Ming-Hsiu Lee
Papers
3
Total Citations
8
H-Index
2
About
Ming-Hsiu Lee is a robotics researcher whose work focuses on ensuring safety in human-robot collaboration through advanced computational geometry and implicit neural representations. Lee’s primary research areas include collision detection, swept volume reconstruction, and safe human-robot interaction in automated manufacturing environments. Their major contribution lies in developing novel methods for representing robot swept volumes using signed distance functions and implicit neural networks, enabling more reliable and accurate collision detection without requiring explicit geometric models. Lee’s most cited paper, “Single Swept Volume Reconstruction by Signed Distance Function Learning” (2022, 4 citations), introduced a feasibility study using implicit geometric regularization to identify safe protective spaces for operators. This was followed by “Fast Collision Detection for Robot Manipulator Path” (2023, 3 citations), which extended the approach to multiple swept volumes, and “Reliable and Accurate Implicit Neural Representation of Multiple Swept Volumes” (2024, 1 citation), which refined the technique for practical human-robot interaction scenarios. Lee’s work directly addresses critical safety challenges in collaborative robotics, offering a path toward more intuitive and computationally efficient collision avoidance systems that could help enable safer, more flexible factory floors where humans and robots work side by side.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3