Integrated M.S.–Ph.D. · SPARO Lab

Hi, I'm Jiwon.

Learning-based state estimation & proprioceptive odometry

I'm an integrated M.S.–Ph.D. student in Electrical and Computer Engineering at Inha University, advised by Younggun Cho in SPARO Lab, where I also received my B.S. in Electrical Engineering. During my M.S. I worked on self-supervised inertial odometry; I'm now working on proprioceptive state estimation — modeling and correcting environment-induced error from inertial, kinematic, and contact signals alone. For my thoughts and research notes, see the .

Jiwon Choi
Hi! I'm Jiwon

News

Latest news

Research

Latest research

KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference
2026 1st Author Conference

KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference

Best Paper on Robot Perception Finalist

IEEE International Conference on Robotics and Automation (ICRA 2026)
PoLaRIS Dataset: A Maritime Object Detection and Tracking Dataset in Pohang Canal
2025 1st Author Conference

PoLaRIS Dataset: A Maritime Object Detection and Tracking Dataset in Pohang Canal

IEEE International Conference on Robotics and Automation (ICRA 2025)

News

News

Papers, awards, and talks, newest first.

Category

Publications

Publications

Conference and journal papers, grouped by year.

Region
Type
  1. RadLoc: Radar-based 3-DoF Global Localization via Fast, Robust, and Lightweight Spatial Descriptor Across Diverse Environmental Scenarios
    Hogyun Kim, Jiwon Choi, Jungwoo Lee, Younggun Cho
    IROS, 2026 , 2026/10
    Project Code
  2. SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments
    Hogyun Kim, Jiwon Choi, Juwon Kim, Geonmo Yang, Dongjin Cho, Hyungtae Lim, Younggun Cho
    T-FR , 2026/08
    arXiv Project Code
  3. Commerge: Communication-Efficient, Robust and Fast LiDAR Map Merging Framework for Multi-robot Coordination in Resource-constrained Scenarios
    Hogyun Kim, Jiwon Choi, Juwon Kim, Geonmo Yang, Seokhwan Jeong, Hyungtae Lim, Younggun Cho
    IJRR , 2026/06
    Project Code
  4. KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference
    Jiwon Choi, Hogyun Kim, Geonmo Yang, Juhui Lee, Younggun Cho
    ICRA, 2026 , 2026/06 · Best Paper on Robot Perception Finalist
    arXiv Project Code
  5. SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments
    Hogyun Kim, Jiwon Choi, Juwon Kim, Geonmo Yang, Dongjin Cho, Hyungtae Lim, Younggun Cho
    ICRA workshop on Field Robotics (spotlight talk), 2025 , 2025/05 · Spotlight Talk
    arXiv Project Code
  6. PoLaRIS Dataset: A Maritime Object Detection and Tracking Dataset in Pohang Canal
    Jiwon Choi*, Dongjin Cho*, Giheyon Lee, Hogyun Kim, Geonmo Yang, Joowan Kim, Younggun Cho
    ICRA, 2025 , 2025/05
    Paper arXiv Project Code
  7. IML-SLAM: 주행 차량 모션을 고려한 LiDAR-Inertial SLAM 시스템
    Jiwon Choi, Hogyun Kim, Geonmo Yang, Younggun Cho
    Korea Institute of ITS Conference , 2025/04 · Excellent Paper Award
  8. Narrowing your FOV with SOLiD: Spatially Organized and Lightweight Global Descriptor for FOV-constrained LiDAR Place Recognition
    Hogyun Kim, Jiwon Choi, Taehu Sim, Giseop Kim, Younggun Cho
    RA-L , 2024/08
    Paper arXiv Project Code
  9. 가벼운 전역 설명자로 이루어진 위치 인식 기술을 이용한 강인한 슬램 기술
    Jiwon Choi, Hogyun Kim, Younggun Cho
    ICROS Annual Conference , 2024/06
  10. Study on Efficient Multi-floor Navigation Using a Visual Marker and Floor Plan Map
    Jiwon Choi, Taehu Sim, Gihyeon Lee, Jaeyong Lee, Gilhwan Kang, Hogyun Kim, Young Gun Cho
    ICROS Journal , 2024/01
    Paper
  11. Visual marker 및 설계도면을 활용한 효율적인 다층 내비게이션에 관한 연구
    Gihyeon Lee, Sangwook Han, Taehu Sim, Jiwon Choi, Changhee Kim, Jaeyong Lee, Younggun Cho
    ICROS Annual Conference , 2023/06
  12. 거리 기반 Sampling Algorithm을 이용한 LiDAR의 객체 인식 성능 개선에 관한 연구
    Dongyoung Kim, Hanbin Song, Jiwon Choi, Jaewoon Lee, Jiung Im, Jonghun Won
    Korea Institute of ITS Conference , 2022/06 · Excellent Paper Award

Research

Research

Projects I led or contributed to.

