OceanAI

A robotic and software orientated ocean development.
See the video »

Table of Contents

1. About The Project
2. Getting Started
   • AUV Software
   • Graphical User Interface
3. License
4. Contact

About the Project

This project aims at creating an autonomous underwater vehicle (AUV) that utilizes cameras, sensors, a microcontroller, and GPS to categorize, identify, and map underwater trash. Detection of litter will be performed with a deep learning model - optimized to run on a microcontroller - allowing for cheap and power-efficient inference of underwater footage.

Main components of the project include:

• AUV Control Board
• AUV Software
• AUV CAD Model
• Deep Learning Model

Getting Started

AUV Software

VSCode and PlatformIO are used to build and upload the software to the AUV.

1. Install VSCode and the PlatformIO extension.
2. Clone the repository.

git clone https://github.com/daniel360kim/OceanAI.git

3. Go to PlatformIO home and go to the 'Projects' tab.
4. Click 'Add Existing Project' and select the software/sub_driver folder.
5. Make sure you have the Teensy 4.1 core installed.
6. Connect the AUV through USB and click the 'Upload' button.
   
   

Graphical User Interface

The GUI is built using ElectricUI. ElectricUI requires:

• Node.js
• Yarn

1. Install Node.js, available from their website.
2. Install Yarn.

npm install -g yarn

3. Install ElectricUI, available here
4. Check everything installed and can be found in your PATH

arc info

5. Clone the repository if you haven't already.

git clone https://github.com/daniel360kim/OceanAI.git

6. Open the GUI project with ElectricUI. software/auv_gui
7. Run the GUI.

arc start

License

Distributed under the MIT License. See LICENSE for more information.

Contact

• Daniel Kim - nmrs.thrust@gmail.com - YouTube - Instagram: @us_rockets
• Project Link: https://github.com/daniel360kim/OceanAI