Term of Award
Master of Science in Applied Engineering (M.S.A.E.)
Document Type and Release Option
Thesis (open access)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department of Mechanical Engineering
M. Rocio Alba-Flores
Committee Member 1
Committee Member 2
Committee Member 3
Committee Member 3 Email
This research compares the behavior of three robot navigation controllers namely: PID, Artificial Neural Networks (ANN), and Fuzzy Logic (FL), that are used to control the same autonomous mobile robot platform navigating a real unknown indoor environment that contains simple geometric-shaped static objects to reach a goal in an unspecified location. In particular, the study presents and compares the design, simulation, hardware implementation, and testing of these controllers. The first controller is a traditional linear PID controller, and the other two are intelligent non-linear controllers, one using Artificial Neural Networks and the other using Fuzzy Logic Techniques. Each controller is simulated first in MATLAB® using the Simulink Toolbox. Later the controllers are implemented using Quartus ll® software and finally the hardware design of each controller is implemented and downloaded to a Field-Programmable Gate Array (FPGA) card which is mounted onto the mobile robot platform. The response of each controller was tested in the same physical testing environment using a maze that the robot should navigate avoiding obstacles and reaching the desired goal. To evaluate the controllers' behavior each trial run is graded with a standardized rubric based on the controllers' ability to react to situations presented within the trial run. The results of both the MATLAB® simulation and FPGA implementation show the two intelligent controllers, ANN and FL, outperformed the PID controller. The ANN controller was marginally superior to the FL controller in overall navigation and intelligence.
Jeanniton, Christopher James, "Design and Development of Intelligent Navigation Control Systems for Autonomous Robots that Uses Neural Networks and Fuzzy Logic Techniques and Fpga For Its Implementation" (2010). Electronic Theses and Dissertations. 770.
Research Data and Supplementary Material