Papers
6
Total Citations
83
H-Index
4
About
Jongchan Baek is a pioneering researcher at the intersection of robotics, control theory, and artificial intelligence, with a primary focus on developing intelligent, adaptive control systems for robotic manipulators and autonomous agents. His most significant contribution is the creation of an Adaptive Model Uncertainty Estimator (AMUE) that enables model-free control algorithms to maintain stable torque inputs even under instantaneous disturbances like friction, payload changes, or trajectory shifts—a breakthrough published in 2022 that has already garnered 46 citations. Baek further advanced the field by integrating reinforcement learning with time-delay control (RL-TDC), producing more intelligent and aggressive control responses than traditional adaptive methods. His work on improving reinforcement learning robustness through uncertainty and disturbance estimators (RL-based UDE) demonstrates his commitment to bridging the gap between simulated training and real-world deployment. Beyond control theory, Baek has made notable contributions to geometric visualization, publishing an influential paper on visualizing quaternion multiplication that aids understanding of 4D rotations for navigation and robotics applications. His recent survey on Embodied AI and transformer-based dynamics models for quadrotor control signals his expanding influence in sim-to-real transfer learning. With over 80 total citations and growing, Baek's research continues to shape how robots learn and adapt in complex, uncertain environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Visualizing Quaternion Multiplication22 citations · 2017
- 3
- 4
- 5
- 6