Min-Gyeom Kim
Papers
3
Total Citations
11
H-Index
2
About
Min-Gyeom Kim is a robotics researcher focused on advancing trajectory optimization for autonomous systems. His primary research areas include optimal control, motion planning, and collision-free navigation for mobile robots. Kim’s major contribution lies in developing hybrid methods that combine the strengths of sampling-based and gradient-based optimization techniques. His most cited work, “MPPI-IPDDP: A Hybrid Method of Collision-Free Smooth Trajectory Generation for Autonomous Robots” (2025, 7 citations), introduces a novel approach that merges Model Predictive Path Integral (MPPI) control with Interior-Point Differential Dynamic Programming (IPDDP). This method effectively generates smooth, collision-free trajectories by leveraging MPPI’s robustness in complex environments and IPDDP’s precision in constrained optimization. Kim also extended IPDDP to handle second-order conic constraints (SOC-IPDDP, 2022), broadening its applicability to real-world control problems. His work bridges critical gaps between sampling-based and optimization-based planning, offering practical solutions for autonomous navigation in cluttered spaces. With growing citation impact, Kim’s research is shaping the next generation of efficient, safe motion planning algorithms for autonomous robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3