Term of Award

Fall 2022

Degree Name

Master of Science, Electrical Engineering

Document Type and Release Option

Thesis (restricted to Georgia Southern)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


Department of Electrical and Computer Engineering

Committee Chair

Fernando Rios-Gutierrez

Committee Member 1

Rocio Alba-Flores

Committee Member 2

Mohammad A. Ahad


This research explores the use of a hybrid system comprising two artificial intelligence techniques namely fuzzy logic and neural networks to create an intelligent indoor navigation system for robots. The proposed methodology gives insight into the design and simulation of the hybrid intelligent controller based on two critical robot behaviors; target reaching and obstacle avoidance for the effective reactive navigation of a differential robot to potentially reduce the limitations involved in conventional path planning for robots. For successful navigation to be established, an autonomous robot must overcome the difficulties of path planning, obstacle avoidance and goal reaching. The ability to create a controller that aids intelligent movement and efficient decision-making skills enables a significant increase in autonomy and overall efficiency of the robot. As a result, the proposed hybrid system is introduced and used to provide the robot with intelligent navigation commands as it moves from one place to the other while avoiding obstacles in the process. Two systems are developed to solve the problem of target reaching and obstacle avoidance. The first system for target reaching makes use of the target location and the current robot location to determine the distance and angle the robot should go and uses the fuzzy system and trained neural network to increase the efficiency at which the robot moves and stops. The second system designed for obstacle avoidance includes left and right sensors to allow the robot to read its surroundings more accurately and make better decisions as it navigates the indoor environment. By combining these artificial intelligence techniques together, the complexity involved in creating fuzzy systems is negated with the use of a trained neural network and vice versa resulting in an optimized performance of the system.

Research Data and Supplementary Material


Available for download on Friday, November 12, 2027