Off-campus Michigan Tech users: To download campus access theses or dissertations, please use the following button to log in with your Michigan Tech ID and password: log in to proxy server

Non-Michigan Tech users: Please talk to your librarian about requesting this thesis or dissertation through interlibrary loan.

Date of Award

2025

Document Type

Campus Access Master's Report

Degree Name

Master of Science in Mechatronics (MS)

Administrative Home Department

Department of Applied Computing

Advisor 1

Amna Mazen

Committee Member 1

Ashraf Saleem

Committee Member 2

Jung Yun Bae

Abstract

Oil spills represent a significant environmental and economic hazard to marine and coastal ecosystems. Rapid detection and containment are vital, as even short delays can lead to spill expansion, causing ecological damage and increasing cleanup costs. This work presents the design and development of a vision-based autonomous UAV platform capable of real-time oil spill sample collection and autonomous recovery, addressing the urgent need for rapid, unmanned incident response.

The proposed platform incorporates autonomous UAV navigation to target areas, performs simulated sampling, and executes precision landing using fiducial AprilTags. The AprilTag2 package, integrated within the Robot Operating System (ROS) framework, enables fiducial detection using image data from an Intel RealSense D435 camera mounted on the UAV. A custom landing algorithm computes the tag’s centroid as the target landing point, transforms its coordinates from the camera to the robot reference frame, and guides the UAV to land precisely via a PID-based controller.

Simulation and Real-world experiments validated the full operational cycle: the UAV autonomously takes off from a platform, navigates to a waypoint representing a simulated spill site (marked by an AprilTag), descends to a predetermined altitude for mock sampling, and returns to the home platform for precision landing on a second AprilTag (representing the oil spill location).

Share

COinS