Trajectory Tracking Control of Mobile Robot Using Adaptive Neuro - Fuzzy Inference System (ANFIS)
No Thumbnail Available
Date
2018-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
In autonomous trajectory tracking navigation of mobile robots in the static environment is a source
of problems. Because it is not possible to model all the possible conditions, the key point in the
robot control is to design a system that is adaptable to different conditions and robust in static
environments.
The subject of this thesis primarily addresses the trajectory tracking control of a differential drive
mobile robot based on Adaptive Neuro-Fuzzy Inference System (ANFIS) controller. ANFIS has
two layers like input fuzzy layer and the following neural network layer. The hybrid system
combines the advantages of fuzzy logic, which deal with explicit knowledge that can be explained
and understood, then also neural network, which deal with implicit knowledge, which can be
acquired by learning. The kinematic modeling is developed for non-holonomic wheeled mobile
robot systems. A learning algorithm based on neural network technique is developed to tune the
parameters of fuzzy membership functions, which smooth the trajectory tracking with minimal
error for the given path. Using the developed ANFIS controller, the mobile robots can be able to
track the trajectory, and reach the target successfully in cluttered environments. The control
objective has been to make the mobile robot actuator traces desired trajectory using ANFIS based
controller. This has been done through the simulation of the robot model using the software
MATLAB/Simulink version R2017a for a Pioneer 3-DX mobile robot.
Description
Keywords
Adaptive Neuro - Fuzzy Inference System (ANFIS), Mobile Robot, Control, Trajectory Tracking