Papers
42
Total Citations
770
H-Index
14
About
Jongeun Choi is a versatile robotics and control systems researcher whose work spans optimal control theory, autonomous robotics, wearable assistive devices, and machine learning. He is perhaps best known for his foundational contributions to the inverse linear quadratic regulator (LQR) problem, developing techniques to recover cost functions from observed controller behavior — a framework with broad implications for analyzing biological and engineered systems, now cited over 150 times. His research extends naturally into inverse reinforcement learning, where he pioneered Gaussian process-based reward prediction methods to tackle high-dimensional problems with unknown dynamics. Choi has made significant strides in autonomous environmental monitoring, designing optimal sampling strategies for aquatic robots navigating large regions with limited resources. His work on microswimmer feedback control and multi-agent field exploration further demonstrates his breadth across micro- and macro-scale robotic systems. More recently, he has advanced flexible tactile sensor technology — addressing longstanding crosstalk challenges in sensor arrays — and applied deep reinforcement learning to design ankle-foot orthosis controllers that account for realistic human-robot interaction. His latest work on SE(3)-equivariant diffusion models for robotic manipulation signals a forward-looking engagement with generative AI in robotics. Across more than a decade of prolific output, Choi has established himself as an innovative bridge between control theory, autonomous systems, and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Feedback control of an achiral robotic microswimmer53 citations · 2017
- 5
- 6
- 7
- 8
- 9
- 10