Max Robotics — Global Service Robot Directory + US Certification

About

Gwanghyeon Ji is a leading researcher in legged robotics, specializing in reinforcement learning, state estimation, and robust locomotion control. His major contributions center on bridging the gap between simulation-trained policies and real-world deployment, particularly on challenging terrains. Ji pioneered a concurrent training framework for control policies and state estimators, enabling dynamic and robust legged locomotion even without external sensors—a breakthrough detailed in his highly cited 2022 work (179 citations). He further advanced the field by addressing deformable terrain locomotion (147 citations), a critical hurdle for high-speed quadrupedal movement on soft ground, and introduced constraint-based reinforcement learning to enhance motion naturalness and task performance (58 citations). His state estimation algorithm, leveraging dynamic contact events and MAP estimation (45 citations), has become a foundational tool for legged robot proprioception. Notably, Ji led the RAIBO2 project, where a quadruped robot completed a full marathon on a single battery charge—a landmark achievement in energy efficiency and endurance. With over 430 total citations and a focus on practical, deployable solutions, Ji’s work is shaping the next generation of agile, resilient legged robots for real-world environments.