Hogyun Kim

Hogyun Kim

Auto-generated profile, based on publicly available information

Hogyun Kim

Inha University

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
HKHogyun Kim
Hogyun Kim
JCJiwon Choi
Jiwon Choi
TSTaehu Sim
Taehu Sim
GKGiseop Kim
Giseop Kim
Younggun ChoYounggun Cho
Younggun Cho
We often encounter limited FOV situations due to various factors such as sensor fusion or sensor mount in real-world robot navigation. However, the limited FOV interrupts the generation of descriptions and impacts place recognition adversely. Therefore, we suffer from correcting accumulated drift errors in a consistent map using LiDAR-based place recognition with limited FOV. Thus, in this letter, we propose a robust LiDAR-based place recognition method for handling narrow FOV scenarios. The proposed method establishes spatial organization based on the range-elevation bin and azimuth-elevation bin to represent places. In addition, we achieve a robust place description through reweighting based on vertical direction information. Based on these representations, our method enables addressing rotational changes and determining the initial heading. Additionally, we designed a lightweight and fast approach for the robot's onboard autonomy. For rigorous validation, the proposed method was tested across various LiDAR place recognition scenarios (i.e., single-session, multi-session, and multi-robot scenarios). To the best of our knowledge, we report the first method to cope with the restricted FOV.

29 January 2024 in IEEE Sensors Letters
Verified
Journal Article
Closed access
SJSeokhwan Jeong
Seokhwan Jeong
HKHogyun Kim
Hogyun Kim
Younggun ChoYounggun Cho
Younggun Cho
Field robots require autonomy in diverse environments to navigate and map their surround-ings efficiently. However, the lack of diverse and comprehensive datasets hinders the evaluation and development of autonomous field robots. To address this challenge, we present a multimodal, multisession, and diverse terrain dataset for the ground mapping of field robots. First of all, we utilize a quadrupedal robot as a base platform to collect the dataset. Also, the dataset includes various terrain types, such as sandy roads, vegetation, and sloping terrain. It comprises RGB-D camera for ground, RGB camera, thermal camera, light detection and ranging (LiDAR), inertial measurement unit (IMU), and global positioning system (GPS). In addition, we provide not only the reference trajectories of each dataset but also the global map by leveraging LiDAR-based simultaneous localization and mapping (SLAM) algorithms. Also, we assess our dataset from a terrain perspective and generate the fusion maps, such as thermal-LiDAR and RGB-LiDAR maps to exploit the information beyond the visible spectrum.

3 October 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
HKHogyun Kim
Hogyun Kim
BCByunghee Choi
Byunghee Choi
ECEuncheol Choi
Euncheol Choi
Younggun ChoYounggun Cho
Younggun Cho
Place recognition plays an important role in achieving robust long-term autonomy. Real-world robots face a wide range of weather conditions (e.g. overcast, heavy rain, and snowing) and most sensors (i.e. camera, LiDAR) essentially functioning within or near-visible electromagnetic waves are sensitive to adverse weather conditions, making reliable localization difficult. In contrast, radar is gaining traction due to long electromagnetic waves, which are less affected by environmental changes and weather independence. In this work, we propose a radar-based lightweight and robust place recognition. We achieve rotational invariance and lightweight by selecting a one-dimensional ring-shaped description and robustness by mitigating the impact of false detection utilizing opposite noise characteristics between free space and feature. In addition, the initial heading can be estimated, which can assist in building a SLAM pipeline that combines odometry and registration, which takes into account onboard computing. The proposed method was tested for rigorous validation across various scenarios (i.e. single session, multi-session, and different weather conditions). In particular, we validate our descriptor achieving reliable place recognition performance through the results of extreme environments that lacked structural information such as an OORD dataset. Our supplementary materials and code are available at https://sites.google.com/view/referee-radar .

