Youngeon Kim

I am Youngeon Kim, a mobile robotics researcher and engineer at the Korea Electronics Technology Institute (KETI).

Research interests, Multi-robot system and Sim-to-Real, LiDAR-inertial-visual localization and mapping, Traversability for outdoor and multi-floor environments, and vision-language models(VLM) as the decision layer for autonomy.

I believe robotics has the potential to make our lives better by solving real-world problems in new ways. I'm passionate about exploring new ideas and turning them into practical robotic solutions. My goal is to keep growing as an engineer and contribute to making robots more useful in the real world.

Youngeon Kim (김영언)
Intelligent Robotics Research Center, KETI
"Better today than yesterday."

Experience

Period	Organization	Role
2023.05 – present	Korea Electronics Technology Institute (KETI), Intelligent Robotics Research Center, Seoul	Researcher, Mobile Robotics — multi-robot fleet management, autonomous navigation, SDR/OTA, simulation, anomaly detection
2022.08 – 2023.03	Korea Institute of Robotics and Technology Convergence (KIRO), Robot Vocational Innovation Center, Gumi	Intern — integrated training environment for heterogeneous industrial and collaborative robots
2021.03 – 2022.01	Robot Dynamics and Intelligent Control Lab, Keimyung University	Undergraduate researcher — system modeling and stability design of piping robots, MFC-based actuator control
2017.03 – 2023.02	Keimyung University, Daegu	B.S. in Robotics Engineering (GPA 4.2/4.5, major 4.4/4.5)

Ongoing Projects

Cooperative Multi-Robot Navigation in Large-Scale Indoor Workspaces
2023.05 – present

Open-RMF fleet management and task system; 30-robot simulation to 4 real robots
Cooperative obstacle sharing and lane closure; fault injection and learning-based anomaly detection
Outdoor extension: traversability navigation pipeline

Software-Defined Robot (SDR) Domain Services
2025.01 – present

Docker/Git OTA framework with robot profiles
Robot–elevator multi-floor navigation and LiDAR-marker ICP docking on a real robot
Go2 multi-floor simulation testbed and VLM mission agent

Full project write-ups are on the projects page; the CV page has the complete record.

selected publications

ICROS
A Learning-based Anomaly Detection Framework for Multi-Robot Systems

Youngeon Kim, Yohan Jung, Dong Yeop Kim, and Keunhwan Kim

In Conference of the Institute of Control, Robotics and Systems (ICROS 2026), Jul 2026

1st author Abs Bib

1st author

In an Open-RMF simulation with ten mobile robots, position error, velocity, battery level and mission progress are defined as time-series features, and a Transformer-based self-supervised model (RESTAD) learns spatio-temporal correlations across robots to detect anomalies without labels. On the region-level metric (Aff-F1 0.94) it outperforms LSTM and a plain Transformer. Learning-based follow-up to the rule-based ICCAS 2025 framework.
@inproceedings{kim2026learning, title = {A Learning-based Anomaly Detection Framework for Multi-Robot Systems}, author = {Kim, Youngeon and Jung, Yohan and Kim, Dong Yeop and Kim, Keunhwan}, booktitle = {Conference of the Institute of Control, Robotics and Systems (ICROS 2026)}, year = {2026}, month = jul, address = {Daegu, Korea}, }
ICCAS
Anomaly Detection and Visualization Framework for Multi-Robot Systems Using RMF

Youngeon Kim, Yohan Jung, Dong Yeop Kim, and Keunhwan Kim

In 2025 25th International Conference on Control, Automation and Systems (ICCAS), Nov 2025

1st author Abs Bib

1st author

Defines four anomaly types in a multi-robot system (battery depletion, unexpected obstacle, trajectory conflict, collision risk within 0.2 m), detects them in a module decoupled from RMF task allocation, and visualizes them in real time on a WebSocket/ROS-bridge web dashboard. Validated in a Gazebo simulation with 30 mobile robots.
@inproceedings{kim2025anomaly, title = {Anomaly Detection and Visualization Framework for Multi-Robot Systems Using RMF}, author = {Kim, Youngeon and Jung, Yohan and Kim, Dong Yeop and Kim, Keunhwan}, booktitle = {2025 25th International Conference on Control, Automation and Systems (ICCAS)}, year = {2025}, month = nov, pages = {808--811}, address = {Incheon, Korea}, publisher = {IEEE}, }
ICCAS
Design and Implementation of an OTA Update Framework for Software-Defined Robots using ROS 2 and Docker

