Minsung Ahn

University of California, Los Angeles, University of West Los Angeles

Papers

Total Citations

H-Index

About

Minsung Ahn is a robotics researcher whose work spans humanoid robot locomotion, intelligent control systems, and motion learning for legged robots. His research focuses on advancing the stability, agility, and adaptability of bipedal and quadrupedal robotic systems through the integration of reinforcement learning and intelligent control frameworks. Among his most notable contributions is his application of deep deterministic policy gradient (DDPG) reinforcement learning to improve bipedal walking stability in real-world humanoid environments — a paper that has garnered 5 citations since its 2023 publication. His earlier work on full-body balancing control for humanoid robots grasping objects of unknown weight demonstrates his long-standing interest in handling real-world uncertainty in robotic manipulation. More recently, Ahn has expanded his scope to quadrupedal systems, developing spatio-temporal motion retargeting techniques that bridge morphological differences between source motions and robot targets. His hardware contributions include the design of lightweight linear actuators tailored for agile humanoid movement. Across his career, Ahn's research reflects a consistent drive to make robots more capable in unpredictable, real-world conditions — combining algorithmic innovation with practical mechanical design to push the boundaries of modern robotics.