Theses and Dissertations
ORCID
0009-0005-4010-7771
Advisor
Gharakhani, Hussein
Committee Member
Lowe, John Wesley
Committee Member
Senyurek, Volkan
Date of Degree
8-12-2026
Original embargo terms
Visible MSU Only 6 months
Document Type
Graduate Thesis - Campus Access Only
Major
Biosystems Engineering
Degree Name
Master of Science (M.S.)
College
James Worth Bagley College of Engineering
Department
Department of Agricultural and Biological Engineering
Abstract
Plastic contamination in cotton fields is a major economic issue. To address it, a collaborative UAV-UGV system is proposed, with a focus on UGV in this research. A modified AMIGA rover was used as the platform. A planar 3-DoF robotic arm was developed, capable of reaching under canopy areas. Additionally, a two-finger shape- and size-adaptable end-effector was developed and mounted on the robotic arm. A control algorithm was developed to manipulate the arm based on a plastic’s location on the canopy. Aerial and terrestrial RGB images were collected to train object detection models, achieving a recall of 80.2% and 90.0%, respectively. The terrestrial-based model was deployed into the UGV. An OAK-D camera mounted on the UGV for localization. The robot was tested in a cotton field where plastic contaminants were placed at various locations within the canopy. The system demonstrated reliable performance, with a retrieval success rate of 73%.
Sponsorship (Optional)
Cotton Incorporated
Recommended Citation
Rahman, Md Sazedur, "Vision-based aerial-terrestrial detection and UGV-mounted robotic manipulator to retrieve plastic contaminants in cotton fields" (2026). Theses and Dissertations. 7095.
https://scholarsjunction.msstate.edu/td/7095
