Max Robotics — Global Service Robot Directory + US Certification

About

Mincheul Kang’s research lies at the intersection of robotics, motion planning, and manipulation, with a focus on enabling robots to operate safely and efficiently in dynamic, cluttered environments. His most impactful work, “RCIK: Real-Time Collision-Free Inverse Kinematics Using a Collision-Cost Prediction Network” (19 citations), introduces a learning-based approach that achieves real-time, collision-free inverse kinematics for 6-DOF commands, handling both static and dynamic obstacles—a critical advance for responsive robotic manipulation. In “Automated Task Planning Using Object Arrangement Optimization” (13 citations), Kang developed a method for robots to autonomously construct target object layouts from cluttered scenes, integrating task and motion planning to guide physical arrangement. His “Harmonious Sampling for Mobile Manipulation Planning” (7 citations) addresses the coupled planning of base and manipulator, overcoming the limitations of decoupled approaches to produce more optimal paths. Further contributions include accelerating optimization-based path-wise inverse kinematics (2022) and improving object detection during navigation via an objectness score (2019). Kang’s work consistently bridges perception, planning, and control, offering practical solutions for real-world robotic autonomy.