Papers
1
Total Citations
99
H-Index
1
About
Dong-Ki Han is a leading researcher in intelligent robotics, specializing in motion planning and reinforcement learning for autonomous systems. His work centers on developing algorithms that enable robot manipulators to generate smoother, more efficient paths in dynamic manufacturing environments. Han’s most influential contribution, the integration of Twin Delayed Deep Deterministic Policy Gradient (TD3) with Hindsight Experience Replay (HER), represents a breakthrough in automated motion planning. This approach, detailed in his 2020 paper (99 citations), overcomes the limitations of traditional probabilistic methods like PRM by allowing robots to learn from sparse rewards and adapt to complex, unstructured workspaces. His research directly addresses critical challenges in Industry 4.0, where flexible automation demands that robots autonomously plan tasks without human intervention. By combining deep reinforcement learning with advanced replay strategies, Han has significantly improved both the smoothness and success rate of manipulator trajectories. His work has been widely recognized in the robotics community, with applications spanning from manufacturing to service robotics, and continues to influence the development of more intelligent and adaptive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1