Jin Gyun Jeong

About

Jin Gyun Jeong is a leading researcher at the intersection of wearable robotics, deep reinforcement learning, and dexterous manipulation. His work focuses on enabling robots to intuitively understand and assist human motion, with key contributions in real-time activity recognition and natural object manipulation. Jeong’s most cited paper, “Real-Time Human Activity Recognition with IMU and Encoder Sensors in Wearable Exoskeleton Robot via Deep Learning Networks” (2022, 52 citations), pioneered a system that fuses inertial measurement unit and encoder data with deep learning to recognize user intent in real time, directly enhancing exoskeleton control for daily tasks. He has also advanced reinforcement learning for robotic hands, introducing reward shaping techniques and a Natural Hand Pose Transformer to teach anthropomorphic hands dexterous manipulation without task-specific engineering (2021, 2022). His work bridges the gap between human biomechanics and autonomous robotic control, with implications for healthcare, smart homes, and industry. Jeong’s research is distinguished by its focus on practical, real-time deployment and biologically inspired learning, making him a rising figure in human-robot interaction and embodied AI.

Research Focus

Key Achievements

Top Papers

1. 1
   Real-Time Human Activity Recognition with IMU and Encoder Sensors in Wearable Exoskeleton Robot via Deep Learning Networks

   52 citations · 2022
2. 2
   Reward Shaping to Learn Natural Object Manipulation With an Anthropomorphic Robotic Hand and Hand Pose Priors via On-Policy Reinforcement Learning

   4 citations · 2021
3. 3
   Dexterous Object Manipulation with an Anthropomorphic Robot Hand via Natural Hand Pose Transformer and Deep Reinforcement Learning

   4 citations · 2022

Key Collaborators

Contact & Links