Autonomous Underwater Vehicle Image Processing and Control
School Name
South Carolina Governor's School for Science and Mathematics
Grade Level
12th Grade
Presentation Topic
Engineering
Presentation Type
Mentored
Abstract
Despite making up 75 percent of the earth’s surface, only 5 percent of the ocean has been explored. Autonomous Underwater Vehicles (AUVs) are valuable tools that help us expand our knowledge of the ocean as well as the Earth as a whole. While coding an undersea robot for autonomous control is far from new, the challenge presented to us encompassed the basics of how AUVs operate in the real world. The challenge combined image processing, vehicle control, and mission reconstruction in order to aid the AUV in successfully navigating an underwater field of red and green buoys, similar to those used by the US Coast Guard. Our team worked remotely due to Covid-19 and our code was uploaded and tested on AUVs in the MIT pool. The AUV was able to successfully navigate one out of four buoys, but due to time constraints there was no time for further tweaking of the code to make the AUV run more smoothly. Despite all this, the AUV was successful in all areas of image processing and control similar to how AUVs navigate the ocean in real missions.
Recommended Citation
Hagerty, Jasmine, "Autonomous Underwater Vehicle Image Processing and Control" (2022). South Carolina Junior Academy of Science. 141.
https://scholarexchange.furman.edu/scjas/2022/all/141
Location
HSS 113
Start Date
4-2-2022 10:00 AM
Presentation Format
Oral Only
Group Project
No
Autonomous Underwater Vehicle Image Processing and Control
HSS 113
Despite making up 75 percent of the earth’s surface, only 5 percent of the ocean has been explored. Autonomous Underwater Vehicles (AUVs) are valuable tools that help us expand our knowledge of the ocean as well as the Earth as a whole. While coding an undersea robot for autonomous control is far from new, the challenge presented to us encompassed the basics of how AUVs operate in the real world. The challenge combined image processing, vehicle control, and mission reconstruction in order to aid the AUV in successfully navigating an underwater field of red and green buoys, similar to those used by the US Coast Guard. Our team worked remotely due to Covid-19 and our code was uploaded and tested on AUVs in the MIT pool. The AUV was able to successfully navigate one out of four buoys, but due to time constraints there was no time for further tweaking of the code to make the AUV run more smoothly. Despite all this, the AUV was successful in all areas of image processing and control similar to how AUVs navigate the ocean in real missions.
