Papers
1
Total Citations
2
H-Index
1
About
Minhwan Ko is a robotics researcher whose work centers on advancing autonomous assembly through sim-to-real adaptation and precision manipulation. His most notable contribution is the development of **PolyFit**, a framework that redefines the classic peg-in-hole assembly problem by enabling robots to handle unseen polygonal shapes with high reliability. Traditional approaches often fail due to sensor noise and mechanical misalignments, but Ko’s method leverages simulation-trained policies that transfer seamlessly to real-world tasks, dramatically reducing insertion failures and jamming. This work, published in 2024 and already garnering 2 citations, marks a paradigm shift from shape-specific solutions to generalizable, adaptive assembly. Ko’s research bridges the gap between simulation and reality, offering scalable solutions for manufacturing and automation. His achievements highlight a deep commitment to solving fundamental robotics challenges, making him a rising figure in manipulation and reinforcement learning. For students and researchers, Ko’s work exemplifies how rigorous sim-to-real strategies can unlock robust, real-world robotic capabilities.
Research Focus
Key Achievements
Top Papers
- 1