Dongwon Son

dongwon.son110@gmail.com

prof_pic.jpg

Building #9

85, Hoegi-ro

Seoul, Korea

I am currently a PhD student in the Graduate School of AI at KAIST. I am in HuGe Lab directed by Beomjoon Kim.

My research focuses on robot learning for manipulation, with an emphasis on computationally efficient simulation, planning, and sim-to-real transfer.

Previously, I received my master’s degree in mechanical engineering from Seoul National University under the guidance of Dongjun Lee, and my bachelor’s degree in mechanical engineering from Seoul National University. I also worked full-time at Samsung Research and Hanwha Techwin, and completed a research internship at the Allen Institute for AI (Ai2), working with Dieter Fox’s robotics group.

CV

news

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

selected publications

  1. CoRL
    NeuralSVCD for Efficient Swept Volume Collision Detection
    Dongwon Son, Hojin Jung, and Beomjoon Kim
    In Conference on Robot Learning 2025
    SITE
  2. 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
  3. 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
  4. RA-L
    Grasping as Inference: Reactive Grasping in Heavily Cluttered Environment
    Dongwon Son
    IEEE Robotics and Automation Letters 2022
    VIDEO PAPER
  5. 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
  6. 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