Autonomous Underwater Vehicle: Electronics and Software Implementation of the Proton AUV

TL;DR

This paper details the electronics and software systems of the Proton AUV, including hardware integration and a CNN-based object detection algorithm, with implementation and tuning on Odroid Xu4 hardware.

Contribution

It presents a comprehensive integration of electronics and a CNN-based object detection software for an autonomous underwater vehicle, including hyperparameter tuning and maneuvering algorithms.

Findings

Successful implementation of CNN for object detection in AUV

Effective communication between hardware components established

Maneuvering algorithms tested via simulation

Abstract

The paper deals with the software and the electronics unit for an autonomous underwater vehicle. The implementation in the electronics unit is the connection and communication between SBC, pixhawk controller and other sensory hardware and actuators. The major implementation of the software unit is the algorithm for object detection based on Convolutional Neural Network (CNN) and its models. The Hyperparameters were tuned according to Odroid Xu4 for various models. The maneuvering algorithm uses the MAVLink protocol of the ArduSub project for movement and its simulation.