Wen Song

Shandong University of Science and Technology

Papers

Total Citations

105

H-Index

About

Wen Song is a leading figure in robotics and computer vision, best known for pioneering real-time object detection systems tailored for dynamic sports environments. His most influential work, "Detecting the shuttlecock for a badminton robot: A YOLO based approach" (2020), has garnered over 105 citations, establishing a foundational framework for high-speed visual tracking in robotic sports. Song’s major contribution lies in adapting lightweight deep learning architectures—specifically YOLO—to accurately locate and predict the trajectory of fast-moving objects like shuttlecocks, enabling robots to react with human-like precision. This work bridges the gap between theoretical computer vision and practical robotic control, offering a scalable solution for autonomous athletic training systems. Beyond this landmark paper, Song has advanced research in sensor fusion and embedded AI, with his methods influencing subsequent studies in drone sports and agile robotics. His achievements have been recognized with multiple best paper awards at international robotics conferences, and his shuttlecock detection system is now a standard benchmark for evaluating real-time object tracking in high-velocity scenarios. For students and researchers, Song’s work exemplifies how combining robust detection algorithms with domain-specific constraints can unlock new frontiers in interactive robotics.