Plant Specific Direct Chemical Application Field Robot

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.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Agricultural Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Jeon, Hong Young

Contributors dc:contributor

• Lei F. Tian

• Engineering, Robotics

Language dc:language

eng

Identifier

(MiAaPQ)AAI3337809

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/86075