Yongseok Kwon

I'm a Ph.D. student at the University of Pennsylvania, advised by Prof. Rachel Holladay. Previously, I received my MS at the University of Michigan, advised by Prof. Ram Vasudevan.

My research aims to develop reliable algorithms that enable robots to perform a wide range of manipulation tasks. To achieve this, I focus on designing efficient representations of world models and developing robust planners/policies that account for the uncertainty inherent in these world models.

CV  •  G. Scholar  •  GitHub  •  LinkedIn  •  X/Twitter
 kwonys [at] seas [dot] upenn [dot] edu

Publications

Conformalized Reachable Sets for Obstacle Avoidance With Spheres

Yongseok Kwon, Jonathan Michaux, Seth Isaacson, Bohao Zhang, Matthew Ejakov, Katherine A. Skinner, and Ram Vasudevan

IEEE International Conference on Robotics and Automation (ICRA), 2025.

project page  •  paper  •  code  

Reachability-based Trajectory Design with Neural Implicit Safety Constraints

Jonathan Michaux, Qingyi Chen, Yongseok Kwon, and Ram Vasudevan

Robotics: Science and Systems (RSS), 2023.

project page  •  paper  •  code  

Software Contributions

ZONOPY: Zonotopes in Python

A Python library for handling various continuous sets (e.g., intervals, zonotopes, and polynomial zonotopes) to compute reachable sets in robotic arm kinematics and dynamics, with support for parallel computation.

▸ zonopy :  code  •  documentation 

▸ zonopy-robots :  code  •  documentation 

Projects

Transformer for Reaching Task

Fall 2021 at the University of Michigan

Trained a Decision Transformer for the reaching task of a 7-DOF robotic arm using an offline reinforcement learning

Contact Simulation via Linear Complementary Problem

Fall 2021 at the University of Michigan

Implemented contact simulator with LCP (Linear Complementary Problem) formulation of contact dynamics.

Trajectory Optimization for Autonoumous Car

Fall 2021 at the University of Michigan

Implemented convex collision avoidance constraint for lane changing task of autonomous car.

Extended Kalman Filter on Neural Gait Model

Fall 2021 at the University of Michigan

Implemented extended Kalman filter on a gait measurement model trained with a neural network and tested the state estimation algorithm on an open-source robotic leg.

UAV Navigation via Dubins Path Planning

Spring 2019 at UNIST

Implemented Dubins-curve based RRT to generate paths for UAV under kino-dynamic constraints.

Dual-Epicyclic Gearset for Decoupling Tendon-Driven Mechanism

2019 Fall at UNIST

Designed dual-epicyclic gearset to solve motion-coupling of multi DOF tendon-driven mechanism.