In‐Kyu Kim
Papers
2
Total Citations
37
H-Index
2
About
In-Kyu Kim is a leading researcher in mobile robotics, specializing in simultaneous localization and mapping (SLAM) and the critical challenges of particle filter-based estimation. His work has fundamentally addressed the particle depletion and sample impoverishment problems that degrade the long-term performance of FastSLAM algorithms. In his highly cited 2007 paper (21 citations), Kim rigorously analyzed how the resampling process in FastSLAM leads to over-confident uncertainty estimates and a loss of particle diversity over time. Building on this, his second major contribution (16 citations) introduced an adaptive prior boosting technique that efficiently determines the optimal sample size, directly mitigating sample impoverishment without excessive computational cost. These contributions are essential for enabling robust, long-duration autonomous navigation in real-world environments. Kim’s research is particularly notable for its practical impact on mobile robot deployment, providing both diagnostic insights into algorithmic failure modes and actionable solutions for improving estimator consistency. His work remains a cornerstone reference for researchers developing particle filter-based SLAM systems, especially those seeking to balance accuracy, efficiency, and reliability in complex, uncertain environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Adaptive prior boosting technique for the efficient sample size in fastSLAM16 citations · 2007