Kun Du
Papers
1
Total Citations
10
H-Index
1
About
Kun Du is a researcher whose work sits at the intersection of computer vision and robotics, with a particular focus on advancing object detection for robotic manipulation. His most-cited paper, "A Multi-Object Grasping Detection Based on the Improvement of YOLOv3 Algorithm" (2020), has garnered 10 citations, demonstrating his contribution to applying state-of-the-art deep learning to practical robotic tasks. In this work, Du improved the YOLOv3 architecture to enable multi-object grasping detection, tackling the critical challenge of accurately detecting both the position and pose of objects in cluttered environments—a key requirement for autonomous robotic systems. By refining the network structure, he proposed a deep learning model that bridges the gap between high-performance object detection and real-world grasping applications. Du’s research is notable for its practical orientation, directly addressing the needs of industrial and service robotics. His work exemplifies how algorithmic improvements in deep learning can be translated into tangible advances in robotic perception and manipulation, making him a contributor to the growing field of intelligent automation.
Research Focus
Key Achievements
Top Papers
- 1