27 June 2025 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
GKGilhwan Kang
Gilhwan Kang
HKHogyun Kim
Hogyun Kim
BCByunghee Choi
Byunghee Choi
SJSeokhwan Jeong
Seokhwan Jeong
YSYoung-sik Shin
Young-sik Shin
Younggun ChoYounggun Cho
Younggun Cho
The unification of disparate maps is crucial for enabling scalable robot operation across multi-session, multi-robot scenarios. However, achieving a unified map robust to sensor modalities and dynamic environments remains a challenging problem. Variations in LiDAR types and dynamic elements lead to differences in point cloud distribution and scene consistency, hindering reliable descriptor generation and loop closure detection essential for accurate map alignment. To address these challenges, this paper presents Uni-Mapper, a dynamic-aware 3D point cloud map merging framework for multi-modal LiDAR systems. It comprises dynamic object removal, dynamic-aware loop closure, and multi-modal LiDAR map merging modules. A voxel-wise free space hash map is built in a coarse-to-fine manner to identify and reject dynamic objects via temporal occupancy inconsistencies. The removal module is integrated with a LiDAR global descriptor, which encodes preserved static local features to ensure robust place recognition in dynamic environments. In the final stage, centralized anchor-node-based pose graph optimization is performed to address intra- and inter-map loop closures for globally consistent map merging. Our framework is evaluated on diverse real-world datasets with dynamic objects and heterogeneous LiDARs, showing superior performance in loop detection across sensor modalities, robust mapping in dynamic environments, and accurate multi-map alignment over existing methods.

8 September 2026 in The International Journal of Robotics Research
Verified
Journal Article
Closed access
HKHogyun Kim
Hogyun Kim
JCJiwon Choi
Jiwon Choi
JKJuwon Kim
Juwon Kim
GYGeonmo Yang
Geonmo Yang
SJSeokhwan Jeong
Seokhwan Jeong
Younggun ChoYounggun Cho
Younggun Cho
By maintaining global consistency across robot teams, multi-robot light detection and ranging (LiDAR) map merging enables faster exploration and efficient area coverage. However, map merging requires exchanging massive sensor data between the server and robots, making communication the bottleneck, especially in communication-constrained environments. Therefore, we present Commerge , a communication-efficient map merging framework that achieves bandwidth reduction through graph-theoretic selective data exchange. By doing so, our Commerge reduces inter-robot communication by up to 5000× while maintaining alignment accuracy. Our key insight is that only a small subset of carefully selected scans is sufficient for robust map merging. We formulate this as a three-stage cascaded optimization problem on an exchange graph, where vertices represent robot keyframes and edges denote candidate inter-robot loops. Through three cascade stages, we select a sequentially overlapped, balanced-transmission-cost, and geometrically-perceptually optimal scan subset that preserves alignment quality while reducing communication. Unlike existing approaches that either transmit whole scans, which require GB-scale data exchange, or employ naïve downsampling, our approach exchanges only MB-scale data while achieving comparable alignment accuracy. Extensive evaluation on five public datasets and four in-house datasets covering cave, planetary-analog, indoor, and outdoor campus environments shows up to 99.98% reduction in data exchange (e.g., from 7000 MB to 1.3 MB on the HeLiPR dataset), while maintaining alignment performance across embedded to desktop platforms. Furthermore, we demonstrate that our proposed framework operates on resource-constrained hardware where existing methods fail, enabling real-world multi-robot deployment in bandwidth-limited field operations. Finally, we validate system robustness under a real-world non-line-of-sight (NLOS) communication environment with up to 73.3% dropout rate, as well as under emulated network degradation scenarios including delay, bandwidth limitation, and packet loss, confirming reliable map merging even under severely degraded connectivity.

30 April 2025 in The Journal of Korean Institute of Information Technology
Verified
Journal Article
Closed access
SJSeokhwan Jeong
Seokhwan Jeong
HKHogyun Kim
Hogyun Kim
JKJuwon Kim
Juwon Kim
Younggun ChoYounggun Cho
Younggun Cho
본 논문에서는 다중 로봇 시스템이 운영되는 실외 환경에서 타겟이 손상된 상황에서도 적용 가능한 새로운 구체 타겟 기반 LiDAR와 카메라 간의 외부 캘리브레이션 방법을 제안한다. 카메라의 경우, 작은 크기의 구체 타겟을 효과적으로 추출하기 위해 SAM(Segment Anything Model)을 활용한다. LiDAR의 경우, 구체 타겟에는 평평한 영역이 없어 노이즈가 불가피하므로, 누적된 포인트클라우드에 가중합을 적용하여 정확한 구체 중심을 추출한다. 실험을 통해 카메라와 세 종류의 LiDAR에서 제안된 방법을 평가하였다. 제안한 접근 방식은 타겟이 손상된 상황에서도 강건하게 타겟을 검출하였으며, 정확도 측면에서 기존 방법 대비 재투영 오차에서 평균 92.51%의 성능 개선을 보여줬다.