Yongseok Kwon

I am a robotics researcher at the Republic of Korea Army Headquarters. Before joining the army, I worked in ROAHM Lab advised by Ram Vasudevan at the University of Michigan. Also, I received my BS(‘20) at UNIST, and MS(‘22) at the University of Michigan.

My research interests lie in safe reinforcement learning, task and motion planning, and neural verification. My research goal is to create reliable deep learning-based algorithms to deploy autonomous robots closer to our daily lives.

CV • Github • G.Scholar • LinkedIn

kwonys [at] umich [dot] edu

Publications

Reachability-based Trajectory Design with Neural Implicit Safety Constraints

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

Robotics: Science and Systems (RSS) 2023

[webpage] • [paper] • [code]

Projects

Transformer for Motion Planning

Fall 2021 at the University of Michigan
Advised by prof. Nima Fazeli

Applied decision transformer on reaching task of 7 DOF robot arm.

Contact Simulation via Linear Complementary Problem

Fall 2021 at the University of Michigan
Advised by prof. Nima Fazeli

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

Trajectory Optimization for Autonoumous Car

Fall 2021 at the University of Michigan
Advised by prof. Ram Vasudevan

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
Advised by prof. Robert D. Gregg

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.