Dongwon Son

Building #9

85, Hoegi-ro

Seoul, Korea

I am currently a PhD student in Graduate School of AI at KAIST. I am in Intelligent mobile-manipulation (IM^2) lab directed by Beomjoon Kim.

I am interested in all the things related with creating an intelligent movement of the robot arm including physics simulation, rendering, vision, computational hardware, reinforcement learning, trajectory optimization and actuator.

Previously, I obtained my Master Degree in mechanical engineering from Seoul National University under the guidance of Dongjun Lee, and my Bachelor Degree in mechanical engineering from Seoul National University. I also had worked full-time at Samsung Research, and Hanwha Techwin.

news

Sep 2, 2022	My work about grasping was posted on Video Friday of IEEE Spectrum!
Aug 23, 2022	I joined IM2 in Graduate School of AI at KAIST.

selected publications

ICLR

An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks

Dongwon Son, Jaehyung Kim, Sanghyeon Son, and 1 more author

In The Twelfth International Conference on Learning Representations 2024

PAPER SITE
RSS

Local Object Crop Collision Network for Efficient Simulation of Non-Convex Objects in GPU-based Simulators

Dongwon Son, and Beomjoon Kim

In Robotics: Science and Systems 2023

VIDEO PAPER SITE
RA-L

Grasping as Inference: Reactive Grasping in Heavily Cluttered Environment

Dongwon Son

IEEE Robotics and Automation Letters 2022

VIDEO PAPER
IROS

Reinforcement Learning for Vision-based Object Manipulation with Non-parametric Policy and Action Primitives

Dongwon Son, Myungsin Kim, Jaecheol Sim, and 1 more author

In IEEE/RSJ International Conference on Intelligent Robots and Systems 2021

VIDEO PAPER
IROS

Sim-to-real transfer of bolting tasks with tight tolerance

Dongwon Son, Hyunsoo Yang, and Dongjun Lee

In IEEE/RSJ International Conference on Intelligent Robots and Systems 2020

VIDEO PAPER