Chae Young Lim

Seoul National University, Michigan State University

Papers

Total Citations

H-Index

About

Chae Young Lim is a researcher whose work lies at the intersection of robotics, computer vision, and statistical modeling, with a particular focus on appearance-based localization for mobile robots. His major contributions center on developing robust self-navigation techniques that allow robots to estimate their position by integrating visual information from omnidirectional cameras with kinematic data. Lim pioneered the use of Group LASSO regression—a sophisticated statistical method that selects relevant visual features while suppressing noise—combined with the Extended Kalman Filter (EKF) to improve localization accuracy in real-world environments. His 2018 paper on this approach has garnered 6 citations, while his foundational 2015 indoor experiment paper has received 5 citations, establishing a solid foundation for subsequent work in the field. By addressing the challenge of how robots can navigate using only visual appearance rather than expensive sensors or pre-mapped landmarks, Lim’s research offers a cost-effective, scalable solution for autonomous vehicle and mobile robot navigation. His work is particularly notable for bridging the gap between advanced statistical techniques and practical robotic applications, making him a key contributor to the growing field of vision-based robot localization.