Qingyun Sun
Papers
1
Total Citations
6
H-Index
1
About
Qingyun Sun is a leading researcher in robotics and computer vision, whose work tackles one of the field’s most persistent challenges: bridging the simulation-to-reality (sim-real) gap. Her research focuses on developing domain-invariant representations that enable robots to transfer skills learned in simulation to the physical world with minimal performance loss. In her highly cited 2020 paper, “How to Close Sim-Real Gap? Transfer with Segmentation!”, Sun proposed a novel approach using segmentation as the interface between perception and control. By identifying two distinct sources of sim-real discrepancy—dynamics and visual differences—she demonstrated that segmentation serves as a robust, domain-invariant state representation, effectively decoupling perception from control. This work has garnered 6 citations and is recognized for its elegant solution to a fundamental problem in robotic learning. Sun’s contributions have significant implications for scalable robot training, reducing the need for expensive real-world data collection. Her innovative thinking continues to inspire new directions in sim-to-real transfer, making her a rising voice in the robotics community.
Research Focus
Key Achievements
Top Papers
- 1How to Close Sim-Real Gap? Transfer with Segmentation!6 citations · 2020