Yeonghun Chun
Papers
1
Total Citations
5
H-Index
1
About
Yeonghun Chun is a robotics researcher focused on advancing bipedal locomotion for humanoid robots, with a particular emphasis on reinforcement learning and real-world control systems. In his most cited work, "DDPG Reinforcement Learning Experiment for Improving the Stability of Bipedal Walking of Humanoid Robots" (2023, 5 citations), Chun developed a novel method for setting trajectory parameters using a deep deterministic policy gradient (DDPG) algorithm. By implementing this approach on a treadmill-like testbed in a real-world environment, he demonstrated how reinforcement learning can significantly enhance walking stability without relying solely on simulation. This experiment bridges the gap between theoretical control methods and practical robotic applications, offering a scalable framework for adaptive gait generation. Chun’s contributions are particularly valuable for researchers working on legged robotics, where maintaining balance under dynamic conditions remains a critical challenge. His work highlights the potential of model-free reinforcement learning to improve robustness in humanoid robots, paving the way for more agile and reliable autonomous systems in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1