Skip to main content
ARS Home » Plains Area » Lubbock, Texas » Cropping Systems Research Laboratory » Cotton Production and Processing Research » Research » Publications at this Location » Publication #379387

Research Project: Enhancing the Profitability and Sustainability of Upland Cotton, Cottonseed, and Agricultural Byproducts through Improvements in Pre-Ginning, Ginning, and Post-Ginning Processes

Location: Cotton Production and Processing Research

Title: Current and potential robotic applications to improve cotton production: Part 2

Author
item BARNES, EDWARD - Cotton, Inc
item MORGAN, GAYLON - Cotton, Inc
item HAKE, KATER - Cotton, Inc
item DEVINE, JON - Cotton, Inc
item KURTZ, RYAN - Cotton, Inc
item GRIFFIN, TERRY - Kansas State University
item IBENDAHL, GREGORY - Kansas State University
item SHARDA, AJAY - Kansas State University
item RAINS, GLEN - University Of Georgia
item SNIDER, JOHN - University Of Georgia
item BRUCE, AARON - University Of Georgia
item ERMANIS, ALESSANDRO - University Of Georgia
item AYRE, BRIAN - University Of North Texas
item MAJA, JOE - Clemson University
item DALY, DENNIS - Clemson University
item CHIU, CHRISTINA - Clemson University
item CUTULLE, MATTHEW - Clemson University
item BURCE, MARLOWE - Clemson University
item GRIFFIN, JAMES - Texas A&M University
item HARDIN, ROBERT - Texas A&M University
item KIMURA, EMI - Texas A&M University
item RAPER, TYSON - University Of Tennessee
item YOUNG, SIERRA - North Carolina State University
item FUE, KADEGHE - North Carolina State University
item Pelletier, Mathew
item Wanjura, John
item Holt, Gregory

Submitted to: National Cotton Council Beltwide Cotton Conference
Publication Type: Proceedings
Publication Acceptance Date: 10/13/2020
Publication Date: N/A
Citation: N/A

Interpretive Summary: Rapid advances in artificial intelligence have enabled the rapid development of commercial robots for self-driving robots for automobiles, vacuuming, lawn-mowing and weed control. This points to a future where robotic systems will play a larger role in agricultural production. Over the last two years, Cotton Incorporated has sponsored a small number of projects to look at the potential use of robots for cotton harvest and more recently, weed control and insect detection and mapping. These projects have collectively resulted in a robot capable of self-driving itself through the field using a combination of sensors. The small tractor uses camera inputs for guidance as it harvests cotton bolls. Part of the study includes an economic model that incorporates weather data to compare the value of multi-pass robotic harvesting to once-over harvesting operations. A comparison study from four locations was conducted to provide estimates for the economic model. The report also includes an initial progress report on the evaluation of a new mechanism for removing seed cotton from the plant and the development of an image library of various weeds significant to cotton. In addition to providing an overview of recent progress, this paper will also explore other areas of cotton production that could benefit from the potential use of robotic systems.

Technical Abstract: Rapid advances in robotic equipment have resulted in commercial self-driving robots for agricultural weeding. This points to a future where robotic systems will play a larger role in agricultural production. Over the last two years, Cotton Incorporated has sponsored a small number of projects to look at the potential use of robots for cotton harvest and more recently, weed control. These projects have collectively resulted in an autonomous robot capable of self-guided travel through the field; a small tractor using robotic vision that can autonomously harvest cotton bolls under defoliated conditions; a draft of an economic model that incorporates regional climate data to compare the value of a multi-pass robotic harvest system to once-over harvesters; and data from plots in four locations where cotton was hand-harvested twice per week to estimate the potential yield and quality benefits of frequent harvest events to provide estimates for the economic model. Initial progress has also been made in evaluating new mechanism for robotic removal of seed cotton from the plant, developing an image library of weed species significant to cotton, exploration of genetic manipulations that could facilitate robotic harvest, and concepts around material handling in the field. In addition to providing an overview of recent progress, this paper will also explore other areas of cotton production that could benefit from the use of robotic systems.