Sunghwan Kim (김성환)

Sunghwan Kim

Hi! My name is Sunghwan Kimpronounced "Sung-Hwahn" (su as in "sun"). I also go by Shawn. I am a PhD student at UC San Diego, working at Existential Robotics Laboratory. I'm fortunate to be advised by Prof. Nikolay Atanasov. I'm also closely working with Prof. Yulun Tian at University of Michigan. Previously, I was a research officer at the Agency for Defense Development (ADD), the South Korean counterpart to the U.S. DARPA. I received my B.S. in Electrical Engineering and Mathematics (double major) at KAIST.

My research goal is to enable mobile robots to perform long-horizon complex tasks in large-scale environments autonomously. To this end, I am interested in building structured state representations that capture the physical world and applying them to robot task planning. My current focus includes neural scene representations, neural SLAM, and robot policy learning methods (e.g., VLA, model-based RL).

News

  • [Jan 2026] Our paper SBP has been accepted to ICRA 2026!
  • [Oct 2025] Attending CoRL 2025. See you in Seoul!
  • [Jun 2025] Attending RSS 2025. See you in LA!
  • [Jun 2025] Our paper SBP has been nominated for Best Paper at the RSS RoboReps Workshop!
  • [Jun 2025] Our paper MISO has been accepted to RSS 2025!
  • [Aug 2024] Started my PhD at UC San Diego!

Publication

Papers sorted by recency. Representative papers are highlighted. * indicates equal contribution.

TLDR thumbnail

Texture Learning Domain Randomization for Domain Generalized Segmentation

Sunghwan Kim, Dae-hwan Kim, Hoseong Kim

ICCV, 2023

Trial thumbnail

Data Gathering Trials for the Development of Military Imaging Systems

Maria Niebla, Duncan L. Hickman, Eunjin Koh, Chanyong Lee, Hoseong Kim, Chaehyeon Lim, Sunghwan Kim

Proc. SPIE, Electro-Optical and Infrared Systems, 2023