Cheol-Hui Min
Papers
2
Total Citations
6
H-Index
2
About
Cheol-Hui Min is a robotics researcher specializing in deep learning-driven manipulation and object grasping. His work focuses on two critical challenges in modern robotics: generating high-quality synthetic training data for object recognition, and developing efficient reinforcement learning strategies for multi-degree-of-freedom manipulators. Min’s 2018 paper on bin picking systems introduced an innovative approach to automated synthetic dataset generation for deep learning-based object recognition, enabling robots to accurately identify and grasp objects in cluttered environments—a fundamental capability for industrial automation. His 2019 work on demonstration-guided goal strategies addressed the notorious difficulty of reward shaping in deep reinforcement learning for 3D manipulation, proposing a method that reduces the need for laborious manual reward function optimization. While his citation counts (4 and 2, respectively) reflect the early-stage nature of this research, Min’s contributions are technically significant, tackling practical bottlenecks that limit the deployment of intelligent robotic systems. His work sits at the intersection of computer vision, deep reinforcement learning, and robotic manipulation, offering solutions that make robot learning more data-efficient and less dependent on expert engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2End-to-end robot manipulation using demonstration-guided goal strategie2 citations · 2019