Papers
1
Total Citations
7
H-Index
1
About
Seojung Min is a robotics researcher advancing tactile perception for dexterous manipulation. Her work centers on bridging the sim-to-real gap for tactile sensing, enabling robots to classify objects and estimate their poses through touch alone—a critical capability for delicate, in-hand manipulation tasks. Her most-cited paper, "In-Hand Object Classification and Pose Estimation With Sim-to-Real Tactile Transfer for Robotic Manipulation" (2023, 7 citations), tackles the challenge of generating rich tactile data efficiently by transferring simulated tactile signals to real-world robotic systems. This approach allows robots to explore and recognize objects without extensive physical data collection, a breakthrough for adaptive grasping. Min’s contributions address a fundamental bottleneck in robotic manipulation: the difficulty of obtaining high-quality tactile data for training. Her work has immediate implications for industrial automation, assistive robotics, and any domain requiring precise, gentle handling of objects. By demonstrating that simulated touch can effectively train real-world perception, she opens new pathways for scalable, robust robotic interaction.
Research Focus
Key Achievements
Top Papers
- 1