Hsuan-Kung Yang

Papers

Total Citations

H-Index

About

Hsuan-Kung Yang is a leading researcher in the intersection of computer vision and robotics, with a primary focus on bridging the reality gap between simulated and physical environments. His seminal work, "Virtual-to-Real: Learning to Control in Visual Semantic Segmentation" (2018), has garnered over 69 citations, establishing him as a key figure in sim-to-real transfer learning. Yang's major contribution lies in developing frameworks that enable robots to learn control policies using synthetic visual data, thereby eliminating the need for costly and dangerous real-world data collection. This approach has profound implications for fragile robotic systems and autonomous navigation, where safety and efficiency are paramount. By leveraging visual semantic segmentation as a bridge between virtual and real domains, Yang has demonstrated how agents can effectively generalize from simulation to physical deployment. His research addresses a critical bottleneck in robot learning, making autonomous systems more accessible and scalable. Yang's work continues to influence the fields of embodied AI and domain adaptation, inspiring new methods for training robust perception and control systems without extensive real-world interaction.