publications

publications by categories in reversed chronological order.

2026

  1. CODA completes the Scene 29 reconstruction, then tests the same objects under gravity
    CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image
    Dongwon Son, Junhyek Han, Yoontae Cho, and 5 more authors
    Under review 2026Under review
    Paper Project
  2. Continuous pushing with TAM: box pushing with repeated goal-pose resets
    TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation
    Dongwon Son, Florian Shkurti, Jason Lee, and 3 more authors
    In Conference on Robot Learning (Spotlight) 2026CoRL
    Paper Project

2025

  1. UR5 motion planning through the mining-site cave obstacles
    NeuralSVCD for Efficient Swept Volume Collision Detection
    Dongwon Son, Hojin Jung, and Beomjoon Kim
    In Conference on Robot Learning 2025CoRL
    Paper Project
  2. Language-directed pick-and-place of shiny objects
    DEF-oriCORN: efficient 3D scene understanding for robust language-directed pick-and-place
    Dongwon Son, Sanghyeon Son, Jaehyung Kim, and 2 more authors
    In under review 2025under review
    Project

2024

  1. Figure 1: EGAD reconstruction comparison with multi-frequency equivariant features
    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 2024ICLR
    Paper Project

2023

  1. Preference-guided planning and belief updates
    Preference learning for guiding the tree search in continuous POMDPs
    Jiyong Ahn, Sanghyeon Son, Dongryung Lee, and 3 more authors
    In 7th Annual Conference on Robot Learning 2023CoRL
    Video Paper Project
  2. Simulated Franka arms shake containers holding non-convex objects
    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 2023RSS
    Video Paper Project

2022

  1. Reactive grasping among cluttered household objects
    Grasping as Inference: Reactive Grasping in Heavily Cluttered Environment
    Dongwon Son
    IEEE Robotics and Automation Letters 2022RA-L
    Video Paper

2021

  1. Figure 1: Four vision-based object manipulation tasks
    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 2021IROS
    Video Paper

2020

  1. Real-robot bolting under a position disturbance
    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 2020IROS
    Video Paper

2019

  1. Figure 1: Robot assembly and peg-in-hole applications
    Data-driven contact clustering for robot simulation
    Myungsin Kim, Jaemin Yoon, Dongwon Son, and 1 more author
    In International Conference on Robotics and Automation 2019ICRA
    Paper

2018

  1. LASDRA aerial skeleton tracks a changing trajectory
    LASDRA: Large-size aerial skeleton system with distributed rotor actuation
    Hyunsoo Yang, Sangyul Park, Jeongseob Lee, and 3 more authors
    In IEEE International Conference on Robotics and Automation 2018ICRA
    Paper