Optimal Control, Reinfocement Learning and World Models.
This is Sewon Kim.
I'm an undergraduate student in electrical and computer engineering based at the Unitversity of
Seoul.
I am interested in developing scalable learning and control methods and their theoretical foundations for autonomous agents, such as robotics.
By the way, I'm originally from Seoul, South Korea π°π·.
I have a passion for jazz and heavy metal, and I spent many years playing acoustic and electric
guitar in rock bands πΈ.
Publications
First-Order Methods for Trilevel Optimization
Sewon Kim, Hyunwoo Lee, Jeongyeol Kwon, and Dohyun Kwon. Under review at NeurIPS 2026.
Finite State MachineObject Pose EstimationInverse Kinematics
[08/25/2025-09/25/2025] Autonomous Air Purifing Agent
π 4th Place (/200) ($2,200) β SK NAMUH X A1: Autonomous Driving Path
Optimization
I independently implemented full-stack autonomous air purifying agent in NumPy from scratch, covering MCL, MPPI, and TSP.
Monte Carlo LocalizationTraveling Salesman ProblemModel Predictive Path Integral Control
[03/01/2024-12/19/2024] Autonomous Racing F1tenth
5th Place (/12) β 22nd F1tenth Autonomous Grand Prix at the Conference
on Decision and Control 2024, Milan
F1Tenth refers to a 1/10-scale car of a real Formula 1 vehicle,
which aims to achieve high-speed and collision-free autonomous driving.
We built a full-stack autonomous navigation system for racing completely
from scratch, especially MPPI, and I led the project with two undergraduate students.
SLAMMonte Carlo LocalizationRace Line OptimizationModel Predictive Path Integral Control
[07/25/2024β09/27/2024] Cart Pole System Design and Control with NMPC and
PID
π 3rd Place (/25) ($220) β UOS ECE Innovation Fair
I built a physical Cart-Pole system, a classical control problem, for just 272 USD and applied
nonlinear model predictive control. I independently developed 3D modeling, sensor integration,
motor control, state estimation, embeded, and MPC.
Model Predictive ControlPIDHardwareMechanical DesignEmbeddedElectronicsState EstimationStepper Motor
[01/05/2024-01/11/2025] InBody AI Scale
Consumer Electronic Show 2025, Las Vegas
Developed height estimation model (acc 99.4%) and face recognition system of "InBody AI Scale", automated body composition analyzer that reduces measurement time from 120s to 40s.