Type
Role
RadLoc: Radar-based 3-DoF Global Localization via Fast, Robust, and Lightweight Spatial Descriptor Across Diverse Environmental Scenarios
2026 Co-author Conference

RadLoc: Radar-based 3-DoF Global Localization via Fast, Robust, and Lightweight Spatial Descriptor Across Diverse Environmental Scenarios

1st author — Hogyun Kim

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)
SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments
2026 Co-author Journal

SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments

1st author — Hogyun Kim

IEEE Transactions on Field Robotics (T-FR 2026)
Commerge: Communication-Efficient, Robust and Fast LiDAR Map Merging Framework for Multi-robot Coordination in Resource-constrained Scenarios
2026 Co-author Journal

Commerge: Communication-Efficient, Robust and Fast LiDAR Map Merging Framework for Multi-robot Coordination in Resource-constrained Scenarios

1st author — Hogyun Kim

International Journal of Robotics Research (IJRR 2026)
KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference
2026 1st Author Conference

KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference

Best Paper on Robot Perception Finalist

IEEE International Conference on Robotics and Automation (ICRA 2026)
SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments
2025 Co-author Conference

SKiD-SLAM: Robust, Lightweight, and Distributed Multi-Robot LiDAR SLAM in Resource-Constrained Field Environments

1st author — Hogyun Kim Spotlight Talk

ICRA Workshop on Field Robotics (ICRA Workshop 2025)
PoLaRIS Dataset: A Maritime Object Detection and Tracking Dataset in Pohang Canal
2025 1st Author Conference

PoLaRIS Dataset: A Maritime Object Detection and Tracking Dataset in Pohang Canal

IEEE International Conference on Robotics and Automation (ICRA 2025)
Narrowing your FOV with SOLiD: Spatially Organized and Lightweight Global Descriptor for FOV-constrained LiDAR Place Recognition
2024 Co-author Journal

Narrowing your FOV with SOLiD: Spatially Organized and Lightweight Global Descriptor for FOV-constrained LiDAR Place Recognition

1st author — Hogyun Kim

IEEE Robotics and Automation Letters (RA-L 2024)

Projects

Projects

Research grants I lead and challenges I have competed in.

Motion-Environment Disentangled Representation Learning for Adaptive IMU Odometry in Heterogeneous Robots
2026.09 – Present Principal Investigator NRF Grant

Motion-Environment Disentangled Representation Learning for Adaptive IMU Odometry in Heterogeneous Robots

모션·환경 분리 표현 학습을 통한 이기종 로봇의 적응형 IMU 자기위치 추정

National Research Foundation of Korea (NRF) · Ph.D. Candidate Research Fellowship

Separates the robot's own motion from terrain and disturbance effects in IMU signals (M&E-IMU), so one IMU odometry framework adapts to new robots and environments without retraining.

  1. Year 1

    Motion–environment disentangled encoder (M&E-IMU)

  2. Year 2

    Heterogeneous pre-training, distilled into on-device student models

  3. Year 3

    Test-time adaptation, field validation, and open-source release

TartanIMU Challenge @IROS 2026
2026.10 Team Leader Challenge

TartanIMU Challenge @IROS 2026

IMU Odometry Challenge · Beyond Exteroception Workshop, IROS 2026

2nd place out of 131 teams

Single-Head IMU Velocity Estimation Across Platforms via a Multi-Scale, Embodiment-Aware Encoder — one network that estimates velocity from IMU alone across cars, quadrupeds, drones, and handheld devices.

Jiwon Choi, Hogyun Kim, Jungwoo Lee, Geonmo Yang, Seunghee Yun, Younggun Cho

project challenge model

Hilti–Trimble SLAM Challenge @ICRA 2026
2026.06 Team Member Challenge

Hilti–Trimble SLAM Challenge @ICRA 2026

SLAM Category · Workshop on Open Challenges in Robotics for Asset Inspection and Management, ICRA 2026

2nd place out of 62 teams

√VINS-Based 360 Visual-Inertial SLAM Systems

Jungwoo Lee, Hogyun Kim, Jiwon Choi, Jinyong Jeong, Younggun Cho

project challenge

Posts

Posts

Interactive notes and small tools.

Category

Tools

ProjectClaude CodeTool

Paper Reviewer

Drop in a paper PDF: get grammar, spacing, and capitalization issues marked right on the page, plus a harsh or typical reviewer's accept/reject verdict for your target venue, in English and Korean.

Open tool

State Estimation

StudyLiDAR SLAMInteractive~12 min

Two Sweeps, One Transform

Ray-cast two real LiDAR sweeps, pick edge and planar features by curvature, and watch a Gauss-Newton solver recover the relative pose the way LOAM and LIO-SAM do.

Open lab
🚧 작성중StudyKinematicsInteractive~10 min

From Foot Contact to Body Velocity

Drive a GO2 quadruped and watch stance-foot contact and leg kinematics fuse with an IMU into a body-velocity estimate.

Open simulator

ETC

Etc.

Academic service.

Academic Service

  • Reviewer RA-L, 2025, 2026 ICRA, 2026 IROS, 2026