Jin Seok Hong
Papers
1
Total Citations
21
H-Index
1
About
Jin Seok Hong is a leading researcher in autonomous robotics and reinforcement learning, with a focus on enabling intelligent navigation in complex, real-world environments. His most-cited work, "Deep Deterministic Policy Gradient-Based Autonomous Driving for Mobile Robots in Sparse Reward Environments" (2022, 21 citations), addresses a critical challenge in robot autonomy: learning effective path-planning when feedback signals are rare. Hong’s key contribution lies in integrating the Deep Deterministic Policy Gradient (DDPG) algorithm with Hindsight Experience Replay (HER), a technique that allows robots to learn from failed trajectories as if they were successes. This innovation significantly improves sample efficiency and performance in sparse reward settings, where traditional methods often fail. By bridging the gap between deep reinforcement learning theory and practical mobile robot control, Hong’s work has direct implications for autonomous driving, warehouse logistics, and search-and-rescue operations. His research exemplifies how algorithmic advances can solve real-world robotic navigation problems, making him a notable figure in the intersection of machine learning and robotics.
Research Focus
Key Achievements
Top Papers
- 1