Hagar Marzouk

Papers

Total Citations

H-Index

About

Hagar Marzouk is a robotics researcher whose work bridges the gap between classical kinematics and modern deep learning. Her primary research focuses on inverse kinematics for high-degree-of-freedom manipulators, with a particular emphasis on 7-DOF robotic arms. Her most-cited paper, "Solving Inverse Kinematics of a 7-DOF Manipulator Using Convolutional Neural Network" (2020, 14 citations), introduces a novel approach that leverages convolutional neural networks to efficiently compute joint configurations for redundant manipulators—a notoriously complex problem due to the multiple possible solutions. This work demonstrates how deep learning can replace traditional iterative methods, offering faster and more accurate solutions for real-time robotic control. Marzouk's contributions are particularly valuable in applications requiring precise and adaptive motion planning, such as surgical robotics and industrial automation. Her research has garnered attention within the robotics community, with her 2020 paper serving as a foundational reference for researchers exploring neural network-based kinematic solvers. By combining theoretical rigor with practical implementation, Marzouk continues to advance the field of robotic manipulation, making her work essential reading for students and engineers seeking to integrate AI into robotic systems.