Yong Hyeon Kim
Papers
2
Total Citations
6
H-Index
2
About
Yong Hyeon Kim is a robotics researcher focused on advancing robotic manipulation, particularly in the challenging domain of bin-picking and grasping in cluttered environments. His work bridges deep learning and analytical methods to enhance robotic dexterity. In his highly cited paper "CoAS-Net: Context-Aware Suction Network With a Large-Scale Domain Randomized Synthetic Dataset" (2023, 4 citations), Kim introduced a novel context-aware approach to suction-based grasping, leveraging a large-scale synthetic dataset generated through domain randomization to improve real-world performance. Building on this, his 2024 work "Enhancing Antipodal Grasping Modalities in Complex Environments Through Learning and Analytical Fusion" (2 citations) presents a hybrid method that combines deep learning with analytical reasoning to generate robust antipodal grasps in highly cluttered scenes. This fusion approach allows robots to better handle the variability and occlusion typical of industrial and household environments. Kim’s contributions are particularly notable for their practical impact on pick-and-place systems used in assembly, packaging, and sorting. By addressing one of robotics’ most persistent challenges—reliable grasping in unstructured settings—his research is helping to bridge the gap between simulation and real-world application.
Research Focus
Key Achievements
Top Papers
- 1
- 2