Papers

4

Total Citations

159

H-Index

4

About

MyeongSeop Kim is a leading researcher at the intersection of robotics and artificial intelligence, specializing in deep reinforcement learning (DRL) for autonomous motion planning. His work addresses critical challenges in manufacturing and robotics, particularly for multi-arm manipulators and quadrupedal locomotion in complex, dynamic environments. Kim’s major contributions include pioneering the use of Twin Delayed Deep Deterministic Policy Gradient (TD3) combined with Hindsight Experience Replay (HER) to generate smoother, automated paths for robot manipulators—a work that has garnered 99 citations. He further advanced the field by integrating Soft Actor-Critic (SAC) algorithms with LSTM-based position prediction to enable multi-arm robots to navigate around moving obstacles. Beyond path planning, Kim has made significant theoretical contributions to reinforcement learning itself, including an adaptive discount factor method for handling uncertainty in continuing tasks (24 citations) and an automated hyperparameter tuning framework for quadrupedal robot locomotion (11 citations). His research is characterized by a practical, systems-level approach that bridges algorithmic innovation with real-world robotic deployment, making him a key figure in the push toward fully autonomous, adaptive manufacturing systems.

Research Focus

Key Achievements

4
H-Index
4
Papers
159
Total Citations
40
Avg Citations/Paper
🏆 Most Cited Paper
Motion Planning of Robot Manipulators for a Smoother Path Using a Twin Delayed Deep Deterministic Policy Gradient with Hindsight Experience Replay
99 citations · 2020
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Seoul National University of Science and Technology, Korea Institute of Industrial Technology

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago