2040. Also make sure to watch the tutorial video with step-by-step instructions.
Edge Impulse is a platform that enables developers to easily train and deploy deep learning models on embedded devices. You can read the full introduction in my first article of the series about TinyML. Now, let’s jump straight to action.
Over the past years, The Things Networks has worked around the democratization of the Internet of Things, building a global and crowdsourced LoraWAN network carried by the thousands of users operating their own gateways worldwide. Thanks to Lacuna Space’ satellites constellation, the network coverage goes one step further. Lacuna Space uses LEO (Low-Earth Orbit) satellites to provide LoRaWAN coverage at any point around the globe. Messages received by satellites are then routed to ground stations and forwarded to LoRaWAN service providers such as TTN. This technology can benefit several industries and applications: tracking a vessel not only in harbors but across the oceans, monitoring endangered species in remote areas. All that with only 25mW power (ISM band limit) to send a message to the satellite. This is truly amazing!
Christopher Getschmann wanted a wall-sized map of the world. He soon realized, however, that it’s tough to actually buy such a map that’s both beautiful and detailed enough to satisfy his cartographic tastes. While many would simply move on to the next “thing,” Getschmann instead took things into his own hands, and built a pen plotter specifically to draw a massive 2×3 meter map for his wall.
