Arduino Projects: Robotic Footage, Ghostwriter, and Monitoring
-
Check out James Bruton’s robotic camera operator | Arduino Blog
We’re ages past the time when a YouTuber could get away with sloppy camera work. If someone wants to achieve any level of success making videos today, they need near-professional camera equipment. But even that equipment isn’t enough if it’s still used for static shots. Many makers build sliders and other rigs, but James Bruton skipped those small steps and jumped straight to a versatile robotic camera operator.
Bruton wanted to capture dynamic videos at any time of day or night without hiring a live-in camera operator and this robot is the result. It can drive around and has complete control over the mounted DSLR camera. It can follow pre-programmed movement patterns, can use tracking to stay focused on Bruton, or a combination of the two to change perspective while staying centered on Bruton. It can also automatically zoom in and out based on motion to ensure that anything interesting is in frame. Bruton can even trigger additional features using foot switches, such as raising a robotic thumbs-up into the frame.
-
Ghostwriter is a gorgeous typewriter with an onboard AI co-writer | Arduino Blog
Much to the consternation of those of us who write for a living, AI writers are gaining traction as their capabilities increase. The hot name in the AI content creation industry at the moment is ChatGPT, which is powered by OpenAI’s GPT-3 engine. With the right input and direction, GPT-3 can output some impressive writing. To harness that power in a co-writing assistant, Arvind Sanjeev built the Ghostwriter.
Ghostwriter is a vintage Brother electric typewriter retrofitted with modern hardware that lets it access and utilize the GPT-3 API (application programming interface). The user can type a query onto paper, such as a writing prompt or question, and GPT-3 will return a result that also prints out on the paper. By guiding GPT-3 with suitable prompts, the user can receive as much AI-generated text as they like. They might then edit that text for publication, use it as-is, or showcase the manuscript as an art piece.
-
Predicting potential motor failures just using sound | Arduino Blog
Nearly every manufacturer uses a machine at some point in their process, and each of those machines is almost guaranteed to contain at least one motor. In order to maintain uptime and efficiency, these motors must always work correctly, as even a small breakdown can lead to disastrous effects. Predictive maintenance aims to achieve this goal while also not going overboard in trying to prevent them entirely by combining sensors with predictive techniques that can schedule maintenance when a failure is probable.
Shebin Jose Jacob’s solution utilizes the Arduino Nano 33 BLE Sense, along with its built-in microphone, to capture audio and predict when a motor is about to fail. He achieved this by first creating a new Edge Impulse project and gathering samples for four classes of sound: OK, anomaly 1, and anomaly 2, as well as general background noise. After designing an impulse and training a classification model on the samples, he was able to achieve an impressive accuracy of about 95% on the test samples.