Max Robotics — Global Service Robot Directory + US Certification

About

Ki-Seo Kim is a robotics researcher whose work focuses on autonomous navigation, slip control, and dexterous manipulation for mobile and robotic systems. His key contributions span reinforcement learning for navigation, sensor-based control for wheeled robots, and force-sensitive grasping for robotic hands. His most-cited paper, “Deep Learning Based on Smooth Driving for Autonomous Navigation” (2018, 11 citations), introduces a Deep Q-Network (DQN) approach combined with LiDAR sensing to enable a two-wheeled mobile robot to navigate unknown environments autonomously. In “Using Current Sensing Method and Fuzzy PID Controller for Slip Phenomena Estimation and Compensation of Mobile Robot” (2017, 7 citations), Kim proposes an optimal slip ratio control system that fuses current and IMU sensor data with a Fuzzy PID controller to mitigate slip in mobile robots. He also advances robotic manipulation in “Stable Grasping of Objects Using Air Pressure Sensors on a Robot Hand” (2018, 4 citations), where machine learning predicts grasping force from air pressure sensor data on a three-fingered hand. Additionally, his work on dual-arm manipulation in a ROS environment (2017, 3 citations) demonstrates robust grasping strategies based on object shape recognition. Kim’s research bridges deep learning, sensor fusion, and control theory to enhance robot autonomy and reliability.