Jong‐Kook Kim
Papers
2
Total Citations
10
H-Index
1
About
Jong-Kook Kim is a rising force in intelligent robotics and autonomous manufacturing, whose work bridges the gap between long-horizon manipulation and industrial-scale multi-robot coordination. His primary research areas span hierarchical reinforcement learning, autonomous assembly, and deep reinforcement learning for scheduling under strict operational constraints. Kim’s most impactful contribution is the development of Gaussian Random Trajectory guided Hierarchical Reinforcement Learning (GRT-HL), a method that enables robots to tackle human-like, long-horizon tasks such as autonomous furniture assembly—a problem requiring both high-level planning and fine-grained manipulation. This work, published in 2022, has already garnered 9 citations, signaling its influence on the field. More recently, in 2025, Kim has advanced the state of the art in semiconductor manufacturing with an autoregressive DRL framework for multi-robot scheduling in cluster tools, addressing the critical challenge of maximizing throughput under tight coordination constraints. His research is notable for its practical impact on real-world automation, from consumer goods assembly to high-precision semiconductor fabrication. Kim’s work is essential reading for anyone interested in how reinforcement learning can unlock complex, multi-step robotic behaviors in constrained environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2