• Brandon Lucia: Orbital Edge Computing in Smart Nanosatellites
    Articles,  Blog

    Brandon Lucia: Orbital Edge Computing in Smart Nanosatellites

    In my lab we’re working on what’s called orbital edge computing. Edge computing is a way of processing sensor data using computing resources that are physically co-located with the sensors that collect that data. The advantage of edge computing is that we don’t need to spend a lot of time and energy sending those sensor data from the sensor to a cloud or to a data center for processing. Instead, we can use that time and energy to process the data locally using machine learning inference algorithms to produce useful conclusions based on the data that we’ve collected. We’re taking the ideas of edge computing and applying those ideas in…

  • Physical computing: HowTo control LEDs, electric motors or servos through GPIOs
    Articles,  Blog

    Physical computing: HowTo control LEDs, electric motors or servos through GPIOs

    In this video I would like to explain how to amplify digital signals, so that you can control homebuilt peripherals by computers or microcontrollers. Furthermore simple input functionalities are treated. The control units I am using are an Arduino Uno microcontroller and a Raspberry Pi single board computer. Both computing machines have digital input/output pins that can be used to control peripherals. Before connecting a device to a pin you must consider the electrical properties of the ports! The Arduino Uno operates with a pin voltage of 5V, while the voltage at the pins of the Raspberry Pi must be kept below 3.3V. First let’s have a look at the…

  • How Machine Learning enables Edge Computing
    Articles,  Blog

    How Machine Learning enables Edge Computing

    How Machine Learning enables Edge Computing With the maturing of IoT technology, we can cover the world in sensors and give computers access to the physical world in a way that just wasn’t possible before. Here’s an example: You have a factory, with lots of machines designed to assemble a widget. From time to time, one of these machines breaks, disrupting production and leaving you with a big headache. Having heard of “predictive maintenance”, you decide to place sensors all over the production line. These sensor collect data continuously. The data collected by the sensors is very often not easily understood by humans. We just don’t deal very well with…