Seungcheon Shin
Papers
3
Total Citations
6
H-Index
1
About
Seungcheon Shin is a researcher advancing the intersection of robotics and neural network-based control systems. His primary research areas include dynamic model learning for robot manipulators, neural network architectures, and optimal data-driven control strategies. Shin’s most significant contribution is his pioneering work on using multi-layer perceptron (MLP) neural networks to learn the complete dynamic model of multi-joint robot manipulators, enabling closed-loop control without explicit physical modeling. His 2023 paper on this topic, which has garnered 4 citations, demonstrates how measured joint angles, velocities, and input torques can train an optimized MLP with carefully tuned layers and nodes. Building on this foundation, Shin has explored recurrent neural networks (RNNs) for dynamic model learning, with his 2024 and 2025 papers investigating optimal data bandwidth and learning processes. These works represent a systematic progression toward more efficient, data-efficient robot control. Though early in his career, Shin’s methodical approach—from hyperparameter optimization to bandwidth analysis—positions him as a thoughtful contributor to the growing field of neural network-based robotics, offering practical pathways for more adaptive and intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3