Michigan Technological University
A VISION BASED AUTONOMOUS UAV REALTIME OIL SPILL SAMPLING
Abstract
dc:description.abstractOil 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).
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Mechatronics (MS)
- Level thesis:degree_level
- Campus Access Master's Report
- Discipline thesis:degree_discipline
- Department of Applied Computing
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Mateyaunga, Innocent
- Committee members dc:contributor.committeemember
-
- Ashraf Saleem
- Jung Yun Bae
- Contributors dc:contributor
-
- Amna Mazen
Subjects
dc:subject × 5Identifiers
dc:identifier.*- Identifier
- https://digitalcommons.mtu.edu/etdr/2009