Honors College Capstone Experience/Thesis Projects

Department

Engineering

Document Type

Thesis

Abstract

According to the United Nations, the world population is expected to grow from its current 7 billion to 9.7 billion by the year 2050. During this time, global food demand is also expected to increase by between 59% and 98% due to the population increase, accompanied by an increasing demand for protein due to a rising standard of living throughout developing countries. [1] Meeting this increase in required food production using present agricultural practices would necessitate a similar increase in farmland; a resource which does not exist in abundance. Therefore, in order to meet growing food demands, new methods will need to be developed to increase the efficiency of farming, thereby increasing yield from the present land. One way in which this problem can be solved is through the usage of autonomous aerial systems to scout for problems which could potentially affect the crop yield – such as nutrient deficiency, water stress, or diseases. Once located, this data can be used to determine the proper treatment for the field to alleviate the problem. Through this process, resources can be reduced to the required minimum, while problems affecting the crop yield will still be corrected, allowing greater production with a lower amount of resources. This project on the application of Unmanned Aerial Vehicles (UAV’s) to the field of agriculture consisted of two phases. First, a study was conducted on the required background to define the problem statement and what solutions were available for this application. This consisted of first defining the operations within agriculture where UAV’s could be used to increase efficiency, and then the sensors, hardware, and software these operations would require. The remainder of the project consisted of evaluating the tools which could be utilized to develop such a solution. Primarily, the project focused on software tools – programming software, simulation environments, and machine learning algorithms – which could be utilized by future students to develop a functional hardware and software toolchain for the research of autonomous systems for agricultural applications. After analyzing these development solutions, a set of tools was selected which showed promise in the creation of a functional solution. It was demonstrated that the core functions required for a UAV-based agricultural solution – navigation, perception, and feature detection – could be implemented within these systems, implying that they could be integrated into a full solution. As the tools were selected to ensure the developed algorithms would be transferable to physical platforms, this additionally supports a physical system could also be developed. The present work is part of the Autonomous Systems Lab which belongs to the WKU Center for Energy Systems. The author hopes that this project contributes to the advancement of the curriculum within the engineering department and serves as a foundation for future students developing autonomous systems, perception, and applied artificial intelligence at WKU.

Advisor(s) or Committee Chair

Dr. Farhad Ashrafzadeh, Prof. Ali Buendia, Prof. Joel Lenoir

Disciplines

Agriculture | Computer Sciences | Electrical and Computer Engineering

Share

COinS