Amir Hossein Dezhdar
Papers
1
Total Citations
2
H-Index
1
About
Amir Hossein Dezhdar is a robotics researcher focused on the intersection of reinforcement learning and robotic control, with particular emphasis on rehabilitation applications. His work centers on developing intelligent compensation methods that enable robotic systems to achieve precise, smooth movements essential for human-robot interaction. His most cited paper, "PPO and SAC Reinforcement Learning Based Reference Compensation" (2024), introduces a novel approach using Proximal Policy Optimization and Soft Actor-Critic algorithms to enhance the accuracy of UR5e robotic manipulators in reaching fixed points and tracking predefined trajectories. This research addresses critical challenges in rehabilitation robotics, where precise and adaptive motion control is paramount for patient safety and therapeutic efficacy. With 2 citations to his name, Dezhdar's contributions represent an emerging yet promising direction in applying state-of-the-art reinforcement learning techniques to real-world robotic systems. His work demonstrates how modern AI methods can bridge the gap between theoretical control algorithms and practical robotic applications, particularly in sensitive domains like medical rehabilitation where smooth, adaptive, and reliable motion is essential.
Research Focus
Key Achievements
Top Papers
- 1PPO and SAC Reinforcement Learning Based Reference Compensation2 citations · 2024