Plant Specific Direct Chemical Application Field Robot
Jeon, Hong Young
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/86075
Description
Title
Plant Specific Direct Chemical Application Field Robot
Author(s)
Jeon, Hong Young
Issue Date
2008
Doctoral Committee Chair(s)
Lei F. Tian
Department of Study
Agricultural Engineering
Discipline
Agricultural Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Engineering, Robotics
Language
eng
Abstract
This study addressed the issues in the conventional chemical application such as chemical drift and application inaccuracy via developing a plant specific direct application field robot. The robot was designed to autonomously detect plants, to identify weeds and to control weeds in the field. The developed robot was equipped with a stereovision with processing algorithms to detect and identify individual weeds in the field image and the custom designed end effector with a robotic arm to carry out plant specific direct application. The developed vision system with the algorithms was dealt with unpredictable outdoor illuminations to sense plants in the field via a series of image processing. The developed algorithm processed field images with the processing error less than 3 % in terms of identifying individual plants, and the algorithm identified 92.5 % and 95.1 % of weeds in the image via trained artificial neural network. The direct application end effector with the arm executed the direct application via cutting weed stem and wiping chemical on the weed surface. The indoor experiment resulted that 90.9 % of the weed treated by the end effector had herbicide symptoms after 6 day from the application. The plant specific direct chemical application field robot was developed by utilizing the vision system and the end effector with the arm to a field robot platform. The potential of developed robot was examined by testing the robot in the field. While testing in the field, the robot autonomously controlled 63.6 % of weeds, and required 12.923 seconds to control a weed from detection to application inspection for reapplication via machine vision.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
