Abstract
This dissertation focuses on trajectory tracking for a 4 degree-of-freedom (4-DOF) robot arm manipulator, harnessing the capabilities of neuro-fuzzy controller. The research journey begins by exploring various tracking models; including kinematics, torques and velocities. Subsequently, it narrows its focus to trajectory tracking with torques, leading to the implementation of the controller. This implementation undergoes an extensive learning process that includes identifying and refining fuzzy inference system (FIS) parameters. This critical phase makes use of a training dataset derived from a finely tuned PID model that incorporates H-infinity control techniques. Once trained, the neuro-fuzzy controller equips the robot with the essential knowledge and adaptability necessary for precise trajectory tracking. Through a series of meticulous simulations, the study effectively displays the controller's prowess in accurately navigating and adhering to predefined reference trajectories. Nevertheless, the practical application of robotics often introduces physical disturbances and uncertainties. In response to these challenges, the dissertation underscores the imperative need for a controller capable of effectively mitigating these disruptions. The proposed neuro-fuzzy controller emerges as a versatile solution, demonstrating its adaptability to a wide array of predefined reference trajectories and highlighting robust performance, even in the presence of disturbances. The significance of this research lies in its substantial contributions towards the field of robotics. It introduces an advanced trajectory-tracking solution that significantly enhances accuracy and adaptability, effectively bridging the gap between theoretical models and practical robotic control. Furthermore, the dissertation suggests the incorporation of optimization techniques further elevates the controller's performance, rendering it a valuable tool for addressing dynamic real-world challenges. In terms of prospects, this research proposes the integration of machine learning techniques to bolster adaptability and the exploration of optimization algorithms for precise parameter tuning. Additionally, it suggests the evaluation of the controller's performance across diverse robot types, expanding its applicability throughout the diverse landscape of the robotics industry. In summation, this dissertation heralds a new era in the trajectory tracking arena, presenting a versatile and robust control solution with the potential to revolutionize robotics applications.
Keywords
Robot, Neoro-Fuzzy, Trajectory Tracking, Autonomous, Controller Design
Citations
IRE Journals:
Emmanuel Unanaowo Eno
"Trajectory Tracking Using Neuro-Fuzzy Controller" Iconic Research And Engineering Journals Volume 8 Issue 6 2024 Page 851-861
IEEE:
Emmanuel Unanaowo Eno
"Trajectory Tracking Using Neuro-Fuzzy Controller" Iconic Research And Engineering Journals, 8(6)
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 7:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12