Devices and Open Hardware: Buzzwords, Arduino, and Raspberry Pi
-
The State of IoT – December 2022 | Ubuntu
Welcome to the December edition of the monthly State of IoT series. While we ended 2021 with a rosy outlook prompted by rising unit shipments and hardware spending, 2022 ended amidst supply chain disruptions, economic sanctions and an ongoing war. Despite this, we will likely remember 2022 as a transitional year in the ever-increasing adoption of embedded and IoT devices. Cybersecurity vulnerabilities in IoT devices, smart homes and a few major announcements took the headlines. Without further ado, let’s dive straight into the most prominent news across the IoT landscape from the last month of what proved to be an exciting year.
-
This search and rescue robot creates 3D maps of disaster areas | Arduino Blog
If you look at footage from the search and rescue efforts following any disaster, you’ll see that first responders have a very difficult time navigating through rubble to find people in need of emergency care. They also have to take extra precautions, as gas line ruptures and other hazards present dangers they don’t normally face. To assist in those efforts, Ranit Bhowmick and his team built the SARDA (Search and Rescue Deployable Assistant) robot that can create 3D maps of disaster areas.
SARDA is currently an early prototype and its capabilities are limited, but the idea is sound. It is a little wheeled robot that would (in theory, at least) rove around a disaster area while mapping its surroundings. It could work autonomously or an operator could guide it manually. While moving around an area, it would generate a 3D map of rigid objects, like walls and obstacles, and also health hazards like clouds of smoke, heat, or toxic gases. A computer at a control station would use that data to produce a digital 3D render of the environment that first responders could reference during their search and rescue efforts.
-
Preventing driver fatigue with the Nicla Vision and Edge Impulse FOMO | Arduino Blog
Drivers who are experiencing tiredness become large dangers to both themselves and anyone else around them on the road, as reaction times, concentration, and alertness are all greatly impaired. This is why Shebin Jose Jacob decided to create a driver drowsiness detection system that can accurately tell when someone is fatigued and should pull over for some rest.
The solution is comprised of a single Nicla Vision board, which contains a 2MP camera for collecting images, an IMU, microphone, distance sensor, and finally a dual Arm Cortex-M7/M4 processor for quickly running embedded machine learning models. Data for the project was gathered by taking many pictures and labeling the bounding boxes surrounding the eyes as either closed or open. From here, Jacob trained a FOMO-based (Faster Objects, More Objects) object recognition model on the sample images and was able to achieve an accuracy of 100%.
-
Queue: the Fun Meeting Facilitator
Queue, the fun arduino based, led signified meeting facilitation object works by assigning an led to each person in the meeting and giving them each a set amount of time to present there idea. It would do this by utilizing the IFTTT chip in the board, connecting to a world timer and letting everyone know that there turn is up after an allotted amount of time, by flashing the LED.
-
Overview | Raspberry Pi Zero NPR One Radio | Adafruit Learning System
If you are a NPR nerd, this project is for you.
-
A Raspberry Pi Pico Pen Holder and Calendar for Your Desk
-
Old MacDonald had a FARM, and became a safer driver - Hackster.io
The first step in the project was creating the model, and for that I needed data. I used the Raspberry Pi and camera to take photos several hundred times while I was out driving so I had some realistic samples for what the model would be seeing. I collected around 300 images of me driving with my seatbelt on in various times of the day and different amounts of sunlight to vary the input. Here was the short Python script I developed to capture those images: