Yeyu Fu

Papers

Total Citations

H-Index

About

Yeyu Fu is a robotics researcher whose work focuses on bridging the gap between computer vision and robotic manipulation, particularly in industrial automation. Their key research areas include RGB-D perception, instance segmentation, and grasp planning, with a special emphasis on suction-based robotic grasping—a method prized for its stability and reliability in picking objects of varying shapes and sizes. Fu’s most notable contribution, "RGB-D Instance Segmentation-based Suction Point Detection for Grasping" (2022), addresses a critical challenge in industrial robotics: evaluating optimal suction positions on object surfaces. By integrating deep learning with geometric reasoning, Fu’s approach moves beyond traditional two-stage methods, enabling robots to adapt to diverse and irregular objects in real-time. This work has garnered 4 citations and is foundational for developing more autonomous and flexible manufacturing systems. Fu’s research is particularly impactful for students and engineers seeking to advance robotic dexterity, offering a practical framework that combines semantic understanding with physical interaction. Their contributions are paving the way for more intelligent, vision-driven robotic systems in logistics and assembly lines.