Thesis
DESIGN AND FIELD EVALUATION OF AN END EFFECTOR FOR ROBOTIC STRAWBERRY HARVESTING
Washington State University
Master of Science (MS), Washington State University
07/2024
DOI:
https://doi.org/10.7273/000007072
Abstract
As the world’s population continues to rise even with fertility rates dropping in recent years, the declining agricultural workforce will struggle to maintain production levels necessary to keep fresh produce in the average American’s kitchen at a reasonable price point. Strawberries grown within the U.S. are especially threatened by such stipulations, as cost of labor for such a delicate crop remains to be the bulk of total production costs. Autonomous systems within the agricultural sector have enormous potential to catalyze the labor and land expansions required to meet the demands of feeding an increasing population, as well as heavily reduce the amount of food waste experienced in open fields. Although there is emerging development towards robotic solutions within strawberry production, WSU-Tri Cities aims to improve such processes so that the efficiency of human workers can be emulated with ease. In collaboration with start-up company, Abberit, a modularized configuration is proposed and identified as a feasible solution to growers. The system consists of a parallel robot from Delta X and pneumatically powered end effector designed by WSU to intricately harvest strawberries by their stem via path finding
algorithms generated by Abberit. This thesis, however, focuses its attention towards optimization of the end effector design and validation of its harvesting capabilities with high speed actuation methods, as Abberit continues to develop their approach in strawberry localization. The presented end effector prototype was found to achieve high success rates of 94.74% in simulated environments and 100% within strawberry fields located at Farias Farms, even when tasked to harvest in the densely covered conditions of the late growing season. Utilizing an off-the-shelf robotic configuration the system’s workspace has been validated as adequate for harvesting in a typical two plant per row strawberry field, with the hardware itself being evaluated to harvest each strawberry in 2.8 – 3.8 seconds. This capability sets the stage for future enhancements, including the integration of Abberit’s machine vision processes such that the system will identify and pick each strawberry within 5 seconds.
Metrics
2 File views/ downloads
63 Record Views
Details
- Title
- DESIGN AND FIELD EVALUATION OF AN END EFFECTOR FOR ROBOTIC STRAWBERRY HARVESTING
- Creators
- Ezekyel Zebedee Ochoa
- Contributors
- Changki Mo (Chair)Joseph Ianelli (Committee Member)John Miller (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- School of Engineering and Applied Sciences (TRIC)
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 65
- Identifiers
- 99901152214801842
- Language
- English
- Resource Type
- Thesis