Harin Kim

Papers

Total Citations

H-Index

About

Harin Kim is a robotics researcher focused on human-robot interaction and assistive technologies, with key contributions in humanoid push recovery and exoskeleton control. Their most cited work, "Push Recovery Control for Humanoid Robot Using Reinforcement Learning" (2019, 15 citations), addresses the fundamental challenge of maintaining balance in humanoid robots. By integrating IMU sensors with high- and low-level controllers, Kim developed a reinforcement learning-based system that enables robots to recover from external pushes—a critical step toward stable, human-like locomotion. This work has implications for disaster response and service robotics. In "Real-Time Joint Torque Estimation on Embedded System using EMG and Artificial Neural Network for Exoskeleton Robot" (2020, 4 citations), Kim tackled the practical challenge of real-time intent detection for exoskeletons. By combining electromyography (EMG) signals with artificial neural networks, they created an embedded system that estimates joint torque, enabling exoskeletons to respond intuitively to user movements. This innovation supports safer, more efficient industrial exoskeletons for muscle strength augmentation. Kim’s research bridges reinforcement learning, sensor fusion, and neural networks, advancing both autonomous humanoid stability and wearable robotic assistance.