Papers
4
Total Citations
46
H-Index
3
About
Dong Ki Kim is a robotics researcher whose work bridges the gap between advanced control theory and practical robotic systems. His primary research areas include model predictive control, imitation learning, and tactile sensing for human-robot interaction. Kim's most significant contribution is his 2022 paper "Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC," which has garnered 21 citations. In this work, he developed an innovative method to compress computationally expensive Model Predictive Controllers into efficient deep neural network representations using imitation learning, dramatically reducing computational requirements while maintaining robust performance. This approach enables real-time deployment of sophisticated control strategies on resource-constrained robotic platforms. Earlier in his career, Kim made notable contributions to tactile sensing technology, including a 3D-curved fingertip sensing module (12 citations) and force-sensing foot modules for biped robots (10 citations). His work on contact-resistance force sensors for robot head modules (3 citations) also advanced safe human-robot interaction. Kim's research demonstrates a consistent focus on making advanced robotic control and sensing practical for real-world applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4