Dong Yeop Kim, Youngeon Kim, Eunsu Kim, Keunhwan Kim, Euntai Kim, and Deok Gyoon Chung

In 2025 25th International Conference on Control, Automation and Systems (ICCAS), Nov 2025

Abs Bib

Proposes an over-the-air (OTA) update framework that realizes the Software-Defined Robot (SDR) paradigm with ROS 2 and Docker. A dual public-cloud / on-premise OTA server architecture with State and Usage Loggers is designed, and container-level modular deployment on the robot PC is validated with initial-install and update shell scripts as a proof of concept.
@inproceedings{kim2025ota, title = {Design and Implementation of an OTA Update Framework for Software-Defined Robots using ROS 2 and Docker}, author = {Kim, Dong Yeop and Kim, Youngeon and Kim, Eunsu and Kim, Keunhwan and Kim, Euntai and Chung, Deok Gyoon}, booktitle = {2025 25th International Conference on Control, Automation and Systems (ICCAS)}, year = {2025}, month = nov, pages = {1994--1997}, address = {Incheon, Korea}, publisher = {IEEE}, }
ICCAS
Traversability Assessment and Path Planning Using Obstacle Recognition Information for Multi-Robot System

YoungEon Kim, Dong Yeop Kim, and Keunhwan Kim

In 2024 24th International Conference on Control, Automation and Systems (ICCAS), Oct 2024

1st author Abs Bib

1st author

Each robot detects dynamic obstacles (people) with an RGB-D camera and YOLOv8 and shares them with the RMF server. When the number of obstacles adjacent to a graph edge exceeds a predefined threshold, the edge is deactivated and affected robots proactively re-plan. Experiments with four robots show reduced collision risk and path cost compared with a non-cooperative system.
@inproceedings{kim2024traversability, title = {Traversability Assessment and Path Planning Using Obstacle Recognition Information for Multi-Robot System}, author = {Kim, YoungEon and Kim, Dong Yeop and Kim, Keunhwan}, booktitle = {2024 24th International Conference on Control, Automation and Systems (ICCAS)}, year = {2024}, month = oct, pages = {1670--1671}, address = {Jeju, Korea}, publisher = {IEEE}, }
ICROS
Method for Cross-Utilization of Obstacle Recognition Information in a Multi-Robot System for Collaborative Path Planning

Youngeon Kim, Keunhwan Kim, and Dong Yeop Kim

In Conference of the Institute of Control, Robotics and Systems (ICROS 2024), Jul 2024

1st author Abs Bib

1st author

Obstacles detected by each mobile robot with a 2D LiDAR and an RGB-D camera (YOLOv8) are transformed into the global map frame and shared so that other robots can use them for collaborative path planning. In the Open-RMF fleet manager, lanes are marked active or inactive from the shared obstacle information so that robots only travel on active lanes. Validated in Gazebo with two robots.
@inproceedings{kim2024crossutilization, title = {Method for Cross-Utilization of Obstacle Recognition Information in a Multi-Robot System for Collaborative Path Planning}, author = {Kim, Youngeon and Kim, Keunhwan and Kim, Dong Yeop}, booktitle = {Conference of the Institute of Control, Robotics and Systems (ICROS 2024)}, year = {2024}, month = jul, address = {Daejeon, Korea}, }
KROC
Cooperative Autonomous Driving System for Multi-Mobile Robots Using Open-RMF

Youngeon Kim, Keunhwan Kim, and Dong Yeop Kim

In 19th Korea Robotics Society Annual Conference (KROC 2024), Feb 2024

1st author Abs Bib

1st author

A server-client fleet management system that integrates the Open-RMF middleware with ROS Navigation, so that multiple mobile robots receive tasks from the server and drive cooperatively without collisions using RMF traffic negotiation. Feasibility was validated with real-robot experiments.
@inproceedings{kim2024openrmf, title = {Cooperative Autonomous Driving System for Multi-Mobile Robots Using Open-RMF}, author = {Kim, Youngeon and Kim, Keunhwan and Kim, Dong Yeop}, booktitle = {19th Korea Robotics Society Annual Conference (KROC 2024)}, year = {2024}, month = feb, pages = {455--456}, }

Patent

Mobile Robot Service System and Method

Youngeon Kim and others

2023

Korea Electronics Technology Institute

Bib

@misc{kim2023patent,
  title = {Mobile Robot Service System and Method},
  author = {Kim, Youngeon and others},
  howpublished = {Korean patent application, filed Dec. 2023, published Jul. 2025, under examination},
  year = {2023},
  note = {Korea Electronics Technology Institute},
}