Michael H. Lim
(Hyun Jae Lim)


UC Berkeley - PhD in Statistics & Robotics
Harvard University Class of 2018
"ML does ML"

I am a 2nd year PhD student in Statistics with a focus on robotics at UC Berkeley, advised by Prof. Claire J. Tomlin. I am interested in the intersection of control theory, sequential decision making, and machine learning, with applications in robotics.

My research goal is to develop algorithms and systems that enable physical robots to operate intelligently, safely, and efficiently, with provable guarantees. Currently, my research trajectory consists of two distinct approaches; First, my research aims to develop MDP and POMDP algorithms that tackle continuous observation and action spaces, which combine provable theoretical convergence guarantees as well as computational efficiency. Second, my research attempts to integrate robust optimal controls with computer vision and machine learning, which enables agents to navigate unknown environments.


December 2019

  • Updated website! Written and designed by myself.
  • Semester is over - I took Advanced Robotics (CS287), and Linear Systems Theory (EE 221A).

October 2019

  • Preprint version of recent work on POMDP convergence guarantees for continuous observations is available on arXiv link.