Seyed Hassan Zabihifar

Papers

Total Citations

H-Index

About

Seyed Hassan Zabihifar is a robotics researcher specializing in computer vision and robotic manipulation, with a particular focus on keypoint-based object detection and grasping. His work addresses the critical challenge of enabling robots to perceive and interact with objects in unstructured environments. Zabihifar’s most impactful contribution is the “Unreal mask” framework, which introduces a one-shot, multi-object class-based pose estimation method for robotic manipulation using keypoints trained on synthetic datasets. This approach, cited 8 times, significantly reduces the need for real-world annotated data, making robotic grasping more scalable and adaptable. In his earlier work, “Object Grasping and Manipulating According to User-Defined Method Using Key-Points” (3 citations), Zabihifar developed a system that allows robots to grasp objects at user-specified points, regardless of the object’s orientation or position. This innovation enables more intuitive human-robot interaction by letting users define custom grasping strategies. Zabihifar’s research bridges the gap between synthetic training data and real-world robotic applications, advancing the field of autonomous manipulation. His contributions are particularly valuable for applications in manufacturing, logistics, and service robotics, where flexible and precise object handling is essential.