Loading...
Intelligent Control of Cable-Driven Parallel Robot for Rehabilitation
Khattab, Omar
Khattab, Omar
Date
2025-08
Author
Advisor
Type
Thesis
Degree
Citations
Altmetric:
Files
35.232-2025.52a Omar Khattab.pdf
Adobe PDF, 4.62 MB
- Embargoed until 2027-01-26
Description
A Master of Science thesis in Mechatronics Engineering by Omar Khattab entitled, “Intelligent Control of Cable-Driven Parallel Robot for Rehabilitation”, submitted in August 2025. Thesis advisor is Dr. Lotfi Romdhane and thesis co-advisor is Dr. Mohammad Jaradat. Soft copy is available (Thesis, Completion Certificate, Approval Signatures, and AUS Archives Consent Form).
Abstract
This thesis aims to improve the accuracy and effectiveness of cable-driven parallel robots (CDPR) in medical rehabilitation by employing advanced kinematic solutions and neural network modelling. The research primarily focuses on three key areas: the geometric solution of inverse kinematics, the use of intelligent methods to solve forward kinematics, and the enhancement of the CDPR design to incorporate rotational movement capabilities. The first step involves a comprehensive analysis of the inverse kinematics, allowing for precise determination of cable lengths to achieve specific poses and orientations of the robot's end-effector. This is crucial for ensuring accurate and controlled movements, which are essential in the context of rehabilitation exercises. Following that an integration of artificial neural networks (ANN) to solve the forward kinematics problem, significantly improving the computational efficiency and accuracy of the robot's movement predictions. The research also explores modifications to the hardware design of the CDPR, enabling rotational movements that increase the range of possible rehabilitation exercises. These enhancements are expected to significantly improve the versatility and efficacy of the robot in targeting different muscle groups in the upper limb and the neck region. Preliminary results demonstrate that the proposed neural network model performs well in predicting the robot's position with high accuracy, particularly in the x and y coordinates. However, there are observed challenges in accurately predicting the θ (rotational) component, suggesting areas for further refinement. Future work will involve additional experimentation to validate these findings and further enhance the CDPR's performance, particularly in the context of complex, multi-dimensional trajectories. This thesis outlines the necessary components, including literature review, design methodology, and future research directions, required for the successful advancement of CDPR technology in rehabilitation applications.