Semester of Graduation

Fall 2023

Degree

Master of Science in Mechanical Engineering (MSME)

Department

Mechanical & Industrial Engineering

Document Type

Thesis

Abstract

This thesis presents the development and testing of Bruce, a low-cost hybrid Remote Operated Vehicle (ROV) / Autonomous Underwater Vehicle (AUV) system for the optical survey of marine archaeological sites, as well as a novel sonar image augmentation strategy for semantic segmentation of shipwrecks. This approach takes side-scan sonar and bathymetry data collected using an EdgeTech 2205 AUV sensor integrated with an Harris Iver3, and generates augmented image data to be used for the semantic segmentation of shipwrecks. It is shown that, due to the feature enhancement capabilities of the proposed shipwreck detection strategy, correctly identified areas have a 15% higher mean accuracy than using sonar imagery alone. Furthermore, mean intersection over union shows an increase of 9.5% using the augmented images. The hybrid ROV/AUV is then used to autonomously collect optical images of the identified shipwrecks. Stereo images are collected using custom camera systems that incorporate the Zed 2i and Zed Mini AI machine vision cameras. The system uses coverage path plans for the surveys generated using two different planners. The performance of the system is validated using tests in a controlled environment and at real-world shipwreck sites. The results from the recorded vehicle odometry show that the system can autonomously track the paths provided to it.

Date

8-14-2023

Committee Chair

Barbalata, Corina

Download

Share

COinS