This week, I did more work on the AI YOLO model on the golf cart, but I decided to move away from that a little bit and focus on some of the more mechanical aspects of the project. I wired up a simple breadboard circuit with an Arduino and the BTS7960 motor driver (capable of 49 amps continuous, which I am skeptical about) which is then wired up to a 30a 12v power supply and the giant steering motor.

Intro As Artificial Intelligence expands and continues to get more and more involved in aspects of daily life, it is only a matter of time until it gets involved in mainstream news feeds… so I sped things up and did it myself. Introducing The Neural Times, your “Only source of news, curated daily” The Neural Times is uses locally run Large Language Models (LLMs) and locally run Stable Diffusion (for image generation) to create satirical takes on current events worldwide.

Although I much prefer Linux, I do need Microsoft Windows for Fusion 360 along with a few other windows-only softwares. Fusion 360 will be no longer supporting Windows 10, so I figured an upgrade was in store, however, I was met with some requirement deficiencies according to Microsoft: These requirements were instated just for Windows 11, as Windows 10 (and previous versions) still have no mention of these necessities.

Introduction. Introducing Ultralytics YOLO11, the latest version of the acclaimed real-time object detection and image segmentation model. YOLO11 is built on cutting-edge advancements in deep learning and computer vision, offering unparalleled performance in terms of speed and accuracy. Its streamlined design makes it suitable for various applications and easily adaptable to different hardware platforms, from edge devices to cloud APIs. Read more… Although there are abundant tutorials on how to set up YOLO and train your own model, most are very case by case and are not applicable to all users.

This week, I made a major software breakthrough on the ROV. The IMU will periodically return invalid data, likely due to a faulty sensor. Due to the lack of error handling in the code, the ROV would receive a null value and the enire software system responsible for the control of the ROV would crash and need to be restarted. This bug that I’ve been tracking for nearly a month now was resolved by simply implenting some basic catches to detect when these null bits come in, and simply ignore them.

This week, I worked on the ROV for the robotics team as I had already completed the lightbox project as shown in the previous post. The robot has been experiencing some reliability issues, and they have something to do with the Raspberry Pi 5 we have onboard. The Pi would suddenly “crash” (meaning a loss of connection over ssh; ethernet port lights turned off; only red power light was illuminated) without warning.

SSH is awesome, but your options when trying to run a GUI application are a bit limited, especially on headless computers. Luckily there are a few ways to go about handling this problem, even if your computer has no monitor directly connected to it. SSH into the machine First of all, you need to ssh into your machine to get everything set up. Now you have a couple options. Some people may have a display (be it a full monitor, a TV screen, a touch display, etc) and others may have nothing it all.

Introduction Between all the various tutorials online, there is no straight way to installing OpenCV on a RPI… Issue’s I have encountered personally include but are not limited to the following: Building from source issues Various rare errors Garbage tutorials So in this simple guide, I have documented my installation of OpenCV on my Raspberry Pi, Model 3 B+ Other models should be quite similar. Requirements For this project, I used a Raspberry Pi 3 B+ running Ubuntu Server 20.

With the annual MATE ROV competition all finished up, Sunk Robotics placed 3rd worldwide in terms of robotics, and 9th overall including the marketing and advertising campaigns. A good run indeed. Our robot performed well, although reliability is our priority for next year’s attempt. A New Competition Although MATE ROV offers its well-known underwater competition, there are other events they host as well. This year, Matty Harris and I undertook a secondary challenge, known as the 2024 Ocean Exploration Video Challenge (OER) where teams must create custom Artificial Intelligence models that can be used to identify underwater species from a provided video.